ANOMALY DETECTION SYSTEM FOR A TRACK VEHICLE SYSTEM

Description

FIELD

The present application relates to a track vehicle system, such as tracked rides, attractions, or transportation systems.

BACKGROUND

A conductor rail (e.g., a bus bar) is a critical piece of infrastructure used to conduct power and signals. A conductor rail can be made of different conductor material, such as aluminum, stainless steel, and copper depending on the application, and are used in many different industries. Conductor rails are often used in transportation systems or attractions, and other areas such as overhead cranes.

Conductor rails require frequent inspection for corrosion, wear and tear, and alignment. Inspecting conductor rails and making sure they are fully operational is a task that requires plenty of planning and safety. Inspecting conductor rails is time consuming and may pose a risk to the inspector, since the person must go underneath the track, in the ride path, to elevated heights, or in confined spaces. Other risks include, but are not limited to, electrocution, dust, and pests.

Therefore, a need exists for systems and methods that addresses the concerns above or at least offers an alternative to existing solutions.

BRIEF SUMMARY

In one example, an anomaly detection system for a track vehicle system includes a sensor configured to traverse along a track of the track vehicle system and gather data of one or more track components. The anomaly detection system further includes a processor configured to detect one or more anomalies of the one or more track components based on the gathered data.

Optionally, the sensor is configured to detect visual information of the one or more track components. The anomaly detection system may include a signal detector configured to detect electrical signal information of the one or more track components, wherein the processor is configured to detect the one or more anomalies based on the visual information and the electrical signal information. The electrical signal information may include electrical signals of the track itself.

Optionally, the anomaly detection system is coupled to a track vehicle to traverse along the track. The track vehicle may be configured to traverse along one side of the track, wherein the anomaly detection system is positioned on a different side of the track.

In another example, an anomaly detection system includes a first sensor and a second sensor each configured to traverse along a track of a track vehicle system and gather data of one or more components of the track. The anomaly detection system further includes a processor configured to detect one or more anomalies of the one or more components based on the gathered data.

Optionally, the first sensor is a visual sensor configured to detect visual defects, and the second sensor is a signal detector configured to detect defects in a signal through the one or more components. The processor may be configured to align the visual defects with the signal defects to detect the one or more anomalies.

Optionally, the one or more components include a conductor rail, and the processor is further configured to detect anomalies in the conductor rail.

Optionally, the processor is further configured to inject a signal in the one or more components for detection of the one or more anomalies.

Optionally, the anomaly detection system includes a location sensor, wherein the processor is further configured to identify a location of the one or more anomalies based on data from the location sensor.

Optionally, the track vehicle system is a ride system including a ride vehicle, and the anomaly detection system is configured for selective attachment to the ride vehicle.

In another example, a method for detecting anomalies along a track of a track vehicle system includes traversing an anomaly detection system along the track, wherein the anomaly detection system comprises a sensor. The method further includes gathering, via the sensor and while traversing along the track, data of one or more components of the track. The method further includes identifying one or more anomalies of the one or more components based on the gathered data.

Optionally, the identifying includes processing an image of the one or more components with machine vision.

Optionally, the method includes training an image analysis model based on user identification of one or more areas of interest.

Optionally, the anomaly detection system includes a location sensor, and the method further includes identifying a location of the one or more anomalies based on data from the location sensor.

Optionally, the method includes generating a report of the one or more anomalies. The report may include a respective image of the one or more anomalies and a respective location of the one or more anomalies along the track. The report may be generated on a user device for manual review.

In addition to the exemplary aspects and embodiments described above, further aspects and embodiments will become apparent by reference to the drawings and by study of the following description.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 illustrates a diagram of an example track vehicle system.

FIG. 2A illustrates a diagram of an example anomaly detection system.

FIG. 2B illustrates a diagram of another example anomaly detection system.

FIG. 3A illustrates a diagram of an example track vehicle system having an anomaly detection system.

FIG. 3B illustrates a diagram of an example track vehicle system having an anomaly detection system.

FIG. 4 illustrates example anomalies detectable by an anomaly detection system.

FIG. 5 illustrates a diagram of an example report generated by an anomaly detection system.

FIG. 6 illustrates an example computing system.

FIG. 7 illustrates an example method for detecting anomalies along a track of a track vehicle system.

DETAILED DESCRIPTION

An anomaly detection system may include an autonomous device configured for anomaly detection, for example, to inspect conductor rails or bus bars, such as for a transportation system, a ride, or attraction, or other components for inspection (e.g., track indications, torque stripe, wheel wear, etc., without intent to limit). The anomaly detection system may be portable or fixed, and include one or more cameras and sensors for identifying areas of concern (e.g., anomalies) for preventive maintenance. The anomaly detection system may be attached to a ride vehicle under maintenance operation or other vehicle configured to ride on or traverse a track (e.g., robotic device, motorized itself, and/or human powered). In either example, the system is deployed around the track and captures high-definition pictures of track components (e.g., conductor rails, bus bars, walls, guide systems, mechanical systems, or the like). The system then analyzes the images, such as through a machine learned model, to identify possible anomalies. In some instances other analysis techniques, such as algorithms or the like may be used.

In instances where a model is used, a field expert may provide the supervised learning or otherwise teach the anomaly detection system (and in particular the ML model) which track segments within various images are good or bad, or as many classes as needed or appropriate. The field expert may be used to provide human-in-the loop interaction and/or to provide input to the dataset as part of the training model. In many instances, the system may be weighted to skew towards more false positives, i.e., trigger more images for possible anomalies to help ensure all possible anomalies are captured.

As images are identified as possibly having anomalies to be addressed, the anomaly detection system may estimate the location of the anomalies using machine learning or location data (e.g., GPS, markers along the track, or other location techniques). A report may be generated indicating areas of concern. In some instances, the images with possible anomalies may be presented on a user device and include annotations or boundaries (e.g., bounding boxes) to identify the area of the possible anomaly to help a user more quickly identify possible issues.

Turning to the figures, FIG. 1 illustrates an example track vehicle system 100. The track vehicle system 100 includes a track 102 and a track vehicle 104 positioned on, coupled to, or otherwise engaged with the track 102. Depending on the application, the track vehicle system 100 may be a crane system, a gantry system, a people or object mover, an attraction or ride, a monorail, a subway or other transportation system, or other systems having a vehicle or other component that follows a track or guide. As one example, FIG. 1 illustrates a ride system including a ride vehicle for an attraction or ride. In such examples, the track vehicle 104 is configured to carry one or more passengers or guests, such as through an attraction or ride, e.g., train on one or more rails, roller coaster, gondola, or other tracked or cabled vehicles or carriers. For example, the track vehicle 104 may include a chassis (e.g., to house or receive one or more passengers, guests, animals, or objects), on-board suspension, one or more wheels, and other features. The track vehicle 104 may have different configurations based on applicable restrictions, a ride or attraction theme, a desired guest experience, or the like. For example, the track vehicle 104 may include an open or closed cockpit, be sized and shaped to mimic a desired vehicle or theme (e.g., air vehicle, water vehicle, ground vehicle, movie vehicle, etc.), be realistic or unrealistic (e.g., imaginary), etc., but generally be configured to receive one or more guests. For example, the cockpit may be configured as a compartment that includes a seating area to allow one or more guests to sit comfortably within the vehicle. In other examples, the cockpit or compartment may include a standing or other position configuration for the guests.

The track 102 may define a track surface 106. Depending on the application, the track vehicle 104 may traverse the track 102 along the track surface 106 (e.g., the wheels of the track vehicle 104 rolling on the track surface 106), above the track surface 106 (e.g., the track vehicle 104 moving adjacent the track surface 106, such as spaced above the track surface 106), or any combination thereof. Although described with reference to a track having a track surface, the systems described herein may be applied to other systems, including gondola or cable vehicle systems.

One or more components of the track vehicle system 100 may be positioned below the track surface 106. In such examples, the track surface 106 may be positioned or otherwise configured to conceal operating or other components of the track vehicle system 100 below the track surface 106. For example, one or more bogie assemblies 110 may be coupled to the track 102 below the track surface 106. The bogie assemblies 110 may be coupled to the track vehicle 104 and glide or otherwise traverse along the track 102 below the track surface 106, such as to direct or guide the track vehicle 104 through the attraction. In such examples, a channel 112 may be defined through the track surface 106 (e.g., along the track surface 106 below the track vehicle 104), such as to allow portions of the bogie assemblies 110 or other components to extend from below the track surface 106 for coupling to the track vehicle 104 above the track surface 106. Other components may be positioned below the track surface 106. For instance, one or more conductor rails 114 may extend below the track surface 106. The conductor rails 114 may provide power, communication, or other signals to the track vehicle 104 (e.g., via a collector assembly or shoe, as described below).

FIG. 2A illustrates an example anomaly detection system 200. The anomaly detection system 200 is configured to detect anomalies of one or more components of the track 102, such as for maintenance operations, active anomaly detection/prevention, or the like. For example, the anomaly detection system 200 may detect defects, damage, wear, or other anomalies of the track 102 (e.g., in the conductor rail 114), such as to facilitate efficient operations. In examples, the anomaly detection system 200 may detect the anomalies automatically, such as using machine vision or other algorithms (e.g., using machine learning).

The anomaly detection system 200 includes a first sensor 204 (e.g., a first sensor suite or sensor assembly). The first sensor 204 may include a visual sensor (e.g., a camera) configured to detect visual information (e.g., visual defects) of track components. For example, the first sensor 204 may be oriented to capture visual data of the conductor rail 114 or other components, such as while the anomaly detection system 200 is traversed along the track 102 (e.g., by the track vehicle 104, motorized itself, or human powered). The data from the first sensor 204 may be gathered by a processor or controller 206 (e.g., in real time as the anomaly detection system 200 traverses along the track 102). Depending on the application, the controller 206 may be onboard the anomaly detection system 200, or the controller 206 may be offboard (e.g., on the track vehicle 104, as a wayside controller, distributed across a network, etc.). In either application, the data may be processed in real time (or near real time) and/or later (e.g., at the end of the attraction, at the end of the day, at a specified maintenance period, etc.).

The controller 206 may be configured to detect one or more anomalies of the track components based on the data gathered from the first sensor 204. For example, the visual information or data from the first sensor 204 may indicate an anomaly, such as damage or wear or any other unexpected or undesirable characteristics, to the conductor rail 114 or other components of the track vehicle system 100.

In examples, the anomaly detection system 200 may include a second sensor 210. The second sensor 210 may be a signal detector configured to detect electrical signal information of track components (e.g., while the anomaly detection system 200 or track vehicle 104 traverses along the track 102). For example, the second sensor 210 may be configured to detect signal defects or electrical signals of the track 102 itself, such as in a signal propagating through the track components. The data from the second sensor 210 may be gathered by the controller 206. Like the visual information data, the data from the second sensor 210 may be processed in real time (or near real time) and/or later (e.g., at the end of the attraction, at the end of the day, at a specified maintenance period, etc.).

The electrical signal information may be gathered during normal operation of the track vehicle system 100. For instance, the second sensor 210 may gather information regarding power, electrical, or other signals propagating through the conductor rails 114 for operation of the track vehicle 104. Additionally, or alternatively, the anomaly detection system 200 may be configured to inject a signal in the one or more components for detection of the anomalies. For example, the anomaly detection system 200 may include its own power source (e.g., a battery 214) to generate and detect signals for analysis of track components when the track vehicle system 100 is not operational.

The controller 206 may be configured to detect anomalies based on a combination of the visual information and the electrical signal information. For instance, the controller 206 may be configured to align the visual defects with the signal defects to detect the anomalies (e.g., the visual and signal defects correspond or match, the visual and signal defects are noted at the same location along the conductor rail 114, etc.). For instance, the visual information may be used to confirm the defects detected in the electrical signal information, or vice-versa, such as to limit false positives, to provide a degree of confidence that actual defects exist, etc. In some examples, the anomaly detection system 200 may include a location sensor 216 (e.g., an RFID (radio frequency identification) reader, a GPS sensor, location marker, or other location sensing equipment or techniques), such as to aid the controller 206 in identifying the location of the anomalies. In some examples, the controller 206 may query or drive a machine learning model used to automatically detect the anomalies (e.g., via machine vision, machine assisted inspection). In this manner, the anomaly detection system 200 may be configured to detect one or more anomalies of track components based on gathered data.

With continued reference to FIG. 2A, the anomaly detection system 200 includes a frame 220. The frame 220 may define attachment or mounting points for the various components discussed above. The frame 220 may be shaped (e.g., L-shaped) to position the sensors and other components for proper detection of track anomalies. For instance, the frame 220 may position at least the first sensor 204 (e.g., the first sensor 204 and the second sensor 210) in proper alignment with the conductor rails 114 for anomaly detection. In examples, the frame 220 may include a mount that fits the needs of the track vehicle system 100 or attraction (e.g., the track vehicle 104).

FIG. 2B illustrates another example anomaly detection system 250. Except as otherwise described below, the anomaly detection system 250 may be similar to the anomaly detection system 200, described above. For example, the anomaly detection system 250 may be configured to detect anomalies of one or more components of the track 102, such as defects, damage, wear, or other anomalies of one or more conductor rails 114, a track fin or beam 254, or other components of track 102 (e.g., automatically using machine vision or machine learning). For convenience, descriptions of like features are omitted.

The anomaly detection system 250 includes first sensor 204, which may be a camera or other visual sensor for detecting visual information of track components. For example, the first sensor may be positioned adjacent one or more conductor rails 114, such as to traverse alongside the conductor rails 114 as the anomaly detection system 250 is moved along the track 102, such as in a manner as described above.

The anomaly detection system 250 may include other sensors. For instance, the anomaly detection system 250 may include location sensor 216. The location sensor 216 may include an RFID (radio frequency identification) reader, a GPS sensor, location marker, or other sensing equipment or technique, such as to determine the position of the anomaly detection system 250 along the track 102. In some examples, the anomaly detection system 250 may include an encoder wheel 260 engaging a track fin 254 or other portions of the track 102, such as for redundancy to the location sensor 216 and/or to improve position determination. As shown, the encoder wheel 260 may ride along the top of the track fin 254, although other configurations are contemplated.

The anomaly detection system 250 may include features for engaging or locating the system with the track 102 (e.g., the track fin 254). For example, the anomaly detection system 250 may include one or more down-stop wheels 264 to locate the anomaly detection system 250 vertically along the track fin 254 (e.g., the down-stop wheels 264 riding along the top of the track fin 254). Additionally, or alternatively, the anomaly detection system 250 may include one or more side-stop wheels 268 to locate the anomaly detection system 250 laterally along the track fin 254 (e.g., the side-stop wheels 268 riding along the lateral sides of the track fin 254). In this manner, the down-stop wheels 264 and side-stop wheels 268 may constrain the anomaly detection system 250, such as to align the anomaly detection system 250 to the track fin 254.

FIG. 2B illustrates portions of the anomaly detection system 250 along one side of the track fin 254. In examples, the anomaly detection system 250 may include a mirrored configuration along the opposite side of the track fin 254. In such examples, the side-stop wheels 268 may be biased to pinch the track fin 254, aligning the anomaly detection system 250 to the track fin 254 (e.g., to ensure the down-stop wheels 264 and encoder wheel 260 ride along the top of the track fin 254).

FIG. 3A illustrates a diagram of the track vehicle system 100, including track vehicle 104, track surface 106, conductor rail 114, and anomaly detection system 200. In examples, the anomaly detection system 200 is mounted to the track vehicle 104 for positioning adjacent the track 102. For instance, the frame 220 may be mounted or coupled to the track vehicle 104. Depending on the application, the anomaly detection system 200 may be selectively coupled or permanently attached to the track vehicle 104. For example, the anomaly detection system 200 may be selectively coupled to the track vehicle 104 during track maintenance, and removed for normal operation. Conversely, the anomaly detection system 200 may be configured for permanent attachment to the track vehicle 104.

As shown, the track vehicle 104 may be configured to traverse along one side of the track 102, with the anomaly detection system 200 positioned on a different side of the track 102 (e.g., above and below the track 102, on opposite sides of the track 102, etc.). In the example illustrated in FIG. 3A, the track vehicle 104 is above the track surface 106, and the anomaly detection system 200 is below the track surface 106, although other configurations are contemplated. In such examples, the frame 220 extends through the channel 112 in the track surface 106 to position the anomaly detection system 200 below the track 102 or below the conductor rail 114. When positioned, the anomaly detection system 200 may be moved along or adjacent the track 102 to detect anomalies. For example, the track vehicle 104 may navigate the track 102 at low speed (e.g., jog speed, alone outside of normal operations, etc.), and the anomaly detection system 200 may record gathered data. In other examples, the anomaly detection system 200 may gather anomaly data during normal operation of the attraction.

Although described as coupled to the track vehicle 104 (e.g., powered by the track vehicle 104 to traverse along the track 102), the anomaly detection system 200 may be self-powered and attachable to the conductor rail 114 without a track vehicle in maintenance mode. For example, the anomaly detection system 200 may be self-propelled or motorized to traverse the track 102, or the anomaly detection system 200 may be pushed, pulled, or otherwise moved along the track 102 using human power. Rather than traversing the track 102 continuously, the anomaly detection system 200 may traverse only certain track sections and pause at certain areas of the conductor rail 114.

With continued reference to FIG. 3A, the first sensor 204 (e.g., a camera) is oriented toward the conductor rail 114. The anomaly detection system 200 may include lighting elements 302 (e.g., LED lights, infrared lights, etc.), such as to illuminate the conductor rail 114 to facilitate visual detection of anomalies. RGB and infrared cameras are just examples, and the first sensor 204 may include other technologies (e.g., thermal, hyperspectral, etc.) to detect anomalies. In examples, the anomaly detection system 200 may include memory 306 (e.g., hard drive), such as for storing instructions and/or gathered data.

The anomaly detection system 200 may include a distance sensor 310 (e.g., ultrasonic, IR (infrared), laser, or proximity sensor), which may determine a distance between the anomaly detection system 200 and the conductor rail 114. In examples, the anomaly detection system 200 may include a collector assembly 314 (e.g., a collector shoe). The collector assembly 314 may mate or slide along the conductor rail 114, such as for power and/or signal transmission with the conductor rail 114. The anomaly detection system 200 may include a motion sensor 320 (e.g., ultrasound, passive IR, microwave, or tomographic sensor, or combinations thereof). The motion sensor 320 may include an accelerometer or other sensor configured to detect motion of the anomaly detection system 200, and may be positioned at or adjacent the collector assembly 314. The anomaly detection system 200 may include a signal analyzer 324. The signal analyzer 324 may analyze signals received from the collector assembly 314 and/or the motion sensor 320 (or provide other signal analysis), such as part of or to facilitate controller 206 (e.g., operations performed by controller 206).

FIG. 3B illustrates a diagram of another implementation of track vehicle system 100, including track vehicle 104, one or more conductor rails 114, and anomaly detection system 250. Except as otherwise described below, the track vehicle system 100 may be similar to that described above with reference to FIG. 3A. Thus, description of similar features (as denoted with the same or similar reference numbers) will be omitted for convenience.

The track vehicle 104 may be embodied as a work tractor. For example, the track vehicle 104 may be configured specifically to move the anomaly detection system 250 along the track 102 (e.g., as part of maintenance operations or a maintenance system). In examples, the track 102 may be embodied as a beam (e.g., a monorail beam, etc.) having conductor rails 114 extending along opposing sides of the track 102. In such examples, the anomaly detection system 250 may traverse the track 102 to detect anomalies in the conductor rail(s) 114 along one side at a time (as shown), or along both sides at the same time. When inspecting one side at a time, the anomaly detection system 250 may make multiple passes along the track 102, or separate anomaly detection systems 250, one configured for each side of the track 102, may traverse the track 102, simultaneously or sequentially.

FIG. 4 illustrates example anomalies 400 detectable by the anomaly detection systems described herein (e.g., anomaly detection system 200, anomaly detection system 250). Depending on the application, the track vehicle system 100 may include a collector shoe 402 (see FIG. 1) that mates or slides along the conductor rail 114, to provide power and other signals to the track vehicle 104. The conductor rail 114 may include a plurality of conductor rails 408 separated by a spacer 406. In such configurations, the conductor rail 114 may accumulate wear and tear (and other anomalies) during normal usage, such as caused by the collector shoe 402 rubbing or sliding along the conductor rail 114. Example anomalies 400 include alignment issues caused by thermal expansion and high speeds, arcing scars created by high voltage, and impact chipping caused by misalignment, among other anomalies. Some areas of the conductor rail 114 may be prone to anomalies 400, such as at a junction 404 between a spacer 406 and an adjacent conductor rail 408.

FIG. 5 illustrates an example report 500 generated by the anomaly detection system 200 or the anomaly detection system 250. The report 500 may be used by an operator of the system to identify track anomalies (e.g., anomalies 400). The report 500 may be reviewed manually (e.g., on a user device for manual review), such as in relation to repair or maintenance operations. The report 500 may include an image 504 of each suspected anomaly 400, the location of the image 504 along the track 102 or ride path, and other useful information or metadata. In some examples, the report 500 may include a recommendation 506 (e.g., a replacement recommendation, a maintenance recommendation, etc.). The report 500 may be generated in real time, such that an operator can see real time footage of the inspection. The report 500 may be notification or output to the user. The report 500 may include more or less information, such as providing just a summary (e.g., track location and estimated issue) or may include an image with or without annotations.

FIG. 6 illustrates an example computing system 600 for implementing various examples described herein. For example, in various embodiments, components of the track vehicle system 100 or other systems described herein may be implemented by one or several computing systems 600. This disclosure contemplates any suitable number of computing systems 600. For example, the computing system 600 may be a server, a desktop computing system, a mainframe, a mesh of computing systems, a laptop or notebook computing system, a tablet computing system, an embedded computer system, a system-on-chip, a single-board computing system, or a combination of two or more of these. Where appropriate, the computing system 600 may include one or more computing systems; be unitary or distributed; span multiple locations; span multiple machines; span multiple data centers; or reside in a cloud, which may include one or more cloud components in one or more networks.

Computing system 600 includes a bus 610 (e.g., an address bus and a data bus) or other communication mechanism for communicating information, which interconnects subsystems and devices, such as one or more processor(s) 608, memory 602 (e.g., RAM), static storage 604 (e.g., ROM), dynamic storage 606 (e.g., magnetic or optical), communications interface 616 (e.g., modem, Ethernet card, a network interface controller (NIC) or network adapter for communicating with an Ethernet or other wire-based network, a wireless NIC (WNIC) or wireless adapter for communicating with a wireless network, such as a WI-FI network), input/output (I/O) interface 620 (e.g., keyboard, keypad, mouse, microphone, display). In particular embodiments, the computing system 600 may include one or more of any such components.

In particular embodiments, processor 608 includes hardware for executing instructions, such as those making up a computer program. For example, a processor 608 may execute instructions for various components of the track vehicle system 100 or other systems described herein. The processor 608 circuitry includes circuitry for performing various processing functions, such as executing specific software to perform specific calculations or tasks. In particular embodiments, I/O interface 620 includes hardware, software, or both, providing one or more interfaces for communication between computing system 600 and one or more I/O devices. Computing system 600 may include one or more of these I/O devices, where appropriate. One or more of these I/O devices may enable communication between a person and computing system 600.

In particular embodiments, the communications interface 616 includes hardware, software, or both providing one or more interfaces for communication (such as, for example, packet-based communication) between computing system 600 and one or more other computer systems or one or more networks. One or more memory buses (which may each include an address bus and a data bus) may couple processor 608 to memory 602. Bus 610 may include one or more memory buses, as described below. In particular embodiments, one or more memory management units (MMUs) reside between processor 608 and memory 602 and facilitate accesses to memory 602 requested by processor 608. In particular embodiments, bus 610 includes hardware, software, or both coupling components of computing system 600 to each other.

According to particular embodiments, computing system 600 performs specific operations by processor 608 executing one or more sequences of one or more instructions contained in memory 602. For example, instructions for the track vehicle system 100 or other systems described herein (e.g., to perform the operations described herein) may be contained in memory 602 and may be executed by the processor 608.

Such instructions may be read into memory 602 from another computer readable/usable medium, such as static storage 604 or dynamic storage 606. In alternative embodiments, hard-wired circuitry may be used in place of or in combination with software instructions. Thus, particular embodiments are not limited to any specific combination of hardware circuitry and/or software. In various embodiments, the term “logic” means any combination of software or hardware that is used to implement all or part of particular embodiments disclosed herein.

The term “computer readable medium” or “computer usable medium” as used herein refers to any medium that participates in providing instructions to processor 608 for execution. Such a medium may take many forms, including but not limited to, nonvolatile media and volatile media. Non-volatile media includes, for example, optical or magnetic disks, such as static storage 604 or dynamic storage 606. Volatile media includes dynamic memory, such as memory 602.

Computing system 600 may transmit and receive messages, data, and instructions, including program, e.g., application code, through communications link 618 and communications interface 616. Received program code may be executed by processor 608 as it is received, and/or stored in static storage 604 or dynamic storage 606, or other storage for later execution. A database 614 may be used to store data accessible by the computing system 600 by way of data interface 612. In various examples, communications link 618 may communicate with the track vehicle system 100 or other systems described herein.

FIG. 7 illustrates an example method 700 for detecting anomalies 400 along the track 102. The method may be implemented using the various systems described herein, such as the track vehicle system 100 or the computing system 600 (e.g., the processor 608). At step 704, the method includes traversing an anomaly detection system (e.g., the anomaly detection system 200 or the anomaly detection system 250) along the track 102. For example, the anomaly detection system 200 or anomaly detection system 250 may be coupled to the track vehicle 104, and the track vehicle 104 may be navigated along the track 102 as part of normal operations, or the track vehicle 104 may be sent down the track 102 specifically for the purpose of gathering track data for anomaly detection (e.g., during monthly inspection or other inspection time frames), such as in a manner as described herein. Step 704 may include installing the anomaly detection system 200 or the anomaly detection system 250 on the track vehicle 104 and activating the anomaly detection system 200 or anomaly detection system 250 for recording. In examples, step 704 may include traversing the anomaly detection system 200 or anomaly detection system 250 along the track 102 using human power, or under the system's own power (e.g., separate from the track vehicle 104).

At step 708, the method 700 includes gathering, via at least one sensor and while traversing along the track 102, data of one or more components of the track 102 (e.g., conductor rail 114). For instance, visual information of track components may be gathered by first sensor 204 and/or signal information through track components may be gathered by second sensor 210, such as in a manner as described herein.

At step 712, the method 700 includes training an image analysis model based on user identification of areas of interest. For example, the gathered visual and/or signal information may be used to train a machine learning model, with a user or operator identifying areas of interest in the gathered data to train the model. As one example, a field expert may provide supervised learning or otherwise teach the anomaly detection system 200 or anomaly detection system 250 (and in particular the image analysis model or another ML model) which track segments within various images are good or bad. The field expert may be used to provide human-in-the loop interaction and/or to provide input to the dataset as part of the training model. Thus, the ML model may then learn as the images are classified. In some implementations, step 712 may be excluded from method 700, such as, for example, when a pre-trained model is provided. Also, step 712 may be performed before step 704 (e.g., using prior data and not necessarily the data obtained from anomaly detection system 200 or 250).

At step 716, the method 700 includes identifying one or more anomalies 400 of the track components based on the gathered data. Step 716 may include processing an image (e.g., image 504) of the track components with machine vision or machine assisted inspection. For example, the trained image analysis model may automatically detect the anomalies 400. In examples, step 716 may include identifying a location of the anomalies 400 based on data from location sensor 216.

At step 720, the method 700 includes generating a report (e.g., the report 500) of the one or more anomalies 400. The report 500 may include a respective image (e.g., image 504) of the detected anomalies 400 and a location of the detected anomalies 400 along the track 102. The report may include a recommended course of action (e.g., recommendation 506) based on the detected anomaly 400 (e.g., a severity of the anomaly 400), an availability of repair/maintenance personnel, an availability of replacement parts, a condition of the track vehicle system 100 (e.g., in operation or out of operation, etc.), a previous course of action, user or ride preference, or the like. The report 500 may be generated on a user device (e.g., a tablet, smartphone, computer, on a graphical user interface, etc.) for manual review. In examples, manual review of the report 500 may provide feedback on detections to improve the machine learning model. The report 500 may be an alert (e.g., to a maintenance crew) reminding or alerting the crew of needed maintenance. The report 500 may include a notification or output to the user, such as on a user device. The report 500 may provide various levels of detail, such as providing a summary only (e.g., track location and estimated issue) or including images without annotations.

The description of certain embodiments included herein is merely exemplary in nature and is in no way intended to limit the scope of the disclosure or its applications or uses. In the included detailed description of embodiments of the present systems and methods, reference is made to the accompanying drawings which form a part hereof, and which are shown by way of illustration specific to embodiments in which the described systems and methods may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice presently disclosed systems and methods, and it is to be understood that other embodiments may be utilized, and that structural and logical changes may be made without departing from the spirit and scope of the disclosure. Moreover, for the purpose of clarity, detailed descriptions of certain features will not be discussed when they would be apparent to those with skill in the art so as not to obscure the description of embodiments of the disclosure. The included detailed description is therefore not to be taken in a limiting sense, and the scope of the disclosure is defined only by the appended claims.

From the foregoing it will be appreciated that, although specific embodiments of the invention have been described herein for purposes of illustration, various modifications may be made without deviating from the spirit and scope of the invention.

The particulars shown herein are by way of example and for purposes of illustrative discussion of the preferred embodiments of the present invention only and are presented in the cause of providing what is believed to be the most useful and readily understood description of the principles and conceptual aspects of various embodiments of the invention. In this regard, no attempt is made to show structural details of the invention in more detail than is necessary for the fundamental understanding of the invention, the description taken with the drawings and/or examples making apparent to those skilled in the art how the several forms of the invention may be embodied in practice.

As used herein and unless otherwise indicated, the terms “a” and “an” are taken to mean “one”, “at least one” or “one or more”. Unless otherwise required by context, singular terms used herein shall include pluralities and plural terms shall include the singular.

Unless the context clearly requires otherwise, throughout the description and the claims, the words ‘comprise’, ‘comprising’, and the like are to be construed in an inclusive sense as opposed to an exclusive or exhaustive sense; that is to say, in the sense of “including, but not limited to”. Words using the singular or plural number also include the plural and singular number, respectively. Additionally, the words “herein,” “above,” and “below” and words of similar import, when used in this application, shall refer to this application as a whole and not to any particular portions of the application.

Of course, it is to be appreciated that any one of the examples, embodiments or processes described herein may be combined with one or more other examples, embodiments and/or processes or be separated and/or performed amongst separate devices or device portions in accordance with the present systems, devices and methods.

Finally, the above discussion is intended to be merely illustrative of the present system and should not be construed as limiting the appended claims to any particular embodiment or group of embodiments. Thus, while the present system has been described in particular detail with reference to exemplary embodiments, it should also be appreciated that numerous modifications and alternative embodiments may be devised by those having ordinary skill in the art without departing from the broader and intended spirit and scope of the present system as set forth in the claims that follow. Accordingly, the specification and drawings are to be regarded in an illustrative manner and are not intended to limit the scope of the appended claims.