SYSTEM AND METHOD FOR MANAGEMENT OF VARIABLE AIR VOLUME UNIT IN A FACILITY

Description

TECHNICAL FIELD OF INVENTION

Various embodiments of the present disclosure relate generally to variable air volume (VAV) systems and more particularly to system and method for managing VAV units/systems in a facility.

BACKGROUND

In facilities such as commercial/industrial buildings, Variable Air Volume (VAV) system is widely used in a Heating Ventilation and Air-conditioning (HVAC) system. Common failures in VAV system may include actuator jamming/seizing, measured airflow being significantly lower than actual airflow, inability to effectively control airflow, and/or the like. In some instances, components of the VAV system may fail over a time due to deterioration of airflow station, dry out, duct leaks, or loosening. Typically, the common failures are detected by identifying the open position of damper actuator, which leads to maximum airflow. As a result, the air flow handler may increase air flow volume to maintain required static pressure and that leads to supplying of air more than a requirement. At the same time, for occupants, this often leads to excessive airflow and noise, and thus complicating temperature control in facilities like commercial buildings. Significant or multiple failures can result in insufficient airflow from the air flow handler, causing low airflow issues in other areas of the building. Overall, failures in the VAV system leads to higher utility costs and decreased occupant satisfaction.

When it comes to energy optimization, energy loss is at times due to malfunction of VAV. There may be several reasons to this such as, but not limited to VAV Controller failure, damper malfunction, disconnection of air ducts/tubes, overflow of air in VAV, underflow of air in VAV, and sensor issue (e.g. thermostat issue, air flow sensor or air flow meter malfunction, etc. ,). Currently, there is no mechanism in place to identify root cause of the failures in VAVs. Usually, in VAV systems, parameters such as damper positions, cubic feet per minute (CFM) Flow, temperature setpoints/configurations and zone temperatures are usually monitored by building management system (BMS), but some challenging issues are still undetectable by an operator using the parameters alone. These challenging issues are mostly captured during a period of preventive maintenance that happens say, in every quarter/half year by vendor of the BMS. For instance, some challenging issues include but are not limited to inconsistent damper stuck issues, delayed response of the VAV system after configuring temperature setpoints, and incorrect CFM displays as per open/close conditions. Therefore, there is a need for system and method to identify problems in VAV units and generate alerts for facility managers/operators thereby to enable real-time response and guidance on taking necessary corrective actions to resolve issues promptly.

The background description provided herein is for the purpose of generally presenting the context of the disclosure. Unless otherwise indicated herein, the materials described in this section are not prior art to the claims in this application and are not admitted to be prior art, or suggestions of the prior art, by inclusion in this section.

SUMMARY

According to certain aspects of the disclosure, systems and methods for managing Variable Air Volume (VAV) units in a facility are described.

According to one aspect, embodiments of the present invention feature a method for managing VAV units in a facility is performed by a processor. Initially, the processor receives sensor data from a plurality of sensors associated with a Variable Air Volume (VAV) system in real-time. The VAV system comprises one or more components. Further, the processor retrieves historical data associated with at least one component of the one or more components from a database. Then, the processor compares the sensor data with configuration data of the at least one component and the historical data. Further, the processor determines at least one anomaly in one or more operations of the at least one component based on the comparison. The at least one anomaly is determined using a machine learning (ML) model. Further, the processor identifies at least one corrective action to modify one or more operations of the at least one component in real-time based on the at least one anomaly. Furthermore, the processor renders one or more notifications to an operator via a user interface, based on the at least one corrective action to modify the one or more operations of the at least one component.

In some embodiments, the sensor data comprises at least: actual air flow rate data, damper position data, and actual zone temperature.

In some embodiments, the method further comprises triggering at least one control signal to adjust the one or more operations of the at least one component of the VAV system based on the at least one corrective action.

In some embodiments, the method further comprises training the ML model to detect anomalies in the one or more operations of the at least one component of the VAV system based on at least: configured rules, operator feedback, and predictions associated with configuration data of the VAV system. The ML model is trained to detect operation anomalies of the VAV system using the sensor data and the historical data.

In some embodiments, the historical data associated with the plurality of sensors comprises at least: operational status of one or more VAV controller associated with the VAV system, configuration of temperature at the VAV controller, operational status of Air handling Unit (AHU), the configuration data and maintenance data of the one or more components associated with the VAV system.

In some embodiments, the one or more components of the VAV system comprises at least: a Variable Air Volume (VAV) controller, a damper, a plurality of air ducts/tubes, a plurality of air flow sensors or air flowmeter, a plurality of temperature sensors, and other plurality of sensors associated with the VAV system.

In some embodiments, the method further comprises obtaining operational status of the VAV controller and other VAV controllers that are connected to the VAV system. The method further comprises comparing the operational status of the VAV controller with at least: historical data associated with the VAV controller, the operational status of the other VAV controllers, and a user input. The method further comprises determining the at least one anomaly associated with the VAV controller due to at least one of: power outage of the VAV controller, and a network cable disconnection based on comparison of the operational status of the VAV controller using the ML model.

In some embodiments, the method further comprises configuring temperature for a specified zone at the VAV controller. The method then comprises comparing the configured temperature with an actual temperature at the specified zone. The method further comprises receiving a damper position data from the plurality of sensors. The method further comprises comparing the damper position data with an expected damper position data based on the configured temperature and historical data associated with a damper. The method then comprises determining the at least one anomaly associated with a damper stuck or an actuator malfunction based on comparison of the damper position data with the expected damper position data using the ML model.

In some embodiments, the method further comprises receiving an actual CFM value based on air flow data measured by the plurality of sensors at a specified area/zone. The method then comprises acquiring a configured CFM value using configuration data of the VAV controller at the specified area/zone and historical data associated with the air flow data measured from the database. The method further comprises determining an expected CFM value based on volume of the specified area/zone. The method further comprises identifying whether the actual CFM is below or above a threshold based on comparison of the actual CFM with the configured CFM value and the expected CFM value. The method further comprises determining the at least one anomaly associated with a damper malfunction or a disconnection of air duct using the ML model based on identification that the actual CFM value and the historical data.

In some embodiments, the method further comprises receiving actual air flow, actual zone temperature and damper position data from the plurality of sensors at the specified area/zone. The method further comprises acquiring configuration of temperature at the VAV controller from the database and operational status of Air handling unit (AHU). The method further comprises identifying absence of the actual air flow based on analysis of the actual zone temperature, the configuration of temperature at the VAV controller, operational status of AHU, and position of the damper. The method further comprises determining the at least one anomaly associated with disconnection of air ducts based on identification of absence of the actual air flow data using the ML model.

In some embodiments, the method further comprises receiving actual sensor data from a plurality of sensors at a specified zone and neighboring zone. Then the method comprises retrieving customized sensor parameters from configuration data of the plurality of sensors, and baseline value from historical data associated with the plurality of sensors. The method then comprises comparing the actual sensor data with the customized sensor parameters and historical data. Further, the method comprises determining at least one anomaly associated with thermostat malfunction at the specified area/zone based on comparison of the actual sensor data with the customized sensor parameters and the historical data using the ML model.

According to another aspect, example embodiments of the present disclosure include a system comprising one or more processors and a memory and one or more programs stored in the memory. The one or more programs executed by the one or more processors comprising instructions configured to: receive sensor data from a plurality of sensors associated with a Variable Air Volume (VAV) system. The VAV system comprises one or more components. The processor is configured to retrieve historical data associated with at least one component of the one or more components from a database. Then the processor is configured to compare the sensor data with configuration data of the at least one component and the historical data. Then the processor is configured to determine at least one anomaly in one or more operations of the at least one component based on the comparison. The at least one anomaly is determined using a machine learning (ML) model. Further, the processor is configured to identify at least one corrective action to modify one or more operations of the at least one component in real-time based on the at least one anomaly. Then the processor is configured to render via a user interface one or more notifications to an operator based on the at least one corrective action to modify the one or more operations of the at least one component.

In some embodiments, the sensor data comprises at least: actual air flow rate data, damper position data, and actual zone temperature.

In some embodiments, the processor is configured to trigger at least one control signal to adjust the one or more operations of the at least one component of the VAV system based on the at least one corrective action.

In some embodiments, the processor is configured to train the ML model to detect anomalies in the one or more operations of the at least one component of the VAV system based on at least: configured rules, operator feedback, and predictions associated with configuration data of the VAV system. The ML model is trained to detect operation anomalies of the VAV system using the sensor data and the historical data.

In some embodiments, the historical data associated with the plurality of sensors comprises at least: operational status of one or more VAV controller associated with the VAV system, configuration of temperature at the VAV controller, operational status of Air handling Unit (AHU), the configuration data and maintenance data of the one or more components associated with the VAV system.

In some embodiments, the one or more components of the VAV system comprises at least: a Variable Air Volume (VAV) controller, a damper, a plurality of air ducts/tubes, a plurality of air flow sensors or air flowmeter, a plurality of temperature sensors, and other plurality of sensors associated with the VAV system.

In some embodiments, further the processor is configured to obtain operational status of the VAV controller and other VAV controllers that are connected to the VAV system. Further, the processor is configured to compare the operational status of the VAV controller with at least: historical data associated with the VAV controller, the operational status of the other VAV controllers, and a user input. Further, the processor is configured to determine the at least one anomaly associated with the VAV controller due to at least one of: power outage of the VAV controller, and a network cable disconnection based on comparison of the operational status of the VAV controller using the ML model.

In some embodiments, further the processor is configured to configure temperature for a specified zone at the VAV controller. Then, the processor is configured to compare the configured temperature with an actual temperature at the specified zone. Further, the processor is configured to receive a damper position data from the plurality of sensors. Then, the processor is configured to compare the damper position data with an expected damper position data based on the configured temperature and historical data associated with a damper. Further, the processor is configured to determine the at least one anomaly associated with a damper stuck or an actuator malfunction based on comparison of the damper position data with the expected damper position data using the ML model.

In some embodiments, the processor is further configured to receive an actual CFM value based on air flow data measured by the plurality of sensors at a specified area/zone. The processor is further configured to acquire a configured CFM value using configuration data of the VAV controller at the specified area/zone and historical data associated with the air flow data measured from the database. The processor is further configured to determine an expected CFM value based on volume of the specified area/zone. the processor is further configured to identify whether the actual CFM is below or above a threshold based on comparison of the actual CFM with the configured CFM value and the expected CFM value. The processor is further configured to determine the at least one anomaly associated with a damper malfunction or a disconnection of air duct using the ML model based on identification that the actual CFM value and the historical data.

In some embodiments, the processor is further configured to receive actual air flow, actual zone temperature and damper position data from the plurality of sensors at the specified area/zone. The processor is further configured to acquire configuration of temperature at the VAV controller from the database and operational status of Air handling unit (AHU). The processor is further configured to identify absence of the actual air flow based on analysis of the actual zone temperature, the configuration of temperature at the VAV controller, operational status of AHU, and position of the damper. The processor is further configured to determine the at least one anomaly associated with disconnection of air ducts based on identification of absence of the actual air flow data using the ML model.

In some embodiments, the processor is further configured to receive actual sensor data from a plurality of sensors at a specified zone and neighboring zone. Then the processor is further configured to retrieve customized sensor parameters from configuration data of the plurality of sensors, and baseline value from historical data associated with the plurality of sensors. The processor is further configured to compare the actual sensor data with the customized sensor parameters and historical data. Further, the processor is further configured to determine at least one anomaly associated with thermostat malfunction at the specified area/zone based on comparison of the actual sensor data with the customized sensor parameters and the historical data using the ML model.

According to another aspect, embodiments of the present invention feature a computer program product comprising at least one non-transitory computer-readable storage medium having computer-readable program code portions stored therein. The computer-readable program code portions comprise an executable portion configured to: receive sensor data from a plurality of sensors associated with a Variable Air Volume (VAV) system. The VAV system comprises one or more components; retrieve historical data associated with at least one component of the one or more components from a database; compare the sensor data with configuration data of the at least one component and the historical data; determine at least one anomaly in one or more operations of the at least one component based on the comparison, here the at least one anomaly is determined using a machine learning (ML) model; identify at least one corrective action to modify one or more operations of the at least one component based on the at least one anomaly; and render via a user interface one or more notifications to an operator based on the at least one corrective action to modify the one or more operations of the at least one component.

The above summary is provided merely for the purpose of summarizing some example embodiments to provide a basic understanding of some aspects of the present disclosure. Accordingly, it will be appreciated that the above-described embodiments are merely examples and should not be construed to narrow the scope or spirit of the present disclosure in any way. It will be appreciated that the scope of the present disclosure encompasses many potential embodiments in addition to those here summarized, some of which will be further described below. Other features, aspects, and advantages of the subject will become apparent from the description, the drawings, and the claims.

BRIEF DESCRIPTION OF THE DRAWINGS

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate various exemplary embodiments and together with the description, serve to explain the principles of the disclosed embodiments.

FIG. 1 illustrates a schematic block diagram showing an exemplary implementation of a facility management system for management of Variable Air Volume (VAV) unit/system in a facility in accordance with one or more example embodiments described herein.

FIG. 2 illustrates a schematic diagram showing an exemplary network arrangement for management of Variable Air Volume (VAV) unit/system in a facility that may execute techniques in accordance with one or more example embodiments described herein.

FIG. 3 illustrates an exemplary method for managing the VAV system in a facility in accordance with one or more example embodiments described herein.

FIG. 4 illustrates an exemplary method for managing the VAV system in a facility to identify anomaly associated with VAV controller in accordance with one or more example embodiments described herein.

FIG. 5 illustrates an exemplary method for managing the VAV system in a facility to identify anomaly associated with a damper in accordance with one or more example embodiments described herein.

FIG. 6 illustrates an exemplary method for managing the VAV system in a facility to identify anomaly associated with underflow/overflow of air in accordance with one or more example embodiments described herein.

FIG. 7 illustrates an exemplary method for managing the VAV system in a facility to identify anomaly associated with disconnection of air ducts/tubes in accordance with one or more example embodiments described herein. and

FIG. 8 illustrates an exemplary method for managing the VAV system in a facility to identify anomaly with respect to a plurality of sensors that are associated with VAV system in accordance with one or more example embodiments described herein.

DETAILED DESCRIPTION

Reference will now be made in detail to embodiments, examples of which are illustrated in the accompanying drawings. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the various described embodiments. However, it will be apparent to one of ordinary skill in the art that the various described embodiments may be practiced without these specific details. In other instances, well-known methods, procedures, components, circuits, and networks have not been described in detail so as not to unnecessarily obscure aspects of the embodiments.

As used herein, the term “comprising” means including but not limited to and should be interpreted in the manner it is typically used in the patent context. Use of broader terms such as comprises, includes, and having should be understood to provide support for narrower terms such as consisting of, consisting essentially of, and comprised substantially of.

The phrases “in one embodiment,” “according to one embodiment,” “in some embodiments,” and the like generally mean that the particular feature, structure, or characteristic following the phrase may be included in at least one embodiment of the present disclosure, and may be included in more than one embodiment of the present disclosure (importantly, such phrases do not necessarily refer to the same embodiment).

The word “example” or “exemplary” is used herein to mean “serving as an example, instance, or illustration.” Any implementation described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other implementations.

If the specification states a component or feature “may,” “can,” “could,” “should,” “would,” “preferably,” “possibly,” “typically,” “optionally,” “for example,” “often,” or “might” (or other such language) be included or have a characteristic, that a specific component or feature is not required to be included or to have the characteristic. Such a component or feature may be optionally included in some embodiments, or it may be excluded.

The use of the term “circuitry” as used herein with respect to components of a system or an apparatus should be understood to include particular hardware configured to perform the functions associated with the particular circuitry as described herein. The term “circuitry” should be understood broadly to include hardware and, in some embodiments, software for configuring the hardware. For example, in some embodiments, “circuitry” may include processing circuitry, communication circuitry, input/output circuitry, and the like. In some embodiments, other elements may provide or supplement the functionality of particular circuitry. Alternatively or additionally, in some embodiments, other elements of a system and/or apparatus described herein may provide or supplement the functionality of another particular set of circuitry. For example, a processor may provide processing functionality to any of the sets of circuitry, a memory may provide storage functionality to any of the sets of circuitry, communications circuitry may provide network interface functionality to any of the sets of circuitry, and/or the like.

The term “electronically coupled,” “electronically coupling,” “electronically couple,” “in communication with,” “in electronic communication with,” or “connected” in the present disclosure refers to two or more elements or components being connected through wired means and/or wireless means, such that signals, electrical voltage/current, data and/or information may be transmitted to and/or received from these elements or components.

The term “VAV system” refers to Variable Air Volume system in the HVAC system. The VAV system controls operations of the VAV controller to control the flow of air to a specific area or zone or space in a HVAC facility management unit according to configuration made by an operator or user. The VAV system can be a standalone system or may be integrated with a third-party building management system.

The term “VAV controller” refers to “Variable Air Volume Controller” for controlling the VAV box to control the flow of air to a specific area or zone or space in a HVAC facility management unit according to configuration made by an operator or user.

The term “VAV Box” or “edge device” refers to “Variable Air Volume box” for controlling the flow of air to a specific area or zone or space in a HVAC facility management unit according to requirement configured at the VAV controller. The VAV box includes components that includes but is not limited to one or more dampers, one or more position sensors, one or more actuators, one or more air ducts/tubes connected to an air handling unit (AHU), one or more air ducts connecting the VAV box outlet/vent and the space/zone or area at the facility and the like.

The term “BMS” is a building management system and refers to a centralized control system that monitors and manages various building systems and services to improve efficiency, comfort, and security.

The term “CFM” refers to cubic feet per minute and CFM is a critical measurement used to assess the airflow within a system. That is, CFM measures the volume of air delivered or exhausted by the system per minute and helps determine whether the system can adequately heat or cool a space.

The term “facility” refers to the systems, components, and infrastructure that work together to maintain comfortable indoor environments in buildings. Management and maintenance of these (Heating, Ventilation, and Air Conditioning) HVAC facilities are essential for ensuring energy efficiency, occupant comfort, and air quality in smart building management.

Various embodiments of the present disclosure relate generally to systems and methods for managing VAV units in a facility. Specifically, embodiments of the present disclosure provide a system and a method for optimizing energy in VAV systems in real-time. A processor coupled with a memory is configured to perform operations of the system and method. The processor initially receives sensor data from a plurality of sensors associated with Variable Air Volume (VAV) system in real-time. The sensor data includes but is not limited to air flow status, damper position, and zone temperature sensor. Then, the processor obtains historical data associated with the plurality of sensors. The historical data can either be created within the building management system or previously collected raw data. The raw data is processed through machine learning platforms such as, for example Databricks™. The sensor data and the historical data are stored in memory of the VAV system or a server of the BMS system. The processor, using a machine learning (ML) model, determines at least one anomaly in at least one component of the VAV system based at least in part on the sensor data and the historical data. Here, the machine learning (ML) model is trained to detect the anomalies and deviations from the baseline that indicate the airflow issue, or malfunction. Techniques like regression analysis, anomaly detection, and clustering algorithms can be employed to train the ML model. The processor identifies at least one corrective action to modify operation of the at least one component in real-time based on the at least one anomaly. The identified anomaly and the corrective action are reported to the operator through a user interface (UI) as a notification, alarm/alert, or report. Further, the corrective action is notified to the operator regarding the issues through medium such as SMS or Email in real-time.

The processor generates a comprehensive report that includes detailed descriptions of various issues, recommendations for corrective actions, and percentage of improvements from the previous year to the current year. The user interface allows the users to easily monitor system performance and take necessary actions. In addition, the UI also receives feedback or input from the operator with which further predictions of corrective action can be developed/implemented. The historical data includes but is not limited to a frequency of damper stuck for a specified period, delayed response of VAV operation after configuration of the temperature setpoints, and incorrect Cubic Feet per Minute (CFM) displays as per open/close conditions. The anomalies in the components of VAV includes but are not limited to controller failure, damper malfunction, disconnection of air ducts/tubes, overflow/under flow of air in VAV, and sensor malfunction (Thermostat issue). The machine learning (ML) model is trained to detect the anomalies and deviations from the baseline that indicate the airflow issue, or malfunction.

The procedures/rules for detection of each of the anomalies and corrective actions or recommendations used by the ML model are described further in relation with FIG. 1 to FIG. 8.

FIG. 1 illustrates a schematic block diagram showing an exemplary implementation of a facility management system or system 100 for management of Variable Air Volume (VAV) system/unit 102 in a facility that may execute techniques in accordance with one or more example embodiments described herein. Referring to FIG. 1, in one or more example embodiments, the facility management system 100 comprises a building management system (BMS) 108, a VAV unit/system 102, one or more VAV controllers 110, one or more Air handling unit (AHU) 116, one or more edge devices/VAV Boxes 112, a server/router 126, and a plurality of sensors or sensors 114. The VAV system 102 is integrated with the BMS 108 or third-party integrators in the facility. The VAV system 102 described herein may include a set of instructions that can be executed to cause the VAV system 102 to perform any one or more of the methods or computer-based functions disclosed herein. The VAV system 102 may operate as a standalone device or may be connected, e.g., using a network, to other computer systems or peripheral devices.

In some embodiments, the VAV system 102 may be operably coupled to the one or more components such as the one or more VAV controllers 110, the one or more Air handling unit (AHU) 116, the one or more edge devices/VAV Boxes 112, the server/router 126, and the plurality of sensors 114 and other devices associated with the facility management system 100. In some embodiments, the VAV system 102 may be operably coupled to the plurality of sensors 114 associated with different types of components within the VAV box 112 and the VAV controllers 110. In this regard, the plurality of sensors 114 often comprises sensors such as air flow sensor 120 (e.g. air flowmeter), temperature sensors 124, and damper position sensors 122. Additionally, the plurality of sensors 114 may also comprise cameras, pressure sensors, temperature sensors, and/or the like. As per this aspect, the one or more sensors of the plurality of sensors 114 sense data such as cubic feet per minute (CFM) flow, zone temperature, temperature setpoints, damper positions and so on. This data sensed by the plurality of sensors 114 may correspond to telemetry data (alternatively referred to as sensor data as well). Additionally, the telemetry data includes data such as, but not limited to maximum flow setpoint, minimum flow setpoint, information regarding designed area/zone, K-factor, raw values (say, for instance, unformatted values) of temperature and pressure inputs, and/or the like associated with the VAV system. Further, in some example embodiments, the one or more sensors transmit the telemetry data to the VAV system 102. For example, the air flow sensor can be used to detect an operational set point of air flow through the VAV boxes 112. In this regard, the air flow sensor transmits the operational set point to a corresponding VAV system 102.

Methods, systems, and computer program products of the present disclosure may be embodied by any of a variety of devices. For example, the method, systems, and computer program product of an example embodiment may be embodied by a networked device (e.g., a VAV system 102), such as a server or other network entity, configured to communicate with one or more devices, such as one or more client devices. Additionally, or alternatively, the computing device may include fixed computing devices, such as a personal computer or a computer workstation. Additionally, or alternatively, example embodiments may be embodied by any of a variety of mobile devices, such as a portable digital assistant (PDA), mobile telephone, smartphone, laptop computer, tablet computer, wearable, or any combination of the aforementioned devices.

As illustrated in FIG. 1, the VAV system 102 may include a processor 104, e.g., a central processing unit (CPU), a graphics processing unit (GPU), or both. The processor 104 may be a component in a variety of systems. For example, the processor 104 may be part of a standard computer. The processor 104 may be one or more general processors, digital signal processors, application specific integrated circuits, field programmable gate arrays, servers, networks, digital circuits, analog circuits, combinations thereof, or other now known or later developed devices for analyzing and processing data. The processor 104 may implement a software program, such as code generated manually (i.e., programmed).

The VAV system 102 may include a memory 106 that can communicate via a bus. The memory 106 may be a main memory, a static memory, or a dynamic memory. The memory 106 may include but is not limited to computer readable storage media such as various types of volatile and non-volatile storage media, including but not limited to random access memory, read-only memory, programmable read-only memory, electrically programmable read-only memory, electrically erasable read-only memory, flash memory, magnetic tape or disk, optical media and the like. In one implementation, the memory 106 includes a cache or random-access memory for the processor 104. In alternative implementations, the memory 106 is separate from the processor 104, such as a cache memory of a processor, the system memory, or other memory. The memory 106 may be an external storage device or database for storing data. Examples include a hard drive, compact disc (“CD”), digital video disc (“DVD”), memory card, memory stick, floppy disc, universal serial bus (“USB”) memory device, or any other device operative to store data such as historical data and the like. The memory 106 is operable to store instructions executable by the processor 104. The functions, acts or tasks illustrated in the figures or described herein may be performed by the processor 104 executing the instructions stored in the memory 106. The functions, acts or tasks are independent of the particular type of instructions set, storage media, processor or processing strategy and may be performed by software, hardware, integrated circuits, firmware, micro-code and the like, operating alone or in combination. Likewise, processing strategies may include multiprocessing, multitasking, parallel processing and the like.

As shown, the VAV system 102 may further include a user interface or display 128, such as a liquid crystal display (LCD), an organic light emitting diode (OLED), a flat panel display, a solid-state display, a cathode ray tube (CRT), a projector, a printer or other now known or later developed display device for outputting determined information. The display 128 may act as an interface for the user to see the functioning of the processor 104, or specifically as an interface with the software stored in the memory 106 or in the drive unit. Additionally, the VAV system 102 may include an input/output device (not shown in figure) configured to allow a user to interact with any of the components of VAV system 102. The input/output device may be a number pad, a keyboard, or a cursor control device, such as a mouse, or a joystick, touch screen display, remote control, or any other device operative to interact with the VAV system 102. The VAV system 102 may also or alternatively include drive unit (not shown in figure) implemented as a disk or optical drive. The drive unit may include a computer-readable medium in which one or more sets of instructions, e.g. software, can be embedded. Further, the instructions may embody one or more of the methods or logic as described herein. The instructions may reside completely or partially within the memory 106 and/or within the processor 104 during execution by the VAV system 102. The memory 106 and the processor 104 also may include computer-readable media as discussed above.

In some systems, a computer-readable medium includes instructions or receives and executes instructions responsive to a propagated signal so that a device connected to a network can communicate voice, video, audio, images, or any other data over the network. Further, the instructions may be transmitted or received over the network via a communication port or interface, and/or using a bus. The communication port or interface may be a part of the processor or may be a separate component. The communication port or interface may be created in software or may be a physical connection in hardware. The communication port or interface may be configured to connect with a network, external media, the display, or any other components in controller, or combinations thereof. The connection with the network may be a physical connection, such as a wired Ethernet connection or may be established wirelessly as discussed below. Likewise, the additional connections with other components of the VAV system 102 may be physical connections or may be established wirelessly. The network may alternatively be directly connected to a bus.

While the computer-readable medium is shown to be a single medium, the term “computer-readable medium” may include a single medium or multiple media, such as a centralized or distributed database, and/or associated caches and servers that store one or more sets of instructions. The term “computer-readable medium” may also include any medium that is capable of storing, encoding, or carrying a set of instructions for execution by a processor or that cause a computer system to perform any one or more of the methods or operations disclosed herein. The computer-readable medium may be non-transitory, and may be tangible. The computer-readable medium can include a solid-state memory such as a memory card or other package that houses one or more non-volatile read-only memories. The computer-readable medium can be a random-access memory or other volatile re-writable memory. Additionally or alternatively, the computer-readable medium can include a magneto-optical or optical medium, such as a disk or tapes or other storage device to capture carrier wave signals such as a signal communicated over a transmission medium. A digital file attachment to an e-mail or other self-contained information archive or set of archives may be considered a distribution medium that is a tangible storage medium. Accordingly, the disclosure is considered to include any one or more of a computer-readable medium or a distribution medium and other equivalents and successor media, in which data or instructions may be stored.

In an alternative implementation, dedicated hardware implementations, such as application specific integrated circuits, programmable logic arrays and other hardware devices, can be constructed to implement one or more of the methods described herein. Applications that may include the apparatus and systems of various implementations can broadly include a variety of electronic and computer systems. One or more implementations described herein may implement functions using two or more specific interconnected hardware modules or devices with related control and data signals that can be communicated between and through the modules, or as portions of an application-specific integrated circuit. Accordingly, the present system encompasses software, firmware, and hardware implementations.

Referring to FIG. 1, the processor 104 coupled with the memory 106 is configured to perform operations of the VAV system 102. The VAV system 102 includes one or more components. The one or more components associated with the VAV system 102 includes but are not limited to one or more Variable Air Volume (VAV) controllers 110, one or more dampers, a plurality of air ducts/tubes, a plurality of air flow sensors or air flowmeter 120, and a plurality of sensors 114 associated with the VAV system 102. Initially, the processor 104 is configured to receive sensor data or telemetry data from the plurality of sensors 114 associated with Variable Air Volume (VAV) system in real-time. The sensor data includes data such as, but not limited to actual air flow rate/cubic feet per minute (CFM) flow data, damper position data, and actual zone temperature. Additionally, the sensor data may also include data such as, but not limited to maximum flow setpoint, minimum flow setpoint, designed area, K-factor, raw values (say, for instance, unformatted values) of temperature, pressure inputs and the like. The actual air flow rate data is referred as data associated with volume of air that is transferred through the VAV box 112 to a specified zone or area 118 for a specific period of time. The volume of the air or CFM flow data measured at the VAV controller 110. That is, air flow rate through the air ducts/tubes for a predetermined time. The air ducts/tubes may be connected to the VAV system 102. The air flow rate can be measured using one or more air flow sensors 120 or flowmeter or one or more air flow sensors associated with the VAV box/edge device 112. The damper position data can be referred as data associated with position of the damper provided in the VAV box/edge device 112 and can be measured using a position sensor 122 and/or an actuator associated with the damper. For example, the damper position data may include details but is not limited to damper position is 50% open or 100% open and the like. The actual zone temperature can be referred as temperature measured at the specified zone 118 at the predetermined time. The actual zone temperature can be measured by the temperature sensors provided at the specified zone or area 118. The specified zone or area 118 is in the facility and the specified zone or area is associated with the VAV box/edge device.

The processor 104 is configured to retrieve configuration data of the one or more components and historical data associated with at least one component of the one or more components from a database. The historical data can either be created within the building management system 108 or previously collected raw data. The raw data is processed through machine learning platforms such as Databricks™. The historical data associated with the one or more components may include data such as, but not limited to operational status (i.e. active or inactive) of one or more VAV controllers 110 associated with the VAV system 102, configuration of temperature (i.e. temperature setpoints) at the VAV controller 110, operational status (i.e. active or inactive) of Air handling Unit (AHU), the configuration data (design or customized data or data at specification sheet), maintenance data (i.e. quarterly or yearly preventive maintenance reports or records) of the one or more components associated with the VAV system, and/or the like. The configuration data of the one or more components associated with the VAV system 102 may include design parameters or customized parameters for specific components in the one or more components associated with the VAV system 102 and other similar data. The maintenance data of the one or more components associated with the VAV system 102 may include but is not limited to quarterly or yearly maintenance data, data associated with repairs, data associated with malfunction of one or more components, and/or the like. For instance, during preventive maintenance performed in every quarter/half yearly by operators or BMS vendors, the maintenance data of the one or more components associated with the VAV system 102 can be captured. During the preventive maintenance of the one or more components, some anomalies can be identified. The anomalies may include but are not limited to inconsistent damper stuck issues throughout the year, delayed response of the VAV system 102 after configuring temperature setpoints, and incorrect CFM displays as per open/close conditions and so on. These anomalies are recorded during the preventive maintenance of the one or more components and can be used as the historical data. The sensor data and the historical data may be stored in the database or the memory 106 of the VAV system 102 or a server 126 of the BMS system 108. The processor 104 is configured to compare the sensor data with the configuration data and the historical data associated with the one or more components of the VAV system 102. The processor 104 may perform the comparison by evaluating the desired or expected air flow or air flow rate and the actual sensor data at a particular configuration/setting of the VAV controller 110.

The processor 104 is configured to determine one or more anomalies in one or more operations of the at least one component of the one or more components based on the comparison of the sensor data with the configuration data and the historical data associated with the one or more components of the VAV system 102. The one or more anomalies are determined using a machine learning (ML) model. The processor 104 may determine at least one anomaly in at least one component of the VAV system 102 based at least in part on the sensor data and the historical data associated with the one or more components. The machine learning (ML) model is trained to detect the anomalies and deviations from a baseline value that indicate the airflow issue, or malfunction and the like. Further, the processor 104 is configured to train the ML model to detect anomalies in the one or more operations of the at least one component of the VAV system based on at least: configured rules, operator feedback, and predictions associated with configuration data of the VAV system 102. The ML model is trained to detect operation anomalies of the VAV system 102 using the sensor data and the historical data. Techniques like regression analysis, anomaly detection, and clustering algorithms can be employed to train the ML model. For example, if the actual air flow is zero, then the ML model may check at least whether the temperature setpoint is less than the actual temperature, the AHU in the specific Zone is ON, the damper Position is 100% open. As a result of the analysis, machine learning algorithm of the ML model detects the issue as disconnection of air ducts/tubes and the incident will be reported instantly to the operator.

In some embodiments, the processor 104 is configured to identify one or more corrective actions to modify one or more operations of the one or more component in real-time based on the one or more anomalies determined by the processor 104 using ML model. The corrective action may include but is not limited to recommendation for replacement of the one or more components associated with the VAV system 102 that is identified with the one or more anomalies, rectifying errors due to network cable connection with the VAV controller 110, fixing air duct leakages, triggering control signal automatically to restart the VAV controller 110, and the like. Further, the corrective action may also include but not limited to triggering of control signal automatically to shut down operations until recovery of a particular VAV controller 110 that is identified with anomaly thereby to control excess energy utilization.

In some embodiments, the processor 104 is configured to render one or more notifications to an operator based on the one or more corrective actions to modify the one or more operations of the at least one component. The identified anomaly and the one or more corrective actions are reported to the operator through a user interface (UI) 128 as a notification that include at least a text message, alarm/alert, an audio prompt, or a detailed report. The UI 128 is integrated with the VAV system. Alternatively, the UI 128 can be integrated with the BMS 108 in the facility. The User interface 128 is provided with a user-friendly dashboard to display status of the one or more VAV controller and status of the one or more edge device, alerts/alarms, notifications and required one or more corrected actions. The user interface 128 may allow users to monitor performance of the VAV system 102 and perform corrective actions accordingly to resolve the one or more anomalies identified at the one or more components associated with the VAV system 102. The corrective action may be notified to the user/operator regarding the one or more anomalies through a medium such as SMS or Email in real-time.

In some embodiments, the processor 104 may be configured to generate a comprehensive report that includes detailed descriptions of various issues, recommendations for corrective actions, and percentage of improvements from the previous year to the current year. The user interface may allow the users to easily monitor system performance and take necessary actions manually or triggering control signals to resolve the one or more anomalies automatically. In some embodiments, the processor 104 is configured to trigger at least one control signal to adjust the one or more operations of the at least one component of the VAV system 102 based on the at least one corrective action. Also, the user interface 128 may allow the user to provide one or more inputs to the BMS 108 as well. For instance, the UI 128 receives feedback or input from the operator with which further predictions of corrective action can be developed/implemented. The historical data associated with the one or more components may include but is not limited to a frequency of damper stuck for a predefined duration, delayed response of VAV operation after configuration of the temperature setpoints, and incorrect Cubic Feet per Minute (CFM) displays as per open/close conditions of the damper. The one or more anomalies in one or more operations of the at least one component of the one or more components may include but are not limited to controller failure, damper malfunction, disconnection of air ducts/tubes, overflow/under flow of air in VAV, and sensor malfunction (Thermostat issue). The machine learning (ML) model is trained to detect the anomalies and deviations from the baseline that indicate the airflow issue, or malfunction. The procedures/rules for detection of each of the anomalies and corrective actions or recommendations used by the ML model are described further in detail in FIG. 3 to FIG. 8.

FIG. 2 illustrates a schematic block diagram showing an exemplary network arrangement 200 for management of Variable Air Volume (VAV) unit/system (as described in FIG. 1) in a facility in which embodiments of the present disclosure may operate. Referring to FIG. 2, the network arrangement 200 comprises the VAV system 102 integrated in the building management system (BMS) 108, one or more VAV controllers (110-1, 110-2, . . . 110-n), one or more edge devices (112-1, 112-2, . . . 112-n) or VAV boxes, and one or more user devices 160, all connected to a network/cloud 202. The one or more edge devices (112-1, 112-2, . . . 112-n) may be coupled to the corresponding one or more VAV controllers (110-1, 110-2, . . . 110-n). The VAV system 102 can be communicatively coupled to the one or more components in the facility. The VAV system 102 can be communicatively coupled to the one or more VAV controllers (110-1, 110-2, . . . 110-n) in the facility. The one or more VAV controllers (110-1, 110-2, . . . 110-n) can communicate with the VAV system 102 that is connected through a bus via a cloud or a network 202. Further, the one or more VAV controllers (110-1, 110-2, . . . 110-n) may be communicatively coupled to other one or more VAV controllers (110-1, 110-2, . . . 110-n) in the network 202 through the bus. For example, the processor 104 of the VAV system 102 may identify exact status of the VAV controller (110-1, 110-2, . . . 110-n) by receiving inputs from the other VAV controllers (110-1, 110-2, . . . 110-n) that are connected in the network 202. Because during initial status check, the status of the VAV controller (110-1, 110-2, . . . 110-n) may be shown as “inactive” due to power outage in that zone. But the inputs received from the other VAV controllers (110-1, 110-2, . . . 110-n) can confirm the status that the VAV controller (110-1, 110-2, . . . 110-n) is inactive due to power outage or network cable disconnection.

In some embodiments, the VAV's may integrate within the building management system (BMS) 108 through the third-party integrators/controllers to monitor parameters or the telemetry data such as CFM flow, zone temperature, temperature setpoints, damper positions and the like. Optionally, according to requirement additional inputs such as maximum flow setpoint, minimum flow setpoint, designed area/zone, K-factor and raw values of temperature, pressure inputs at the specified zone/area can also obtained by the processor 104 of the VAV system 102. Further the telemetry data may be transferred to router or server 126 through mediums such as, for example, JACE™ boxes, Forge connect™ box, and/or the like and protocols such as, for example, BACnet™, Modbus™, and/or the like for training and updating the machine learning model. The ML model may get updated automatically at specific time intervals based at least on the telemetry data, the additional inputs say, that are provided by the users/operators, configured rules, operator feedback, and predictions associated with configuration data of the VAV system. The processor 104 of the VAV system 102 determines the one or more anomalies in one or more operations of the at least one component of the one or more components using ML model.

The VAV system 102 may be connected to the network 202. The network 202 may define one or more networks including wired or wireless networks. The wireless network may be a cellular telephone network, an 802.11, 802.16, 802.20, or WiMAX network. Further, such networks may include a public network, such as the Internet, a private network, such as an intranet, or combinations thereof, and may utilize a variety of networking protocols now available or later developed including, but not limited to TCP/IP based networking protocols. The network may include wide area networks (WAN), such as the Internet, local area networks (LAN), campus area networks, metropolitan area networks, a direct connection such as through a Universal Serial Bus (USB) port, or any other networks that may allow for data communication. The network 202 may be configured to couple one computing device to another computing device to enable communication of data between the devices. The network 202 may generally be enabled to employ any form of machine-readable media for communicating information from one device to another. The network 202 may include communication methods by which information may travel between computing devices. The network 202 may be divided into sub-networks. The sub-networks may allow access to all of the other components connected thereto or the sub-networks may restrict access between the components. The network 202 may be regarded as a public or a private network connection and may include, for example, a virtual private network or an encryption or other security mechanism employed over the public Internet, or the like.

As described above and as will be appreciated based on this disclosure, embodiments of the present disclosure may be configured as methods, mobile devices, backend network devices, and the like. Accordingly, embodiments may comprise various means including entirely of hardware or any combination of software and hardware.

Referring now to FIG. 3 to FIG. 8, example methods in accordance with various embodiments of the present disclosure are illustrated. In some examples, each block or step of the flowchart, and combinations of blocks and/or steps in the flowchart, may be implemented by various means such as hardware, circuitry and/or other devices associated with execution of software including one or more computer program instructions.

In some examples, one or more of the procedures described in the figures may be embodied by computer program instructions, which may be stored by a memory circuitry (such as a non-transitory memory) of an apparatus employing an embodiment of the present disclosure and executed by a processing circuitry (such as a processor 104) of the apparatus. These computer program instructions may direct the apparatus to function in a particular manner, such that the instructions stored in the memory circuitry may produce an article of manufacture, the execution of which may implement the function specified in the flowchart block(s). Further, the apparatus may comprise one or more other components, such as, for example, a communication circuitry and/or an input/output circuitry. Various components of the apparatus may be in electronic communication between and/or among each other to transmit data to and/or receive data from each other.

In some examples, embodiments may take the form of a computer program product on a non-transitory computer-readable storage medium storing computer-readable program instructions (e.g. computer software). Any suitable computer-readable storage medium may be utilized including non-transitory hard disks, CD-ROMs, flash memory, optical storage devices, and/or magnetic storage devices.

FIG. 3 illustrates an exemplary method for managing the VAV system in a facility in accordance with one or more example embodiments described herein. In some examples, the method 300 may be performed by a processor 104 (for example, a processor 104 of the VAV system 102 described in connection with FIG. 1 and/or the VAV system 102 described in connection with FIG. 2). Referring to FIG. 3, the method for managing the VAV system in a facility is described. Specifically, FIG. 3 describes the method for detecting anomalies in the one or more operations of the at least one component of the VAV system in the facility.

The method 300 begins at step 302, at which the processor comprised in the VAV system (such as, but not limited to, the VAV system 102 thereof as described above in connection with FIG. 1 and FIG. 2) may receive sensor data or telemetry data from the plurality of sensors associated with Variable Air Volume (VAV) system. The sensor data includes but is not limited to actual air flow rate/cubic feet per minute (CFM) flow data, damper position data, and actual zone temperature. For example, the damper position data may include details but is not limited to damper position is 50% open or 100% open and the like. Additionally, the sensor data may also include but not limited to maximum flow setpoint, minimum flow setpoint, designed area, K-factor and raw values of temperature, pressure inputs and the like. Further, the VAV system includes the one or more components such as the one or more Variable Air Volume (VAV) controllers, the one or more dampers, the plurality of air ducts/tubes, the plurality of air flowmeter, the plurality of temperature sensors, and the other plurality of sensors associated with the VAV system.

At step 304, the processor may retrieve configuration data of the one or more components and historical data associated with at least one component of the one or more components from a database. The historical data can either be created within the building management system or previously collected raw data. The raw data is processed through machine learning platforms such as Databricks™. The historical data associated with the one or more components may include but are not limited to operational status (i.e. active or inactive) of one or more VAV controller associated with the VAV system, configuration of temperature (i.e. temperature setpoints) at the VAV controller, operational status (i.e. active or inactive) of Air handling Unit (AHU), the configuration data (design or customized data or data at specification sheet) and maintenance data (i.e. quarterly or yearly preventive maintenance reports or records) of the one or more components associated with the VAV system. The configuration data of the one or more components associated with the VAV system may include design parameters or customized parameters for specific components in the one or more components associated with the VAV system and other similar data. The maintenance data of the one or more components associated with the VAV system may include but is not limited to quarterly or yearly maintenance data, repairs, malfunction of one or more components. For instance, during preventive maintenance performed in every quarter/half yearly by operators or BMS vendors, the maintenance data of the one or more components associated with the VAV system can be captured. During the preventive maintenance of the one or more components, some anomalies can be identified. The anomalies may include but are not limited to inconsistent damper stuck issues throughout the year, delayed response of the VAV system after configuring temperature setpoints, and incorrect CFM displays as per open/close conditions and so on. These anomalies are recorded during the preventive maintenance of the one or more components and can be used as the historical data. The sensor data and the historical data may be stored in the database or the memory of the VAV system or a server of the BMS system.

At step 306, the processor may compare the sensor data with the configuration data and the historical data to identify deviations or similarities present in the sensor data. The processor may perform the comparison by evaluating the desired or expected air flow rate and the actual sensor data at a particular configuration/setting of the VAV controller using the ML model. The desired or expected air flow rate refers to predicted air flow data by an operator/user based on the configuration data or setpoints for the VAV units provided by a manufacturer and requirement of the facility. For example, the expected air flow rate for a space having specific volume may be configured by the operator based on at least number of occupants in the space/area, duration, weather condition and the like.

At step 308, the processor may determine at least one anomaly in one or more operations of the at least one component of the one or more components based on comparison. The at least one anomaly is determined using a machine learning (ML) model. In some embodiments, the processor may determine the at least one anomaly in at least one component of the VAV system based at least in part on the sensor data and the historical data associated with the one or more components. The one or more anomalies in one or more operations of the at least one component of the one or more components may include but are not limited to controller failure, damper malfunction, disconnection of air ducts/tubes, overflow/under flow of air in VAV, and sensor malfunction (Thermostat issue). The machine learning (ML) model is trained to detect the anomalies and deviations from the baseline value that indicate the airflow issue, or malfunction and the like. Techniques like regression analysis, anomaly detection, and clustering algorithms can be employed to train the ML model. For example, if the actual air flow is zero, then the ML model may check at least whether the temperature setpoint is less than the actual temperature, the AHU in the specific Zone is ON, the damper Position is 100% open. As a result of the analysis, machine learning algorithm of the ML model detects the issue as disconnection of air ducts/tubes and the incident will be reported instantly to the operator.

At step 310, the processor may identify at least one corrective action to modify one or more operations of the at least one component based on the at least one anomaly. The corrective action may include but is not limited to recommendation for replacement of the one or more components associated with the VAV system that is identified with the one or more anomalies, rectifying errors due to network cable connection with the VAV controller, fixing air duct leakages, triggering control signal to restart the VAV controller, and the like. Further, the corrective action may also include triggering of control signal to shut down operations until recovery of a particular VAV controller that is identified with anomaly thereby to control excess energy utilization.

At step 312, the processor may render, via a user interface, one or more notifications to an operator based on the at least one corrective action to modify the one or more operations of the at least one component. The identified anomaly and the one or more corrective actions are reported to the operator through a user interface (UI) as a notification that include at least a text message, alarm/alert, oral communication, or a detailed report. The UI is integrated with the VAV system. Alternatively, the UI can be integrated with the BMS in the facility. The User interface is provided with a user-friendly dashboard to display status of the one or more VAV controller and status of the one or more edge device, alerts/alarms, notifications and required one or more corrected actions. The user interface may allow users to monitor performance of the VAV system and perform corrective actions accordingly to resolve the one or more anomalies identified at the one or more components associated with the VAV system. The corrective action may be notified to the user/operator regarding the one or more anomalies through a medium such as SMS or Email in real-time. In some embodiments, the processor may be configured to generate a comprehensive report that includes detailed descriptions of various issues, recommendations for corrective actions, and percentage of improvements from the previous year to the current year.

At step 314, the processor may optionally trigger at least one control signal to adjust the one or more operations of the at least one component of the VAV system based on the at least one corrective action. In addition, the UI also receives feedback or input from the operator with which further predictions of corrective action can be developed/implemented. The historical data associated with the one or more components may include but is not limited to a frequency of damper stuck for a predefined duration, delayed response of VAV operation after configuration of the temperature setpoints, and incorrect Cubic Feet per Minute (CFM) displays as per open/close conditions of the damper.

At step 316, the processor may train the ML model to detect anomalies in the one or more operations of the at least one component of the VAV system based on at least: configured rules, operator feedback, and predictions associated with configuration data of the VAV system, and wherein the ML model is trained to detect operation anomalies of the VAV system using the sensor data and the historical data. The historical data associated with the plurality of sensors comprises at least: operational status of one or more VAV controller associated with the VAV system, configuration of temperature at the VAV controller, operational status of Air handling Unit (AHU), the configuration data and maintenance data of the one or more components associated with the VAV system. The procedures/rules for detection of each of the one or more anomalies and corrective actions or recommendations used by the ML model are described further in detail in FIG. 4 to FIG. 8.

FIG. 4 illustrates an exemplary method for managing the VAV system (described in connection with FIG. 1 and FIG. 2) in a facility to identify anomaly associated with VAV controller in accordance with one or more example embodiments described.

The method 400 begins at step 402, at which the processor comprised in the VAV system (such as, but not limited to, the VAV system 102 thereof as described above in connection with FIG. 1 and FIG. 2) may obtain operational status of the VAV controller and other VAV controllers that are connected to the VAV system.

At step 404, the processor may compare the operational status (i.e. active or inactive) of the VAV controller with at least: historical data associated with the VAV controller, the operational status of the other VAV controllers in the network associated with the VAV system, and user inputs/feedback. The processor may compare the operational status of the VAV controller similar to the step 306 described in connection to the FIG. 3.

At step 406, the processor may determine the at least one anomaly associated with the VAV controller due to at least one of: power outage of the VAV controller, and a network cable disconnection based on comparison of the operational status of the VAV controller using the ML model. Similar to the step 308 described in connection to the FIG. 3, the processor may determine the at least one anomaly associated with the VAV controller using the ML model.

At step 408, the processor may identify at least one corrective action to modify one or more operations of the VAV controller based on the at least one anomaly similar to the step 310 that is described in connection to the FIG. 3.

At step 410, the processor may render, via a user interface, one or more notifications to an operator based on the at least one corrective action to modify the one or more operations of the VAV controller similar to the step 312 that is described in connection to the FIG. 3.

For instance, considering the anomaly related to VAV controller failure, the root cause of the VAV controller failure may occur majorly due to network cable disconnection and power outage issues. For example, in case the VAV controller is in an offline state, then the processor reports the VAV controller failure to the VAV system along with a period of inactive status of the VAV controller at an initial stage. Further, the report may disclose details with respect to a previous pattern of power outage in a day and/or week and/or month. Further, the power outage issues in the VAV system are identified using machine learning algorithms based on previous patterns and manual inputs from the operators. The machine learning algorithms are used in the ML model. At next stage, the processor further analyzes a status of other VAV controllers that are connected to the BMS in the network at different zone/space. The status of other VAV controllers that are connected to the BMS in the network may be active or inactive. If all the other VAV controllers are offline, then the processor predicts the problem as “Network Cable disconnection”. The processor may recommend corrective action for overcoming the network cable disconnection and the ML model provides insights or step by step procedure to resolve the anomaly with respect to the VAV controller. In other case, if all the other VAV controllers are online, then the processor predicts the problem as “power outage” at the specified zone/area. The processor may recommend corrective action for rectifying the power outage issue at the specified zone and the ML model provides insights or step by step procedure to resolve the anomaly with respect to the VAV controller.

FIG. 5 illustrates an exemplary method for managing the VAV system in a facility to identify anomaly associated with a damper/actuator in accordance with one or more example embodiments described herein. The damper/actuator is associated with the VAV box that is controlled by the VAV controller.

The method 500 begins at step 502, at which the processor 104 comprised in the VAV system (such as, but not limited to, the VAV system 102 thereof as described above in connection with FIG. 1 and FIG. 2) may configure temperature for a specified zone at the VAV controller.

At step 504, the processor may compare the configured temperature with an actual temperature at the specified zone. For example, if the configured temperature or temperature set point is 25° C. (i.e. 25 degree Celsius) and the actual zone temperature is 30° C. than the processor may provide a result of the comparison as the zone temperature is higher than the temperature setpoint.

At step 506, the processor may receive damper position data from the plurality of sensors. For example, the damper position data may include details related to position of the damper expressed as for example, 50% open or 100% open and the like.

At step 508, the processor may compare the damper position data with an expected damper position data based on the configured temperature and historical data associated with a damper. The processor may compare the damper position data with an expected damper position data similar to the step 306 described in connection to the FIG. 3.

At step 510, the processor determines the at least one anomaly associated with the damper stuck or an actuator malfunction based on comparison of the damper position data with the expected damper position data using the ML model. Similar to the step 308 described in connection to the FIG. 3, the processor may determine the at least one anomaly associated with the damper/actuator malfunction using the ML model.

At step 512, the processor may identify at least one corrective action to modify one or more operations of the damper based on the at least one anomaly similar to the step 310 that is described in connection to the FIG. 3. For example, if there is delayed or no response from the damper, then the operations with respect to the damper movements are checked. The operations with respect to the damper movements may be checked by triggering control signals from the VAV system or by sending notification to operator to check the operations of the damper movements.

At step 514, the processor may render, via a user interface, one or more notifications to an operator based on the at least one corrective action to modify the one or more operations of the damper/actuator similar to the step 312 that is described in connection to the FIG. 3. For example, the corrective actions may include but are not limited to replacement of either the damper/actuator, or function of the damper/actuator may be reset after cleaning/servicing the damper/actuator (if the damper malfunction is due to dust accumulation).

In this case of the damper/actuator malfunction, if there is no change of damper position for the temperature setpoint that is less than actual temperature of VAV and vice versa, then processor identifies that there is a damper stuck and notification may be sent to the operator regarding the incident. For example, to reduce cooling in an area connected to the VAV system, the temperature setpoint is greater than the actual temperature and in that case the damper has to be in a close position. The expected anomaly is the open position of the damper. If the damper remains in open position, then the operator is notified that there is a damper stuck. In such instances, a damper output may in a range of 0 to 10 V and there is no feedback from the damper. In another example, to increase cooling in an area connected to the VAV system, the cooling temperature setpoint is set lower than the actual temperature. The expected anomaly is the open position of the damper. If the damper remains in close position, then the operator is notified that there is a damper stuck. In such instances, a damper output may in a range of 0 to 10 V and there is no feedback from the damper. Here, the exact damper/actuator issue is identified and reported based on the past predictions and input provided by the operator through Machine learning algorithm.

FIG. 6 illustrates an exemplary method for managing the VAV system in a facility to identify anomaly associated with underflow/overflow of air in accordance with one or more example embodiments described herein.

The method 600 begins at step 602, at which the processor 104 comprised in the VAV system (such as, but not limited to, the VAV system 102 thereof as described above in connection with FIG. 1 and FIG. 2) may receive an actual CFM value based on the actual air flow data measured by the plurality of sensors at a specified area/zone. The CFM value is a critical measurement used to assess the airflow within the facility or building. The CFM measures the volume of air delivered or exhausted by the system per minute and helps determine whether the system can adequately heat or cool a space.

At step 604, the processor may acquire configured CFM value using configuration data of the VAV controller at the specified area/zone, and historical data associated with the air flow data measured by the plurality of sensors from the database. For example, the VAV controller may be designed to operate at one or more configured CFM value based on conditions that includes but are not limited to room temperature, number of occupants, weather condition and so on. The processor may acquire the configured CFM value based on a specific condition at the zone in the building. Further, the processor may acquire the historical data associated with the air flow data measured by the plurality of sensors. For instance, the historical data associated with the air flow data may include but is not limited to air filters replacement, air ductwork issues, closed or blocked vent, thermostat issues, duct insulation, humidification or dehumidification requirements, age of the VAV unit, mechanical failures of internal components such as the damper, compressor, blower, or other mechanical parts can impact overall airflow and the like. For example, any clogged or dirty filters that restrict airflow, and the filters are marked for replacement in the database, then in that case the processor may be aware of the historical data associated with the air flow data while determining the anomaly.

At step 606, the processor may determine expected CFM value based on volume of the specified area/zone. For instance, the expected CFM or required CFM value can be determined using room volume. For example, the required air flow of room=volume of room/space*Air changes per hour (ACH).

At step 608, the processor may identify whether the actual CFM value is below or above a threshold based on comparison of the actual CFM value with the configured CFM value and the expected CFM value. For example, if the identified actual CFM value is above threshold when compared to the actual CFM value with the configured CFM value and the expected CFM value, then the air flow is identified as overflow of air volume to the specified space/area. Alternatively, if the identified actual CFM value is below threshold (predefined or expected limit) when compared to the actual CFM value with the configured CFM value and the expected CFM value, then the air flow is identified as underflow of air volume to the specified space/area. The processor may compare the actual CFM value with the configured CFM value and the expected CFM value similar to the step 306 described in connection to the FIG. 3.

At step 610, the processor may determine the at least one anomaly associated with a damper malfunction or a disconnection of air duct and the historical data using the ML model based on identification that the actual CFM value is below or above the threshold and historical data with respect to the flow sensor and the damper movements. Similar to the step 308 described in connection to the FIG. 3, the processor may determine the at least one anomaly associated with the underflow/overflow of air using the ML model.

At step 612, the processor may identify at least one corrective action to modify one or more operations associated with underflow/overflow of air based on the at least one anomaly similar to the step 310 that is described in connection to the FIG. 3. For example, if there is abnormal change or no change in the flow sensor data, then the operations with respect to the flow sensors are checked. The operations with respect to the flow sensors are checked by triggering control signals from the VAV system or by sending notification to operator to check the operations of the flow sensors. Alternatively, if change in the CFM value is below or above predefined threshold, then the operations with respect to the damper movements are checked. The operations with respect to the damper movements are checked by triggering control signals from the VAV system or by sending notification to operator to check the operations of the damper movements.

At step 614, the processor may render, via a user interface, one or more notifications to an operator based on the at least one corrective action to modify the one or more operations of the damper/actuator and/or flow sensor similar to the step 312 that is described in connection to the FIG. 3. For example, either the flow sensor and/or damper/actuator may be replaced, or function of the flow sensor or damper/actuator may be reset after cleaning/servicing the flow sensor or damper/actuator (if the damper malfunction is due to dust accumulation). For instance, the overflow of air is reported by comparing the actual flow with air flow details mentioned in design specification/configuration data of the VAV system and design calculations of the area or room in the commercial building or the facility.

For example, the overflow of the air can be determined by estimating the cubic feet per minute (CFM) value of the space or area in the commercial building. The CFM can be calculated using values provided in the design specification/configuration data of the VAV system. Further, the CFM can also be measured using a flow sensor associated with the VAV controller. In other case, the required CFM can be determined based on volume of the room. The machine learning algorithm is trained using the above-mentioned procedure to detect the overflow of the air and notify the incident to the operator instantly. The required flow of room is estimated based on result of a product of the Volume of Room and ACH (Air Changes Per hour). Here, the ACH and the Volume of Room can be predefined or obtained from the expected configuration from the operator.

For instance, if the damper is 50% open and the CFM is greater than the flow provided in the VAV system design specification flow then the air flow is considered as “Overflow”. In another example, if the damper is 50% open and the CFM value is greater than the required CFM value based on room volume then the air flow is considered as “Overflow”. In another instance, if the damper is 100% open/close and the CFM value is greater than the air flow provided in the VAV system design specification then the air flow is considered as “Overflow”. In another instance, if the damper is 100% open/close and the CFM value is greater than the required CFM value based on room volume or unable to control (reduce) the temperature for the specific room/space is considered as overflow. In this case, anomaly identified is related to overflow of air.

Alternatively, the under flow of air is reported by comparing the actual flow with air flow details mentioned in design specification/configuration data of the VAV system and design calculations of the area or room in the commercial building. For example, the underflow of the air can be determined by estimating the cubic feet per minute of the room or area in the commercial building. The CFM can be calculated using values provided in the design specification/configuration data of the VAV system. Further, the CFM can also be measured using a flow sensor associated with the VAV controller. In other case, the required CFM can be determined based on volume of the room. The machine learning algorithm is trained using the above-mentioned procedure to detect the overflow of the air and notify the incident to the operator instantly. The required flow of room is estimated based on result of a product of the Volume of Room and ACH (Air Changes Per hour). Here, the ACH and the Volume of Room can be predefined or obtained from the expected configuration from the operator.

That is, required CFM or air flow of room=the Volume of Room*ACH

For example, if the damper is 100% open and the CFM is less than the air flow specified in the VAV system configuration data then the anomaly is identified as “Underflow of air”. In another case, if the damper is 100% open and the CFM is less than the required CFM based on room volume then the anomaly is identified as “Underflow of air”.

FIG. 7 illustrates an exemplary method for managing the VAV system in a facility to identify anomaly associated with disconnection of air ducts/tubes in accordance with one or more example embodiments described herein.

The method 700 begins at operation 702, at which the processor comprised in the VAV system (such as, but not limited to, the VAV system 102 thereof as described above in connection with FIG. 1 and FIG. 2) may receive actual air flow data, actual zone temperature and damper position data from the plurality of sensors at the specified area/zone.

At step 704, the processor may acquire configuration of temperature at the VAV controller from the database and operational status of Air handling unit (AHU).

At step 706, the processor may identify absence of the actual air flow based on analysis of the actual zone temperature, the configuration of temperature at the VAV controller, operational status of AHU, and position of the damper.

At step 708, the processor may determine the at least one anomaly associated with disconnection of air ducts based on identification of absence of the actual air flow data using the ML model. The ML model can detect the disconnection of air ducts/tubes by comparing the actual flow with the temperature setpoints, damper position and Air handling unit (AHU) running conditions at a specific zone or area in the commercial building (similar to the steps 306 and 308 described in connection to the FIG. 3.).

At step 710, the processor may identify at least one corrective action/root cause to modify one or more operations associated with the air ducts/tubes based on the at least one anomaly similar to the step 310 that is described in connection to the FIG. 3. For example, if the actual air flow is zero, then the ML model may check at least whether the temperature setpoint is less than the actual temperature, the AHU in the specific Zone is ON, the damper Position. As a result of the analysis, the machine learning algorithm detects the issue as disconnection of air ducts/tubes and the incident will be reported instantly to the operator.

At step 712, the processor may render, via a user interface, one or more notifications to an operator based on the at least one corrective action to modify the one or more operations of associated with the air ducts/tubes similar to the step 312 that is described in connection to the FIG. 3. For example, the corrective actions may include but are not limited to either replacement of the air tubes/ducts, or recommendation to operator to check leakage or disconnection in the air ducts and the like.

FIG. 8 illustrates an exemplary method for managing the VAV system (described in connection with FIG. 1 and FIG. 2) in a facility to identify anomaly with respect to the plurality of sensors that are associated with VAV system in accordance with one or more example embodiments described herein.

The method 800 begins at operation 802, at which the processor comprised in the VAV system (such as, but not limited to, the VAV system 102 thereof as described above in connection with FIG. 1 and FIG. 2) may receive actual sensor data from a plurality of sensors at a specified zone and neighboring zone in real-time.

At step 804, the processor may retrieve customized sensor parameters from configuration data of the plurality of sensors, and baseline value from historical data associated with the plurality of sensors. The ML model can detect the thermostat issue using customized sensor parameters. The customized sensor parameters may include but are not limited to at least upper and lower thresholds configured for the sensors, acceptable range of sensor values in the specified zone in comparison with the neighboring sensors that are available in same zone, and baseline values of the sensors that are recorded earlier and stored as the historical data.

At step 806, the processor may compare the actual sensor data with the customized sensor parameters and historical data. The processor may compare the actual sensor data with the customized sensor parameters and historical data similar to the step 306 described in connection to the FIG. 3.

At step 808, the processor may determine at least one anomaly associated with thermostat malfunction at the specified area/zone based on comparison of the actual sensor data with the customized sensor parameters and the historical data using the ML model. The machine learning model may detect the sensor issue based on the comparison of the actual sensor data with the customized sensor parameters. Similar to the step 308 described in connection to the FIG. 3, the processor may determine the at least one anomaly associated with the sensor (e.g thermostat) malfunction using the ML model.

At step 810, the processor may identify at least one corrective action/root cause to modify one or more operations associated with the thermostat based on the at least one anomaly similar to the step 310 that is described in connection to the FIG. 3.

At step 812, the processor may render, via a user interface, one or more notifications to an operator based on the at least one corrective action to modify the one or more operations of the sensor (e.g. thermostat) similar to the step 312 that is described in connection to the FIG. 3. For example, the corrective actions may include but are not limited to replacement of either the sensor, or function of the sensor may be reset after cleaning/servicing the sensor. For example, the at least one anomaly determined using the ML model may be reported along with the corrective actions to the operator thereby to resolve the sensor issue (i.e. malfunction of sensor or failure of the sensor to provide accurate sensor data). Alternatively, the processor may also compare the neighboring sensor values and baseline records until the new thermostat got replaced.

The present invention provides solution to identify the one or more anomalies in the VAV units/systems and generate alerts for facility managers/operators using the ML model. Based on the alerts, the present invention enables immediate response by sending notification to the operators and guidance on taking necessary actions to resolve issues promptly using the ML model. The present invention can also reduce equipment failures in the Heating Ventilation and Air-conditioning (HVAC) systems. Further, the present invention also reduces maintenance costs associated with the VAV units in the facility. Furthermore, the present invention also improves accuracy of detection of the one or more anomalies in the one or more components of the VAV system in the facility.

Although example processing systems have been described in the figures herein, implementations of the subject matter and the functional operations described herein can be implemented in other types of digital electronic circuitry, or in computer software, firmware, or hardware, including the structures disclosed in this specification and their structural equivalents, or in combinations of one or more of them.

Embodiments of the subject matter and the operations described herein can be implemented in digital electronic circuitry, or in computer software, firmware, or hardware, including the structures disclosed in this specification and their structural equivalents, or in combinations of one or more of them. Embodiments of the subject matter described herein can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions, encoded on computer storage medium for execution by, or to control the operation of, information/data processing apparatus. Alternatively, or in addition, the program instructions can be encoded on an artificially-generated propagated signal, e.g., a machine-generated electrical, optical, or electromagnetic signal, which is generated to encode information/data for transmission to suitable receiver apparatus for execution by an information/data processing apparatus. A computer storage medium can be, or be included in, a computer-readable storage device, a computer-readable storage substrate, a random or serial access memory array or device, or a combination of one or more of them. Moreover, while a computer storage medium is not a propagated signal, a computer storage medium can be a source or destination of computer program instructions encoded in an artificially-generated propagated signal. The computer storage medium can also be, or be included in, one or more separate physical components or media (e.g., multiple CDs, disks, or other storage devices).

The operations described herein can be implemented as operations performed by an information/data processing apparatus on information/data stored on one or more computer-readable storage devices or received from other sources.

The term “data processing apparatus” encompasses all kinds of apparatus, devices, and machines for processing data, including by way of example a programmable processor, a computer, a system on a chip, or multiple ones, or combinations, of the foregoing. The apparatus can include special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application-specific integrated circuit). The apparatus can also include, in addition to hardware, code that creates an execution environment for the computer program in question, e.g., code that constitutes processor firmware, a protocol stack, a repository management system, an operating system, a cross-platform runtime environment, a virtual machine, or a combination of one or more of them. The apparatus and execution environment can realize various different computing model infrastructures, such as web services, distributed computing and grid computing infrastructures.

A computer program (also known as a program, software, software application, script, or code) can be written in any form of programming language, including compiled or interpreted languages, declarative or procedural languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, object, or other unit suitable for use in a computing environment. A computer program may, but need not, correspond to a file in a file system. A program can be stored in a portion of a file that holds other programs or information/data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub-programs, or portions of code). A computer program can be deployed to be executed on one computer or on multiple computers that are located at one site or distributed across multiple sites and interconnected by a communications network.

The processes and logic flows described herein can be performed by one or more programmable processors executing one or more computer programs to perform actions by operating on input information/data and generating output. Processors suitable for the execution of a computer program include, by way of example, both general and special purpose microprocessors, and any one or more processors of any kind of digital computer. Generally, a processor will receive instructions and information/data from a read-only memory or a random access memory or both. The essential elements of a computer are a processor for performing actions in accordance with instructions and one or more memory devices for storing instructions and data. Generally, a computer will also include, or be operatively coupled to receive information/data from or transfer information/data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magneto-optical disks, or optical disks. However, a computer need not have such devices. Devices suitable for storing computer program instructions and information/data include all forms of non-volatile memory, media and memory devices, including by way of example semiconductor memory devices, e.g., EPROM, EEPROM, and flash memory devices; magnetic disks, e.g., internal hard disks or removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks. The processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry.

To provide for interaction with a user, embodiments of the subject matter described herein can be implemented on a computer having a display device, e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor, for displaying information/data to the user and a keyboard and a pointing device, e.g., a mouse or a trackball, by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback, e.g., visual feedback, auditory feedback, or tactile feedback; and input from the user can be received in any form, including acoustic, speech, or tactile input. In addition, a computer can interact with a user by sending documents to and receiving documents from a device that is used by the user; for example, by sending web pages to a web browser on a user's client device in response to requests received from the web browser.

Embodiments of the subject matter described herein can be implemented in a computing system that includes a back-end component, e.g., as an information/data server, or that includes a middleware component, e.g., an application server, or that includes a front-end component, e.g., a client computer having a graphical user interface or a web browser through which a user can interact with an implementation of the subject matter described herein, or any combination of one or more such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital information/data communication, e.g., a communications network. Examples of communications networks include a local area network (“LAN”) and a wide area network (“WAN”), an inter-network (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks).

The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communications network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. In some embodiments, a server transmits information/data (e.g., an HTML page) to a client device (e.g., for purposes of displaying information/data to and receiving user input from a user interacting with the client device). Information/data generated at the client device (e.g., a result of the user interaction) can be received from the client device at the server.

While this specification contains many specific implementation details, these should not be construed as limitations on the scope of any disclosures or of what may be claimed, but rather as descriptions of features specific to particular embodiments of particular disclosures. Certain features that are described herein in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable sub-combination. Moreover, although features may be described above as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a sub-combination or variation of a sub-combination.

Similarly, while operations are depicted in the drawings in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Moreover, the separation of various system components in the embodiments described above should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

Thus, particular embodiments of the subject matter have been described. Other embodiments are within the scope of the following claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In certain implementations, multitasking and parallel processing may be advantageous.

It is to be understood that the disclosure is not to be limited to the specific embodiments disclosed, and that modifications and other embodiments are intended to be included within the scope of the appended claims. Although specific terms are employed herein, they are used in a generic and descriptive sense only and not for purposes of limitation, unless described otherwise.