ADAPTIVE AUTO-DRILLING FOR DRILLING APPLICATIONS

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims priority to U.S. Provisional Patent Application Ser. No. 63/678,528, filed Aug. 1, 2024, and also claims priority to U.S. Provisional Patent Application Ser. No. 63/686,153, filed Aug. 22, 2024, the entireties of which are hereby incorporated by reference. This application is also related to U.S. Pat. No. 9,194,183, the entirety of which is hereby incorporated by reference.

BACKGROUND

Boreholes, sometimes known as wellbores, are often drilled during mining operations or natural resource exploration and production. For example, blasthole drills may be used in surface mining applications to drill holes that can be loaded with explosives for blasting and rock fragmentation purposes. Other types of drills, including rotating drills, may use a drill bit to grind a borehole into the ground.

The standard practice for drilling a borehole includes drilling a collaring depth at the beginning of the borehole. During collaring, the operator drills slowly and softly to prepare the borehole contour before engaging the full force and speed of the drill. The process may be used to create a well line-up start of the borehole to avoid downhole deviation from the intended borehole orientation. After the collaring depth has been reached, the drilling process may enter a normal drilling segment.

However, the process of drilling is rife with problems and difficulties. Equipment may be subjected to extraordinary stress and may malfunction or break during a drilling operation. A subtle shift in borehole direction may later result in mining, or exploration, and production difficulties. Thus, devices, methods, and systems are sought for improving the accuracy and effectiveness of drilling boreholes.

SUMMARY

A method of drilling a borehole, including drilling, with a drill, the borehole into a subsurface region. The drill includes a drill string, a drill bit connected to the drill string, a hoist control connected to the drill string, and a drill controller for controlling at least one of the drill bit, the drill string, and the hoist control. The method also includes identifying, based on a depth of the drill bit in the subsurface region, a collaring stage of drilling the borehole. The method also includes sensing, with a sensor in operational communication with the drill, a measured parameter of the drill during drilling. The method also includes identifying, based on the collaring stage, a reference value for a drilling parameter of the drill. The reference value is comparable to the measured parameter. The drilling parameter includes a measured value of an operation of the drill during drilling. The method also includes generating a difference between the measured parameter and the reference value. The method also includes determining, from the difference, an adjustment factor to the drilling parameter. The method also includes adjusting the drilling parameter according to the adjustment factor to generate an adjusted drilling parameter. The method also includes modifying, during drilling and with the drill controller, operation of the drill according to the adjusted drilling parameter to change the measured parameter to a new measured parameter.

One or more embodiments also provide for a drill system for drilling a borehole into a subsurface region. The drill system includes a drill string and a drill bit connected to the drill string. The drill system also includes a hoist control connected to the drill string. The drill system also includes a drill controller for controlling at least one of the drill bit, the drill string, and the hoist control. The drill system also includes a sensor in operational communication with the drill. The drill system also includes a computer processor in communication with the sensor. The drill system also includes a data repository in communication with the computer processor. The data repository stores a collaring stage. The data repository also stores a measured parameter of the drill and a new measured parameter of the drill. The data repository also stores a reference value for a drilling parameter of the drill. The reference value is comparable to the measured parameter. The drilling parameter includes a measured value of an operation of the drill during drilling. The data repository also stores an adjusted drilling parameter. The data repository also stores a difference between the measured parameter and the reference value. The data repository also stores an adjustment factor to the drilling parameter. The drill system also includes a server controller executable by the computer processor to command the drill to drill the borehole into the subsurface region. The server controller is also executable by the computer processor to identify, based on a depth of the drill bit in the subsurface region, the collaring stage of drilling the borehole. The server controller is also executable by the computer processor to sense, with the sensor, the measured parameter of the drill during drilling. The server controller is also executable by the computer processor to identify, based on the collaring stage, the reference value. The server controller is also executable by the computer processor to generate the difference. The server controller is also executable by the computer processor to determine, from the difference, the adjustment factor. The server controller is also executable by the computer processor to adjust the drilling parameter according to the adjustment factor to generate the adjusted drilling parameter. The server controller is also executable by the computer processor to command the drill controller to modify, during drilling, operation of the drill according to the adjusted drilling parameter to change the measured parameter to the new measured parameter.

Other aspects of one or more embodiments will be apparent from the following description and the appended claims.

BRIEF DESCRIPTION OF DRAWINGS

FIG. 1A and FIG. 1B show a computing system for adaptive auto-drilling, in accordance with one or more embodiments.

FIG. 2 shows a flowchart of a method for adaptive auto-drilling, in accordance with one or more embodiments.

FIG. 3 shows an overview of individual methods for adaptive auto-drilling, in accordance with one or more embodiments.

FIG. 4 shows a method for dynamic hoist pulldown force and speed control during drilling, in accordance with one or more embodiments.

FIG. 5 shows a method for competent ground detection during drilling, in accordance with one or more embodiments.

FIG. 6 shows another method for dynamic hoist pulldown force control during drilling, in accordance with one or more embodiments.

FIG. 7 shows a method for vibration control during drilling, in accordance with one or more embodiments.

FIG. 8 shows a method for rotation speed ramp control during drilling, in accordance with one or more embodiments.

FIG. 9 shows another method for rotation speed control during drilling, in accordance with one or more embodiments.

FIG. 10 shows a drill machine which may be controlled according to the techniques described with respect to FIG. 1 through FIG. 9, in accordance with one or more embodiments.

FIG. 11 shows an example of a control system for a drill, in accordance with one or more embodiments.

FIG. 12 and FIG. 13 show examples of a drill drilling a borehole according to the techniques described with respect to FIG. 1 through FIG. 9, in accordance with one or more embodiments.

FIG. 14A and FIG. 14B show a computing system and network environment, in accordance with one or more embodiments.

Like elements in the various figures are denoted by like reference numerals for consistency.

Definitions of Terms

As used herein, the following terms have the following meanings:

“OEM” is an acronym standing for “original equipment manufacturer.”

“PLC” is an acronym standing for “programmable logic controller.”

The term “max pulldown force scaler” refers to a maximum amount of pulldown force allowed in relation to the depth of a borehole.

The term “base value” refers to generally static values used as starting or reference points for a drill control system during a drilling operation.

The term “collaring control” refers to a control methodology, described herein, to stabilize the top of a drill borehole in order to prevent material from falling back into the borehole.

The term “feed direction” refers to a hoist system's motion in a downward or lowering direction along the mast towards a borehole.

The term “hoist direction” refers to a hoist system's motion in an upward or raising direction along the mast away from a borehole.

“PN” is an acronym standing for “penetration rate.” The penetration rate is a rate at which a bit penetrates the ground while drilling a borehole.

The term “stroker control” refers to an electronic control over a hydraulic pump to adjust hydraulic fluid direction and flow.

“PID” is an acronym standing for “proportional integral derivative.” The term “PID loops” refers to a proportional integral derivative controller that provides a control mechanism that manipulates an input variable based on an error signal. The error signal may be the difference between the target value and the measured value.

“PD” is an acronym standing for “pulldown.” The term “PD force” refers to the force generated in the feeding direction, generally in relation to the bit of a drill.

DETAILED DESCRIPTION

One or more embodiments are directed to improved devices and methods for controlling a drill to perform a drilling operation in a subterranean surface (e.g., in the ground or into the Earth). Drilling can be difficult, particularly in the beginning phases of drilling a borehole. The difficulties can arise from differing materials encountered as the borehole increases in depth. The difficulties may include deflection of the drill string (i.e., the borehole angles or turns in an undesirable manner), catching of or damage to the drill bit (e.g., the drill bit becomes stuck or is damaged during the drilling process), undue wear and tear on drilling equipment due to unusually high stresses or vibration, and many other difficulties.

The difficulties mentioned above may be overcome or mitigated by way of one or more drilling techniques described herein. The drilling techniques described herein potentially may be used alone or in combination to handle changing subsurface drilling conditions in real time. The term “real time” means on a time scale in which a change in drilling conditions may be detected, and in which drilling equipment or methods may be modified within about the same time scale or within a predetermined time. Together, one or more of the drilling techniques described herein may be referred to as “adaptive auto-drilling,” as the drilling techniques described herein may be performed automatically using a combination of physical equipment, electrical circuits, and computer programs.

Briefly, five drilling techniques are described with respect to adaptive auto-drilling, which again may be performed singly or in combination, depending on prevailing conditions at any time during a drilling operation. The five drilling techniques may be referred to as dynamic pulldown, dynamic hoist speed, competent ground detection, rotational speed control, and vibration control. Dynamic pulldown automatically adjusts the pressure applied to the bottom of the borehole by the drill during drilling. Dynamic hoist speed refers to the speed at which the drill string or drill bit of the drill are hoisted up or down the borehole. Competent ground detection is used to determine when the subsurface feature being drilled at a particular time is of a type at which drilling speed and force may be increased. Rotational speed control refers to adjusting the bit rotation speed in order to accommodate a detected rate of penetration of the drill and thereby avoid plugging the bit with cuttings that are not removed quickly enough. Vibration control refers to modulating rotation speed or pulldown force of the drill in order to contain drill vibration within an acceptable range of measured vibrations of the drill. The various adaptive auto-drilling techniques are described in more detail with respect to the following figures.

FIG. 1A shows a system, in accordance with one or more embodiments. The system includes both a drill (e.g., drill (100)) as well as a computer or application specific integration circuit (e.g., the computer (124), the data repository (112), and possibly one or more user devices (134)).

The drill (100) is a machine that includes components for drilling a borehole into the ground. FIG. 10 through FIG. 13 show examples of the drill (100).

The drill (100) includes a drill string (102). The drill string (102) is a column, rod, tube, etc., referred to as a “string.” The drill string (102) may include a drill pipe (not shown) that transmits drilling fluid (via one or more mud pumps) and torque (via a top drive, typically above the surface) to a drill bit (104). Thus, the drill string (102) connects the drill bit (104) to the drive system that rotates the drill bit (104).

As indicated above, the drill (100) also includes a drill bit (104) connected to the drill string (102). The drill bit (104) is at a distal end of the drill string (102), and thus is disposed to be placed in contact with the drilling surface. The drilling surface is the bottom of the borehole, or the material through which the drill bit (104) is to drill. The drill bit (104) is designed to rotate, possibly independently of the drill string (102), as part of a drilling operation. The drill bit (104) grinds or cuts through the drilling surface.

The drill (100) also includes a hoist control (106). The hoist control (106) is a device or set of devices that lift the drill string (102) up and down within the borehole. The hoist control (106) may be, for example, a cable, a chain, a rack and pinion mechanism, etc.

The drill (100) also includes a drill controller (108). The drill controller (108) is a device or set of devices that control operation of the drill (100). The drill controller (108) may be used to control the drill string (102), the drill bit (104), or the drill controller (108). The drill controller (108) may include physical machinery (e.g., gears, motors, etc.), computers (e.g., the computer (124)), and a combination thereof.

The drill (100) also includes a sensor (110). The sensor (110) is one or more sensors for sensing physical parameters associated with the drill (100) (e.g., the measured parameter (116) or the drilling parameter (118) described with respect to the data repository (112) described below). The sensor (110) may be a vibration sensor, a bit rotation speed sensor, a string translation speed sensor, a pressure sensor, a force sensor, etc. The sensor (110) may be connected to various parts of the drill (100), depending on the nature of the sensor. Thus, the sensor (110) may be connected to the drill string (102), the drill bit (104), the hoist control (106), or the drill controller (108). The sensor (110) may be multiple sensors sensing the same parameter at different locations on the drill (100), may be multiple sensors sensing different parameters at one or more different locations on the drill (100), or a combination thereof.

The system shown in FIG. 1 includes a data repository (112). The data repository (112) is a type of storage unit or device (e.g., a file system, database, data structure, or any other storage mechanism) for storing data. The data repository (112) may include multiple different, potentially heterogeneous, storage units and/or devices.

The data repository (112) may store information describing a collaring stage (114). A collaring stage is the stage at which the drill (100) is digging the collar of a borehole. Collaring is an initial step in the drilling process, particularly in pipe jacking and auger boring. Collaring involves the initial installation of the first casing into the ground, ensuring the borehole is started on the correct trajectory. Collaring is useful for maintaining alignment and preventing deviations that could affect the borehole's integrity and productivity. Proper collaring minimizes disturbance to the alignment of the borehole and ensures that the borehole is accurately aligned to the design trajectory. If an alignment deviation is found during or after collaring, corrections may be made, and in severe cases, the collaring may be performed again. Once collaring is complete, the next casing is lowered into position, and both the casing(s) and auger(s) are aligned to keep the drill string (102), and thus the borehole, on a desired trajectory. Thus, the collaring stage (114) is computer readable data that describes the stage of collaring that the physical drill (100) is in at the initial phase of drilling a borehole.

Collaring may be separated into multiple stages. In an embodiment, the collaring stage (114) may be defined by three distinct stages: slow collar one, slow collar two, and normal collar. The collaring stages are defined by how deep within the borehole the bit has penetrated the ground. In other words, the collaring stage (114) represents a depth of the borehole.

However, because the ground may vary at any given location, there is not necessarily a specific depth for each collaring stage. Rather, a combination of current ground conditions and borehole depth determine the collaring stage. Thus, each of the three collaring stages uses a different base reference for hoist speed reference, pulldown force reference, and rotation speed reference. In general, the collaring stages increase in pulldown force and rotation speed of the drill bit (104), the combination of which has associated hoist speed at which the drill bit (104) is raised or lowered along a mast of the drill (100) (see FIG. 10 and FIG. 13 for an example of the mast). In general, the hoist speed also increases with the collaring stage. A further description of the collaring process is provided with respect to FIG. 2.

The drill (100) also stores a measured parameter (116). The measured parameter (116) is data taken by the sensor (110) and stored in the data repository (112). The measured parameter (116) may refer to multiple different parameters that are sensed and stored as data. The measured parameter (116) therefore, may be a measured rotation rate of the drill bit (104) or drill string (102), a pulldown force on the drill bit (104), a hoist speed of the drill bit (104), a degree of vibration of one or more components of the drill (100), or a combination thereof.

Because the measured parameter (116) is derived from the readings of the sensor (110) (or multiple sensors), the measured parameter (116) (or multiple measured parameters) may be characterized as sensor data. The sensor data is data gathered from one or more sensors disposed on or near a drilling apparatus being used to drill a borehole. For example, the sensor data may describe vibration data taken by one or more vibration sensors disposed on or near a drill bit of a drilling apparatus. However, the sensor data may relate to other types of sensor data, such as the direction of the borehole, the orientation of various components of the drilling apparatus with respect to the direction of gravity, the speed of the drill bit rotation, the force or forces applied to the drill bit or to various other parts of a drill string, and other sensor data. Accordingly, the measured parameter (116) may include any of the sensor data described above.

The data repository (112) also stores a drilling parameter (118). The drilling parameter (118) is a measured value of an operation of the drill during drilling. Thus, the drilling parameter (118) is a subset of the measured parameter (116). Whereas the measured parameter (116) may include many types of data sensed with respect to the borehole, the drill (100), or conditions in and around the drill (100) or borehole, the drilling parameter (118) specifically is a measurement of some operational aspect of the drill (100) (e.g., the rotation speed of the drill bit, the hoist speed, the pulldown force, etc.)

The drilling parameter (118) may be associated with a reference value (120). The reference value (120) is a value that is comparable to the measured parameter (116) (i.e., is also comparable to the drilling parameter (118)). The reference value (120) may be a limit (i.e., a value above which or below which the measured parameter (116) should not exceed) or may be a desired operational parameter (i.e., a value at which the drilling parameter (118) should be at, within a predetermined range). The drilling parameter (118) is predetermined by a technician, or may be determined in real time by a computer program or application specific integrated circuit (e.g., the machine learning model (128) or a traditional computer-executed algorithm).

The data repository (112) also stores an adjustment factor (122). The adjustment factor (122) is a number that is used to determine a degree to which the drilling parameter (118) should be changed. The adjustment factor (122) is used by the computer processor (126) to control one or more components of the drill (100) so that the drilling parameter (118) is changed to be within a desired range (i.e., within or otherwise in conformance with the reference value (120)). Use of the adjustment factor (122) is described with respect to FIG. 2.

The system shown in FIG. 1A may include other components. For example, the system shown in FIG. 1A also may include a computer (124). The computer (124) is one or more computer processors, data repositories, communication devices, and supporting hardware and software. The computer (124) may be in a distributed computing environment, and thus may be a server, a remote computing device (i.e., located at a point distant from the drill (100)), or may be a local computing device (i.e., part of the drill (100), such as located within the drill string (102), on a trailer to which the drill (100) is attached, etc.). The computer (124) is configured to execute one or more applications, such as the machine learning model (128), the server controller (130), and the training controller (132). An example of a computer system and network that may form the computer (124) is described with respect to FIG. 14A and FIG. 14B.

The computer (124) includes a computer processor (126). The computer processor (126) is one or more hardware or virtual processors which may execute computer readable program code that defines one or more applications, such as the machine learning model (128), the server controller (130), and the training controller (132). An example of the computer processor (126) is described with respect to the computer processor(s) (1302) of FIG. 14A.

The computer (124) also includes a machine learning model (128). The machine learning model (128) is an iterative algorithm that adjusts parameters of the programming of the model in order to come to a conclusion regarding data input to the machine learning model (128). The machine learning model (128) may be, for example, a classification machine learning model. For example, the machine learning model (128) may be a supervised machine learning model that determines whether the sensor (110) may be classified into one or more classifications. More specifically, for example, the machine learning model (128) may be a neural network that classifies whether the sensor (110) should be classified as being in a particular drill bit state for which an action should be taken (e.g., to raise the hoist and reduce pressure on the drill bit, reduce the rotation rate of the drill bit, or take some other action with respect to the drilling equipment).

The machine learning model (128) thus may include neural networks and may operate using one or more layers of weights that may be sequentially applied to sets of input data, which may be referred to as input vectors. For each layer of a machine learning model, the weights of the layer may be multiplied by the input vector to generate a collection of products, which may then be summed to generate an output for the layer that may be fed, as input data, to a next layer within the machine learning model. The output of the machine learning model may be the output generated from the last layer within the machine learning model. Multiple machine learning models may operate sequentially or in parallel. The output may be a vector or scalar value. The layers within the machine learning model may be different and correspond to different types of models. As an example, the layers may include layers for recurrent neural networks, convolutional neural networks, transformer models, attention layers, perceptron models, etc. Perceptron models may include one or more fully connected (also referred to as linear) layers that may convert between the different dimensions used by the inputs and the outputs of a model. Different types of machine learning algorithms may be used, including regression, decision trees, random forests, support vector machines, clustering, classifiers, principal component analysis, gradient boosting, etc.

The server (126) also may include a server controller (130). The server controller (130) is software or application specific hardware which, when executed by the computer processor (126), controls and coordinates operation of the software or application specific hardware described herein. Thus, the server controller (130) may control and coordinate execution of the machine learning model (128) and the training controller (132).

The computer (124) also may include a training controller (132). The training controller (132) is software or application specific hardware which, when executed by the computer processor (126), trains one or more machine learning models (e.g., the machine learning model (128)). The training controller (132) is described in more detail with respect to FIG. 1B.

The machine learning model (128) may be trained by the training controller (132) by inputting training data to the machine learning model (128) to generate training outputs that are compared to expected outputs. While the training process is described in more detail with respect to FIG. 1B, briefly, for supervised training, the expected outputs may be labels associated with a given input. For unsupervised learning, the expected outputs may be previous outputs from the machine learning model. The difference between the training output and the expected output may be processed with a loss function to identify updates to the weights of the layers of the model. After training on a batch of inputs, the updates identified by the loss function may be applied to the machine learning model to generate a trained machine learning model. Different algorithms may be used to calculate and apply the updates to the machine learning model, including back propagation, gradient descent, etc.

The system shown in FIG. 1A also may include one or more user devices (134). The user devices (134) may be considered remote or local. A remote user device is a device operated by a third-party (e.g., an end user of a chatbot) that does not control or operate the system of FIG. 1A. Similarly, the organization that controls the other elements of the system of FIG. 1A may not control or operate the remote user device. Thus, a remote user device may not be considered part of the system of FIG. 1A.

In contrast, a local user device is a device operated under the control of the organization that controls the other components of the system of FIG. 1A. Thus, a local user device may be considered part of the system of FIG. 1A.

In any case, the user devices (134) are computing systems (e.g., the computing system (1300) shown in FIG. 14A) that communicate with the computer (124). The sensor data (e.g., the measured parameter (116)), the reference value (120), or the adjustment factor (122) may be received from one or more of the user devices (134). In another embodiment, one or more of the user devices (134) may be operated by a computer technician that services the various components of the system shown in FIG. 1A.

Attention is turned to FIG. 1B, which shows the details of the training controller (132). As mentioned above with respect to FIG. 1A, the training controller (132) is a training algorithm, implemented as software or application specific hardware, that may be used to train one or more of the machine learning models described with respect to the computing system of FIG. 1A.

In general, machine learning models are trained prior to being deployed. The process of training a model, briefly, involves iteratively testing a model against test data for which the final result is known, comparing the test results against the known result, and using the comparison to adjust the model. The process is repeated until the results do not improve more than some predetermined amount, or until some other termination condition occurs. After training, the final adjusted model is applied to unknown data (i.e., data for which the actual result is not known) in order to make predictions.

Some machine learning models may be applied to vector data structures. A vector is a computer readable data structure. A vector may take the form of a matrix, an array, a graph, or some other data structure. However, a frequently used vector form is a one by N matrix, where each cell of the matrix represents the value for one feature. As described above, a feature is a topic of data (e.g., a color of an object, the presence of a word or alphanumeric text, a physical measurement type, etc.). A value is a numerical or other recorded specification of the feature. For example, if the feature is the word “cat,” and the word “cat” is present in a corpus of text, then the value of the feature may be “1” (to indicate a presence of the feature in the corpus of text).

In one or more embodiments, some of the data in the data repository (112) of FIG. 1A may be stored in the form of one or more vectors. For example, the measured parameter (116), drilling parameter (118), control system (120), or adjustment factor (122) may be expressed as one or more vectors. Thus, when the machine learning model (128) is executed during the method of FIG. 2, the data in the data repository (112) may be input in vector format into the machine learning model for execution of the machine learning model.

Returning to the operation of the training controller (138), training starts with training data (176), which may be expressed in vector form. The training data (176) may be any of the data in the data repository (112) taken when drilling past boreholes. Thus, when past boreholes have been drilled, the data regarding the collaring stage (114), a normal drilling stage (if desirable), measured parameter (116), drilling parameter (118), reference value (120), or adjustment factor (122) for each of the past boreholes may be stored and expressed in vector form.

The training data may be labeled. The labels may represent a known result. Thus, a label applied to an instance of the adjustment factor (122) may be “correct” or “incorrect” (i.e., for a prior application of the machine learning model (128), the adjustment factor (122) that was determined at a particular time was evaluated to be correct or incorrect). For example, at a given collaring stage (114), normal drilling stage, and set of measured parameters (i.e., the measured parameter (116)), the machine learning model (128) may predict, at a given training stage, the adjustment factor (122). Because the correct or incorrect value of the adjustment factor (122) at a given collaring stage of drilling the past borehole may be known as correct or incorrect, a label may be applied to the adjustment factor (122) in the training data as either being correct or incorrect.

Thus, the training data (176) may be data for which the final result is known with certainty. If the prediction of the machine learning model (128) (e.g., the prediction of the adjustment factor (122)) does not match the label, then the weights of the layers in the machine learning model (178) (e.g., the machine learning model (128) of FIG. 1A) may be updated and the training process iterated.

More generally, the training data (176) is provided as input to the machine learning model (178), which may be the machine learning model (128) of FIG. 1A. The machine learning model (178) may be characterized as a program that has adjustable parameters. The program is capable of learning and recognizing patterns to make predictions. The output of the machine learning model (178) may be changed by changing one or more parameters of the algorithm, such as the parameter (180) of the machine learning model (178). The parameter (180) may be one or more weights, the application of a sigmoid function, a hyperparameter, or possibly many different variations that may be used to adjust the output of the function of the machine learning model (178).

One or more initial values are set for the parameter (180). The machine learning model (178) is then executed on the training data (176). The result is an output (182), which is a prediction, a classification, a value, or some other output which the machine learning model (178) has been programmed to output.

The output (182) is provided to a convergence process (184). The convergence process (184) is programmed to achieve convergence during the training process. Convergence is a state of the training process, described below, in which a predetermined end condition of training has been reached. The predetermined end condition may vary based on the type of machine learning model (178) being used (supervised versus unsupervised machine learning), or may be predetermined by a user (e.g., convergence occurs after a set number of training iterations, described below).

In the case of supervised machine learning, the convergence process (184) compares the output (182) to a known result (186). The known result (186) is stored in the form of labels for the training data (176). For example, the known result (186) for a particular entry in an output (182) vector of the machine learning model (178) may be a known value, and that known value is a label that is associated with the training data (176).

Continuing the example of supervised machine learning model training, a determination is made whether the output (182) matches the known result (186) to a predetermined degree. The predetermined degree may be an exact match, a match to within a prespecified percentage, or some other metric for evaluating how closely the output (182) matches the known result (186). Convergence may occur when the known result (186) matches the output (182) to within a prespecified percentage. When many predictions are involved, then convergence may occur when more than a threshold number of predictions correctly match the corresponding labels.

For example, the threshold may be 95%. In this case, when the accuracy of the machine learning model (178) reaches 95% (representing that in 95 times out of 100 query predictions the machine learning model (178) correctly predicted an output) then convergence occurs.

In the case of unsupervised machine learning, the convergence process (184) may be compared to the output (182) or to a prior output in order to determine a degree to which the current output changed relative to the immediately prior output or to the original output. Once the degree of change fails to satisfy the threshold degree of change, then the machine learning model may be considered to have achieved convergence. Alternatively, an unsupervised model may determine pseudo labels to be applied to the training data and then achieve convergence as described above for a supervised machine learning model. Other machine learning training processes exist, but the result of the training process may be convergence.

If convergence has not occurred (a “no” at the convergence process (184)), then a loss function (188) is generated. The loss function (188) is a program which adjusts the parameter (180) (one or more weights, settings, etc.) in order to generate an updated parameter (190). The basis for performing the adjustment is defined by the program that makes up the loss function (188). The program may be an algorithm which attempts to guess how the parameter (180) may be changed so that the next execution of the machine learning model (178), using the training data (176) with the updated parameter (190), will have an output (182) that is more likely to result in convergence. In this manner, the next execution of the machine learning model (178) is more likely to match the known result (186) (supervised learning), or which is more likely to result in an output (182) that more closely approximates the prior output (one unsupervised learning technique), or which otherwise is more likely to result in convergence.

In any case, the loss function (188) is used to specify the updated parameter (190). As indicated, the machine learning model (178) is executed again on the training data (176), this time with the updated parameter (190). The process of execution of the machine learning model (178), execution of the convergence process (184), and the execution of the loss function (188) continues to iterate until convergence.

Upon convergence (a “yes” result at the convergence process (184)), the machine learning model (178) is deemed to be a trained machine learning model (192). The trained machine learning model (192) has a final parameter, represented by the trained parameter (194). Again, the trained parameter (194) shown in FIG. 1B may be multiple parameters, weights, settings, etc.

During deployment, the trained machine learning model (192) with the trained parameter (194) is executed again, but this time on unknown data (which may be in the form of an unknown data vector) for which the final result is not known. The output of the trained machine learning model (192) is then treated as a prediction of the information of interest relative to the unknown data.

While FIG. 1A and FIG. 1B show a configuration of components, other configurations may be used without departing from the scope of one or more embodiments. For example, various components may be combined to create a single component. As another example, the functionality performed by a single component may be performed by two or more components.

FIG. 2 shows a flowchart of a method for adaptive auto-drilling, in accordance with one or more embodiments. The method of FIG. 2 may be implemented using the system of FIG. 1 and one or more of the steps may be performed on or received at one or more computer processors (e.g., the computer (124) of FIG. 1) in combination of with a physical drill (e.g., the drill (100) of FIG. 1). In other words, the method of FIG. 2 represents a method of using a computer to control various operational parameters of a physical drill in order to effect one or more adaptive auto-drilling embodiments. The method of FIG. 2 therefore also may be characterized as a method of drilling a borehole.

Step 200 includes drilling, with a drill, the borehole into a subsurface region. The drill includes a drill string, a drill bit connected to the drill string, a hoist control connected to the drill string, and a drill controller for controlling at least one of the drill bit, the drill string, and the hoist control. Drilling the borehole includes applying the bit of the drill to the ground and then rotating the bit while a pulldown force is applied to the bit. The bit grinds the material of the ground into cuttings, which are lifted up and out of the borehole. As the grinding process continues the borehole becomes deeper.

The process of drilling includes other steps not described herein. For example, the process of drilling may include providing additional casing sections around the drill string, pumping mud or liquid into or out of the borehole, or many other drilling procedures, any of which are contemplated within the scope of the method of FIG. 2.

Step 202 includes identifying, based on a depth of the drill bit in the subsurface region, a collaring stage of drilling the borehole. The collaring stage may be determined by a combination of a depth of the borehole and one or more measured parameters of the drill, ground, or other aspects of the drilling environment. In general, the deeper the borehole, the higher the collaring stage. In general, the less competent (i.e., less hard or more fragile) the ground, the lower the collaring stage. However, because ground properties at various depts can vary from location to location at different drilling sites, there generally is no specific depth at which a collaring stage may be reached. Thus, a combination of borehole depth and measured parameters is used to determine the collaring stage.

In general, drilling starts slowly at collar stage one, wherein the pulldown force and rotation speed of the drill bit are relatively slow compared to later pulldown forces and rotation speeds used at different drilling stages. The reference values increase at collar stage 2 and again at normal collar stage. The reference values may increase yet again (e.g., to a maximum value) once competent ground (e.g., solid stone) is reached.

More or fewer collaring stages may be present in a given drilling environment. For example, only two collaring stages may be present, or more than three collaring stages may be present. Furthermore, the drilling parameters may individually vary at the various collaring stages. For example, pulldown force could be higher at a lower collaring stage, assuming a further reduction in drill bit rotation speed. In another example, some collaring stages may have one, more, or all drilling parameters increased relative to a normal collaring stage or even a normal drill phase. Thus, one or more embodiments are not necessarily limited to the collaring phases described above.

Step 204 includes sensing, with a sensor in operational communication with the drill, a measured parameter of the drill during drilling. Sensing is accomplished actively (by commanding a sensor to take a reading) or passively (the sensor continuously takes readings). Again, the measured parameter may be multiple parameters. Thus, for example, the borehole depth, rotation speed of the drill bit, hoist speed of the drill, pulldown force of the drill bit, and degree of vibration of the drill bit may be measured by one or more sensors. The step of sensing may include storing the sensed data in a data repository, and possibly converting the sensed data into a vector format for input to a machine learning model.

Step 206 includes identifying, based on the collaring stage, a reference value for a drilling parameter of the drill. The reference value is comparable to the measured parameter. The drilling parameter includes a measured value of an operation of the drill during drilling. As indicated above with respect to FIG. 1A, the drilling parameter is a sub-type of the measured parameter in that the drilling parameter specifically is a sensed parameter of one or more components of the drill.

Thus, identifying the reference value for a drilling parameter may be performed on a computer processor executing a machine learning model or some other computer program. The drilling parameter may serve as input to the program, and the reference value may be returned. In a simple example, the reference value may be determined by comparing the measured drilling parameter to a table that stores drilling parameters in columns and stores reference values in rows (or vice versa). The determined reference value is the reference value for the corresponding stored drilling parameter in the table that most closely matches the measured parameter. In another example, the reference value may be determined by plugging the drilling parameter into a formula, in which case the reference value is the output of the formula. A machine learning model may take the drilling parameter as input and generate, as output, a predicted reference value. Other techniques for identifying the reference value are also possible.

Step 208 includes generating a difference between the measured parameter and the reference value. The difference may be determined by one or more different methods. In a simple example, the difference may be determined by subtracting the measured parameter from the reference value. The difference may be determined by a formula, such as by taking the derivative of the rate of change of the measured parameter, and then comparing that rate of change to a chart of reference values that vary by rate of change of the measured parameter. Other techniques for generating the difference are possible.

Step 210 includes determining, from the difference, an adjustment factor to the drilling parameter. Determining the adjustment factor may be performed by one or more different methods. For example, the adjustment factor may be determined by comparing the difference to a table of adjustment factors (in rows) to determined differences (in columns) (or vice versa). Similarly, the adjustment factor may be determined by a formula, or from the output of a machine learning model that takes the difference as input. Other techniques for determining the adjustment factor are possible.

Step 212 includes adjusting the drilling parameter according to the adjustment factor to generate an adjusted drilling parameter. In other words, the adjusted drilling parameter becomes a new reference value to which the drill components should be operated. Adjusting the drilling parameter may include overwriting a prior reference value with the new adjusted drilling parameter.

Step 214 includes modifying, during drilling and with the drill controller, operation of the drill according to the adjusted drilling parameter to change the measured parameter to a new measured parameter. Modifying operation of the drill may be performed by commanding a hoist control or drilling controller to change an operational component of the drill such that the current drilling parameter matches the adjusted drilling parameter (i.e., to increase or decrease rotation speed of the drill bit, pulldown force, hoist speed, etc.). Because adjustment happens in real time, the drill may slow and speed up multiple times, possibly multiple times in each collaring stage. In any case, modifying the operation of the drill according to the adjusted drilling parameter includes physically changing how the drill operates when drilling the borehole.

The method of FIG. 2 may be varied. For example, at any of the collaring stages, the method may include determining, from the measured parameter, that a broken ground condition is satisfied. In this case, the measured parameter includes a combination of a rotation speed of the drill bit and a vibration of at least one of the drill bit and the drill string. Then, modifying operation of the drill at step 214 may include slowing drilling, responsive to the broken ground condition being satisfied. Slowing drilling may be performed by one or both of floating the drill bit and reducing a hoist speed of the drill string. In another example, modifying operation of the drill at step 214 may include increasing, after slowing, the rotation speed of the drill bit.

The method of FIG. 2 may be performed iteratively (i.e., continually in real time). Thus, for example, the method may include iterating, continuously, identifying the collaring stage, sensing, identifying the reference value, generating, determining, adjusting, and modifying until a stop condition is satisfied. Drilling may be stopped when the stop condition is satisfied. For example, the stop condition may include the detection of a hazard. The stop condition may include a normal collaring stage, as during the prior iterations of the method the collaring stage may be a collaring stage that is prior to the normal collaring stage (e.g., slow collar 1 and slow collar 2).

In an embodiment, the drill parameter includes a pulldown force and a drill speed. In this case, the method may further include setting the pulldown force to a selected pulldown force and setting the drill speed to a selected drill speed. The selected pulldown force and drill speed may be reference values for the pulldown force and drill speed.

In an embodiment, the collaring stage includes, at a given time, one of a slow collar one stage, a slow collar two stage, and a normal collar stage. The reference value may be different at each of the slow collar one stage, the slow collar two stage, and the normal collar stage.

Thus, in a more specific example, the collaring stage may include a slow collar one stage. In this case, the reference value may include a first hoist speed, a first pulldown force, and a first rotation speed. The measured value may include a first measured hoist speed, a first measured pulldown force, and a first measured rotation speed. Then, the adjustment factor is proportional to at least one difference between the measured value and the reference value.

In another example, the measured value includes a first measured hoist speed, a first measured pulldown force, and a first measured rotation speed. When the adjustment factor is greater than one, then the adjustment factor is applied to the first pulldown force. When the adjustment factor is less than one, then the adjustment factor is applied to the first hoist speed. The adjustment factor may limit the first pulldown force to a maximum including a reference pulldown force.

In another example, the collaring stage includes the slow collar two stage. In this case, the reference value may include a second hoist speed, a second pulldown force, and a second rotation speed. The second hoist speed is higher than the first hoist speed, the second pulldown force is higher than the first pulldown force, and the second rotation speed is higher than the first rotation speed.

In yet another example, the collaring stage includes the normal collar stage. In this case, the reference value includes a third hoist speed, a third pulldown force, and a third rotation speed. The third hoist speed is higher than the second hoist speed, the third pulldown force is higher than the second pulldown force, and the third rotation speed is higher than the second rotation speed.

Considering the collaring stages together, a rotation speed of the drill bit may increase at each of the slow collar two stage and the normal collar stage, relative to the rotation speed at the slow collar one stage. The measured value includes a combination of a penetration rate of the drill bit and a pulldown force of the drill bit. In this case, the method further may include determining that the penetration rate is less than a predetermined percentage of a predetermined collaring penetration rate. Then, the method includes determining that the pulldown force is greater than a predetermined collaring pulldown force. Then, the method includes determining that, responsive to both determining the penetration rate and the pulldown force, a competent ground condition exists. Then, the method includes increasing a rotation speed of the drill bit to a drill phase rotation speed and increasing the pulldown force to a drill phase pulldown force.

Because the method of FIG. 2 may be performed iteratively in real time, the method may also include processing the measured data using a machine learning model. Thus, the method of FIG. 2 also may include embedding data describing a plurality of holes previously drilled by the drill into a vector data structure. In this case, the method also may include executing, by a processor, a machine learning model on the vector data structure to predict the reference value either prior to drilling or during drilling. The method additionally may include further embedding the measured value into the vector data structure. In this case, executing may be performed during drilling. Additionally, the reference value may be predicted based on a combination of the plurality of holes and the measured value.

While the various steps in the flowchart of FIG. 2 are presented and described sequentially, at least some of the steps may be executed in different orders, may be combined or omitted, and at least some of the steps may be executed in parallel. Furthermore, the steps may be performed actively or passively. Additional variations to the method of FIG. 2 are possible, as shown in the following figures.

FIG. 3 through FIG. 13 show examples of one or more embodiments. The following examples are for explanatory purposes only and not intended to limit the scope of one or more embodiments.

FIG. 3 shows an overview of individual methods for adaptive auto-drilling, in accordance with one or more embodiments. Adaptive auto-drilling is described with respect to FIG. 2, but may include automatic control of one or more different drilling aspects. Thus, the adaptive drilling (300) shown in FIG. 3 may be conceptualized as a circle that includes dynamic pulldown (302), vibration control (304), RPM versus penetration rate control (306), competent ground detection (308), and dynamic hoist speed (310). Each of the different controls may be performed, or not performed, at any given time, but may be varied in real time.

The dynamic pulldown (302) refers to varying the pulldown force applied by the drill bit to the drilling surface within the borehole (typically at the bottom of the borehole). In some situations, the top layer of the ground can include fractured rock (e.g., the fractured hard rock (11) shown in FIG. 12), soft rock, hard rock, fragmented rock from previous blast, sticky ground, and a combination thereof.

The variability in the ground consistency at the beginning of the borehole poses challenges to drilling. The variability can result in a stuck bit, deviated borehole, or excessive vibration. In some cases, collar drilling may take much longer than an acceptable amount of time because low drilling settings may drill a borehole very slowly. As a result, an unacceptable loss of mining productivity may occur.

The dynamic pulldown layer of adaptive drilling (300) modulates the pulldown force pushing the drill bit into the ground interface during the collaring phase of the borehole. The dynamic pulldown (302) takes into consideration the penetration rate down the borehole in a manner that matches a good operator performance. By monitoring the ground hardness, the penetration rate, and other measured parameters, the pulldown force may be adjusted gradually to optimize the penetration rate without compromising the borehole collaring (i.e., to achieve a desired drilling outcome for a good standing borehole).

The vibration control (304) represents controlling the amount of vibration that occurs at the drill bit or other portions of the drill. Under some conditions, the drill bit and the drill string may start to vibrate. Vibration can potentially cause damage to the drill. Vibration also may cause the borehole to deviate from a planned borehole route (e.g., the borehole may begin to curve when the borehole should be straight, or vice versa). The vibration control (304) modulates the rotation speed of the drill in order to contain drill vibration within an acceptable range. The pulldown force also may be adjusted when the rotation torque exceeds a configurable threshold.

The RPM versus penetration rate control (306) controls the penetration rate versus the revolutions per minute (RPM) of the drill bit. RPM is a measurement of the rotation speed of the drill bit. In some instances, the drilling penetration rate may exceed the capacity of the rotation speed to flush the cuttings out of the borehole. This event can result in plugging the bit with cuttings, or in a stalled bit. In either case, the operator stops the drill, or the automated system may automatically stop drilling. Then an attempt is made to clear the bit from its cuttings. However, the RPM versus penetration rate control (306) may be used to adjust the bit rotation speed to accelerate in an attempt to flush out the cuttings before the bit is plugged. In other words, the rotation speed of the drill bit may be increased or decreased to grind cuttings before they plug the bit.

The competent ground detection (308) detects whether the drilling surface has reached competent ground. When collaring a borehole, a determination is made when to switch to normal drilling (i.e., at a higher drill rotation speed and pulldown force compared to a collaring stage). The ground interface (i.e., the drilling surface) may be sensed based on the drill response to drilling and the stability of the collar depth. The competent ground detection (308) senses when it is time to switch from collaring to normal drilling. Making the switch at the optimal depth allows the drill to switch to normal drilling sooner rather than later, thereby optimizing drilling production.

The dynamic hoist speed (310) controls the speed at which the drill bit moves either up or down the borehole. The dynamic hoist speed works in conjunction with dynamic pulldown when drilling and independently when hoisting the bit outside the borehole. A hoist or pulldown pump may derive the flow to the hoist pulldown motor controlling the motion speed of the drill bit. The dynamic hoist speed (310) specifically modulates the speed by which the bit moves up and down the borehole in order to dynamically adjust the desired penetration rate based on the current borehole depth. When drilling down the borehole, the pulldown force may be adjusted via a pressure valve setpoint, which is what the dynamic hoist speed (310) controls.

Attention is now turned to FIG. 4 through FIG. 9. FIG. 4 through FIG. 9 are methods for performing the various aspects of the adaptive drilling (300) shown in FIG. 3.

FIG. 4 shows a method for dynamic hoist pulldown force and speed control during drilling, in accordance with one or more embodiments. The method of FIG. 4 corresponds to the dynamic hoist speed (310) of FIG. 3.

Step 400 includes determining a set point value for the hoist speed. The set point value may be determined as described above with respect to FIG. 2 (e.g., the set point value is the reference value). In addition, step 402 includes determining a measured penetration rate (i.e., the “pen” rate shown in FIG. 4).

Step 404 includes performing a penetration rate PID loop. Again, the term “PID” means “proportional integral derivative.” The PID loops refers to a proportional integral derivative controller that provides a control mechanism that manipulates an input variable based on an error signal. The error signal may be the difference between the target value and the measured value. In this case, the PID loop determines whether the measured penetration rate satisfies the set point value.

Step 406 includes determining how to apply the output of the PID loop.

The output may be applied to one of a pulldown (PD) force or a hoist feed speed (the speed at which the bit is hoisted or lowered). Note that, in an embodiment, the dynamic hoist speed (310) controller may concurrently apply both outputs of the decision at step 406.

If the output is to be applied to pulldown force, then at step 408 a collaring pulldown force base value is determined or retrieved from a data repository. At step 409, the collaring PD force is combined with (e.g., multiplied by) the measured penetration rate. The output of the combination is a maximum pulldown scalar output at step 410.

The maximum pulldown scalar is then used to determine step 412, which is the hoist output. The hoist output is the speed at which the hoist system of the drill moves the drill bit up or down the borehole. For example, the hoist output may be a negative number that indicates that the drill bit should be hoisted upwardly at a speed proportional to the negative number. In another example, the hoist output may be a positive number that indicates that the drill bit should be hoisted downwardly at a speed proportional to the positive number.

Returning to step 406, the output of the penetration rate PID loop may be combined with (at step 416) a collaring hoist feed speed base value (received or derived by a computer system at step 414). The output is provided to a selector process at step 422. The selector process determines whether to float the drill bit at step 418 or to adjust a hoist stroker output at step 414. The selection may be driven by a broken ground detection process (step 420). For example, if broken ground is detected at step 420, then the drill bit may be floated at step 418. If the broken ground is not detected at step 420, then the hoist stroker output may be adjusted at step 424.

Note that the method of FIG. 4 is only one example method of performing the dynamic hoist speed (310) of FIG. 3. Thus, other methods are possible.

FIG. 5 shows a method for competent ground detection during drilling, in accordance with one or more embodiments. Thus, the method of FIG. 5 may be an example of competent ground detection (308) in FIG. 3.

At step 502 a normal collaring stage has been reached. A determination is then made at step 504 whether a penetration rate is less than a collar feed rate setpoint. At step 506, if the pulldown force is greater than the collaring pulldown setpoint, then a delay timer may be set at step 510, indicating that the pulldown force should be delayed. Similarly, the borehole depth may be measured. Then, at step 508 (concurrently performed with step 504), a determination is made whether the borehole depth is greater than a collar maximum depth. If so, then again a delay timer is set at step 510.

The method may include, at step 512, determining that competent ground has been detected. If so, then at step 514 the drill bit may be retracted above the ground.

Note that the method of FIG. 5 is only one example method of performing the competent ground detection (308) of FIG. 3. Thus, other methods are possible.

FIG. 6 shows another method for dynamic hoist pulldown force control during drilling, in accordance with one or more embodiments. FIG. 6 is an example method of performing the RPM versus penetration rate control (306) of FIG. 3.

At step 600 a rotational pressure setpoint is received from a data repository or generated by a computer system. Additionally, at step 602, a rotational pressure feedback is measured as one of the drilling parameters.

At step 604, a rotary pounds per square inch (PSI) PID loop is executed. The PSI PID loop monitors rotational torque (the rotational pressure feedback) by comparing the feedback to the rotational pressure setpoint. The control system prevents the rotational torque from becoming greater than a predetermined value by adjusting the hoist pulldown pressure reference, which is received at step 606. At step 608 the output of the rotary PSI PID loop is combined with the pulldown force base setpoint. As the rotational pressure increases above the setpoint, the PID reduces the pulldown force base setpoint at step 610, reducing pressure on the bit, which in turn reduces the rotational pressure feedback.

Note that the method of FIG. 6 is only one example method of performing the RPM versus penetration rate control (306) of FIG. 3. Thus, other methods are possible.

FIG. 7 shows a method for vibration control during drilling, in accordance with one or more embodiments. The method of FIG. 7 is an example of vibration control (304) of FIG. 3.

At step 700 a vibration setpoint is received or generated by a computer system. Additionally, at step 702, a vibration measured parameter is received at the computer system. Then, at step 704, a vibration PID loop compares the setpoint to the vibration measured parameter. Furthermore, at step 710, a rotary speed base setpoint is received at the computer system.

Then, at step 712, the output of the vibration PID loop is combined with the rotary speed base setpoint. The output of step 712 is provided, at step 714, to a rotary speed PID and signal ramp generator. The generator, at step 716, outputs a rotary speed base point. The rotary speed base point, in turn, is used to control the rotation speed of the drill bit. Thus, as vibration increases, the drill bit rotation speed may decrease. Alternatively, as vibration decreases, the drill bit rotation speed may increase.

Concurrently, the vibration parameter measured at step 702 may be used to determine, at step 706, whether the vibration measured parameter exceeds a predetermined value for a predetermined time. If not, then no action is taken. However, if the vibration measured parameter exceeds the predetermined value for a predetermined time, then at step 708 a burp bit control process may be activated. The burp bit control process is shown in FIG. 9.

Note that the method of FIG. 7 is only one example method of performing the vibration control (304) of FIG. 3. Thus, other methods are possible.

FIG. 8 shows a method for rotation speed ramp control during drilling, in accordance with one or more embodiments. The method of FIG. 8 is an example of the dynamic pulldown (302) shown in FIG. 3.

Initially, at step 800, a rotation speed control base value is sent to a rotation speed ramp generator. At step 802, the rotation speed ramp generator will increase or decrease the reference value over a predetermined time period. At the same time, at step 804, a rotation speed sensor sensors a measured value of the rotation speed of the drill bit. Then, at step 806, the rotary speed trim PID loop actively adjusts the post ramp generator speed command in relation to the rotation speed sensor feedback to account for minor differences in pump control. In particular, the outputs of steps 802 and 806 may be combined (e.g., multiplied) at step 808. The output may be used at step 810 in a rotary pump stroker reference command. In this manner, the control system may use speed, rather than a reference control to control the rotation speed of the drill bit, resulting in a more predictable behavior of the drill bit.

Note that the method of FIG. 8 is only one example method of performing the dynamic pulldown (302) of FIG. 3. Thus, other methods are possible.

FIG. 9 shows a method for combining rotation speed and vibration control during drilling, in accordance with one or more embodiments. Specifically, FIG. 9 is an example of a burp bit control process, as initiated at step 708 of FIG. 7. Thus, FIG. 9 is a combination of the vibration control (304) and the RPM versus penetration rate control (306) controls of FIG. 3. “Burp bit” refers to a phenomenon during drilling when the drill bit slows while grinding, suddenly speeds up, slows again, and speeds up again multiple times.

At step 902, a determination is made that the burp bit control is active (i.e., a command to initiate burp bit control was initiated at step 708 of FIG. 7). Then, at step 904, the bit is hoisted (i.e., lifted away from the drilling surface, or at least the pressure against the drilling surface is reduced). At step 906, a determination is made whether a rotary stall has occurred (i.e., whether the drill bit fails to rotate, or fails to rotate at greater than some predetermined rate). If yes, then a bit protection process is triggered at step 908. Bit protection may include further hoisting the bit away from the drilling surface, or potentially lifting the drill bit out of the borehole for cleaning or maintenance.

If the bit rotation does not stall at step 908, (i.e., the drill bit is still rotating) then a determination is made at step 910 whether a measured vibration is determined to be excessive (i.e., exceeds a predetermined reference value). If vibration is excessive, then the process returns to step 904 and the bit is hoisted yet again and the process repeats. However, if at step 910 the vibration is not excessive (i.e. does not exceed a predetermined reference value), then at step 912 the bit is lowered to the bottom of the borehole to resume normal drilling.

Note that the method of FIG. 9 is only one example method of combining multiple aspects of adaptive drilling (300) of FIG. 3. Thus, other combinations are possible.

An integrated example is now provided. Prior to one or more embodiments, operators or technicians would set and or adjust the base values depending on the ground conditions (i.e., a human would guess at the base values based on their experience working in the drilling industry). However, using the speed control loop of one or more embodiments, the control system may adjust the base values in real time in relation to ground conditions.

Collaring is separated into three stages, slow collar one, slow collar two, and normal collar. These stages are defined by how deep within the drill borehole the bit has penetrated the ground defined as the borehole depth, possibly together with prevailing ground conditions at the depth. Each of these stages uses a different base reference for hoist speed reference, pulldown force reference, and rotary speed reference.

Hoist speed reference controls the speed and direction the bit raises or lowers along the mast of the drill. Pulldown force reference controls the pressure at which the bit pushes down on the ground. Rotary speed refence controls the speed at which the rod and bit turn.

As the borehole depth increases, each of the three base reference values may increase in relation to the borehole depth drilled. The increase is performed to start the drill borehole in a controlled manner to minimize disturbing material around the drill borehole.

While collaring, the proportional integral derivative (PID) controller compares desired penetration rate value to the current penetration rate value and determines an adjustment factor. If the adjustment factor is greater than one, then the adjustment factor is applied to the pulldown force control reference. If the adjustment factor is less than one, then the adjustment value is applied to the hoist speed control reference.

The maximum pulldown force scalar limits the amount of pulldown force that can be applied on the bit, in relation to the borehole depth. Starting at the beginning of slow collar two (lowest predetermined value) throughout the normal collar range (highest predetermined value).

Rotational speed begins with a base speed and may adjust depending on the current penetration rate. At lower penetration rates, the rotational speed may be slower, and at higher penetration rates, the rotational speed may increase.

There may be instances where the surface ground could be highly fractured hard rock. Highly fractured rock, in turn, affects the collaring process by catching the bit causing rotational stalled conditions or deflecting the bit to one side, termed bit deflection. The bit deflection condition, if not prevented, may cause the drill borehole to become offset from an intended borehole path or borehole angle, compromising the borehole or damaging a drill rod.

To avoid these conditions, broken ground detection may be used. The system monitors machine vibration and rotational speed. If a higher than normal vibration is detected, or the difference between commanded rotational speed and actual rotational speed is too great, the system triggers a broken ground control process.

The broken ground control process, when activated, floats the bit or reduces the hoist speed control reference, effectively stopping the bit from being pressed into the rock/ground. Rotational speed is increased to 110% of base value. The changes prevent the bit from deflecting off center and allow the bit to move or break the rock, centering the bit in the borehole. Once the vibration or rotational speed returns to normal drilling conditions, the pulldown force reference and rotary speed reference are returned to the dynamically calculated reference values. In turn, the bit then continues penetrating the ground. Furthermore, if competent ground is not detected prior to a predetermined maximum collaring depth setpoint being reached, the system automatically may transition into drilling control.

Competent ground detection, when used with the above-mentioned collaring speed control, can be adapted to more accurately detect the correct transition point between collaring and drilling control. During the normal collaring stage, the penetration rate and pulldown force are monitored. When the actual penetration rate is less than a percentage of the desired collaring penetration rate, and actual pulldown force is greater than the base collaring pulldown force setpoint value, then the control system determines the bit is in competent ground and transitions into drilling control.

In addition, rotational torque may be monitored during normal drilling. The control system prevents the rotational torque from becoming greater than a predetermined value by adjusting the hoist pulldown pressure reference. As the rotational pressure increases above a set value, the PID reduces the pulldown force base setpoint, reducing pressure on the bit, which in turn reduces the rotational pressure feedback.

Furthermore, vibration may be measured via a vibration sensor located on the drill mast and monitored during normal drilling conditions. When vibration is detected, the vibration may indicate that the bit is turning too fast and is ‘skipping’ on the rock rather than grinding the rock. To control this event, the control system reduces the rotary speed command, allowing the bit to press more onto the rock surface and grind or cut the rock.

In some cases, only reducing the rotational speed does not reduce or mitigate the sensed vibration. This event can be due to a rock becoming lodged in the borehole or in the drill bit, or a rock falling down the borehole onto the bit. The control system monitors for this event. Once detected, a burp bit control is activated. The control retracts or hoists the bit until the vibration has dissipated, then lowers the bit back to the bottom of the borehole and resumes normal drilling. While retracting the bit, if the rock gets lodged onto the side wall of the borehole, a bit protection routine is activated.

In addition, a rotary speed control base value is sent to the rotary speed ramp generator. The rotary speed ramp generator may increase or decrease the reference signal over a brief period. At the same time, the rotary speed ‘trim’ PID is actively adjusting the post ramp generator speed command in relation to the rotary speed sensor feedback to account for minor differences in pump control. In this manner, the control system may use speed, rather than reference control, resulting in a more predictable behavior of the drill bit.

The drill may be provided with a system that maps in 3D the trajectory of the drill string, thereby detecting drill rod deflections. A control layer can leverage this information to provide enhanced control over the drill hoist speed, pulldown force and rotation speed. Furthermore, as indicated above, machine learning models may learn from previous holes drilled to anticipate challenging rock conditions before the bit encounters them in the current borehole.

One or more embodiments can be applied to other methods for drilling boreholes, whether they are core drilling, piling, oil & gas drilling, FRAC drilling, road construction drilling, contour drilling, etc.

FIG. 10 shows a drill system which may be controlled according to the techniques described with respect to FIG. 1 through FIG. 9, in accordance with one or more embodiments. FIG. 11 is a schematic representation of a drill system shown in FIG. 10. The drill system (10) shown in FIG. 10 and FIG. 11 may be the drill (100) of FIG. 1. FIG. 11 also shows an example of a control system for a drill, in accordance with one or more embodiments, such as the hoist control (106) or drill controller (108) described in FIG. 1. Thus, FIG. 10 and FIG. 11 should be considered together as a whole.

One embodiment of a drill system (10) for forming or drilling a borehole (12) is shown and described herein as it could be used to form blastholes (14) of the type commonly used in mining and quarrying operations. After the drill system (10) has been used to drill or form a number of blastholes (14) in the desired pattern, the various blastholes (14) are then filled with an explosive material (not shown). The subsequent detonation of the explosive material ruptures or fragments the geologic structure (15), which may then be collected and processed in a manner consistent with the intended application (e.g., mining or quarrying, as the case may be).

Briefly, the drill system (10) of the one or more embodiments increases the quality of boreholes (12), i.e., the percentage of boreholes (12) that comply with the desired borehole specification. Significantly, the one or more embodiments not only increases initial borehole quality, i.e., immediately after the boreholes (12) are drilled, but also long-term borehole quality, i.e., the percentage of boreholes (12) that remain in compliance after they have been formed. That is, boreholes (12) that are formed in accordance with the teachings of the one or more embodiments are less subject to cave-ins and other post-drilling events that would otherwise make compliant boreholes (12) non-compliant.

The one or more embodiments increases both initial and long-term borehole quality by monitoring one or more drill parameters while the boreholes (12) are being formed or drilled. The monitored drill parameter(s) is compared with a predetermined specification for the parameter(s). If the monitored drill parameter is outside the specification, the one or more embodiments selects and implements one or more defect mitigation routines to ensure that the borehole (12) is drilled to the desired specification. Significantly, the defect mitigation routine(s) also helps to ensure that the borehole (12) remains compliant even after it has been drilled. Explained another way, the drill system (10) uses the monitored drill parameter to draw a conclusion about one or more borehole characteristics. The system then chooses the mitigation routine that will most effectively mitigate or compensate for the particular borehole characteristic. Consequently, the one or more embodiments allows for a significant increase in the number of boreholes (12) that are compliant with the particular borehole specification, both on an initial and long-term basis.

Referring now to FIGS. 10 and 11 together, in one embodiment the drill system (10) may include a drill rig (16) having a mast or derrick (18) configured to support a drill string (20) having a drill bit (32) provided on the end thereof. Drill rig (16) may also be provided with various systems for operating the drill string (20) to form boreholes (12) (e.g., blastholes (14)). For example, in the embodiments shown and described herein, drill rig (16) may also include a drill motor system (22), a drill hoist system (24), an air injection system (26), and a water injection system (28), as best seen in FIG. 11. The drill system (10) of the one or more embodiments may also include a control system (30) that is operatively associated with the drill rig (16), as well as the various systems thereof, e.g., motor system (22), hoist system (24), air injection system (26), and water injection system (28). As explained in much greater detail above with respect to FIG. 1 through FIG. 9, the control system (30) (e.g., the hoist control (106) and the drill controller (108) of FIG. 1) monitors various drill parameters generated or produced by the various drill systems and controls them as to form the blasthole (14). In doing so, control system (30) may also implement the various borehole defect mitigation routines in order to improve blasthole quality.

As its name implies, drill motor system (22) is connected to the drill string (20) and may be operated by control system (30) to provide a rotational force or torque to rotate the drill bit (32) provided on the end of the drill string (20). Control system (30) may operate drill motor system (22) so that the drill bit (32) rotates in either the clockwise or counterclockwise directions. Drill motor system (22) may also be provided with various sensors and transducers (e.g., sensor (110) of FIG. 1) to allow the control system (30) to monitor or sense the rotational force or torque applied to the drill bit (32), as well as the rotational speed and direction of rotation of the drill bit (32).

Drill hoist system (24) is also connected to the drill string (20) and may be operated by control system (30) to raise and lower drill bit (32). As was the case for the drill motor system (22), the drill hoist system (24) may also be provided with various sensors and transducers (e.g., sensor (110) of FIG. 1) to allow the control system (30) to monitor or sense the hoisting forces applied to the drill string (20) as well as the vertical position or depth of the drill bit (32).

The air injection system (26) of drill rig (16) is operatively connected to drill string (20) and may be operated by control system (30) to provide high pressure air to the drill string (20). The high pressure air from air injection system (26) is directed through a suitable conduit (not shown) provided in drill string (20) and ultimately exits the drill string (20), typically though one or more openings (not shown) provided in drill bit (32). The high pressure air from air injection system (26) is primarily used to assist in the bailing or removal from the borehole (12) of cuttings (34) dislodged by the rotating drill bit (32). However, the system and method of the one or more embodiments may use the high pressure air for other purposes as well.

As was the case for the other systems of drill rig (16), the air injection system (26) may be provided with various sensors and transducers (e.g., sensor (110) of FIG. 1) to allow the control system (30) to monitor or sense various drill parameters relating to the function and operation of the air injection system (26).

The water injection system (28) of drill rig (16) is also operatively connected to the drill string (20). Control system (30) may operate the water injection system (28) to provide a drilling fluid, such as water, to the drill bit (32). More specifically, pressurized water from the water injection system (28) is directed through a suitable conduit or passageway (not shown) provided in drill string (20), whereupon it ultimately exits the drill string (20), typically through one or more openings (not shown) provided in drill bit (32). The water (or other drilling fluid) from water injection system (28) is primarily used to assist in the removal of cuttings (34) from borehole (12). However, the system and method of the one or more embodiments may also use the water injection system (28) for other purposes as well.

The water injection system (28) may also be provided with various sensors and transducers (e.g., sensor (110) of FIG. 1) to allow the control system (30) to monitor or sense various drill parameters relating to the function and operation of the water injection system (28). As mentioned, the control system (30) is operatively connected to various systems and devices of drill rig (16) and receives information (e.g., drill parameters, including the drilling parameter (118) and the adjustment factor (122) of FIG. 1) from the various systems and devices of drill rig (16) in the manner described herein. In addition, control system (30) also stores program steps for program control, processes data, chooses or selects one or more borehole defect mitigation routines (e.g., the method of FIG. 2 or the adaptive drilling (300) described in FIG. 3 through FIG. 9), and implements those routines by the appropriate control of the various systems and devices of drill rig (16).

FIG. 12 and FIG. 13 show examples of a drill drilling a borehole according to the techniques described with respect to FIG. 1 through FIG. 9, in accordance with one or more embodiments. FIG. 12 shows a pictorial representation of a borehole showing a blockage area around the drill. FIG. 13 is a pictorial representation of a borehole showing moderate and heavy fracture zones.

Turning first to FIG. 12, when retracting the rotation drill string (20) from the borehole (12), control system (30) (see FIG. 10 and FIG. 11) monitors the hoist speed (e.g., the speed at which the drill bit (32) is being retracted from borehole (12)). Control system (30) also monitors the torque applied to the drill bit (32) as well as its rotation speed. Control system (30) compares these monitored drill parameters with predetermined specifications for these respective parameters during the retraction phase. If the bit retraction rate and rotational speed decline with a corresponding increase in torque, it is likely that material (98) has fallen from borehole wall (74) and is interfering with the rotating drill bit (32), as illustrated in FIG. 12. Once the drill bit (32) has been jammed or hung-up by material (98), control system (32) implements or performs the various auto-drilling techniques to mitigate the impediment, such as described with respect to the method of FIG. 2 or the examples of FIG. 3 through FIG. 9. In this manner, the drill bit (32) may be better controlled, especially through difficult formations such as fractured hard rock (11).

In addition, and with reference now primarily to FIG. 13, when fractured areas (92) are encountered, they can cause failure points in the wall (74) of the borehole (12). These failure points are manifested as voids in the normally intact borehole wall (74). Loose rocks and material (e.g., rocky material (17)) may fall to the bottom of the borehole (12) resulting in boreholes (12) that are not as deep as when originally drilled. In catastrophic cases, i.e., where the geologic structure (15) is heavily fractured, these voids can lead to complete borehole failure, i.e., where the entire borehole (12) is filled up by sloughing material from the fractured areas (92). For example, a heavily fractured area (94) near the bottom of the borehole (12) has resulted in a major void (96) forming at the bit (32). Failing to reduce the penetration rate and rotational speed will result in a borehole failure in most instances. The methods described with respect to FIG. 2 and the examples of FIG. 3 through FIG. 9 may be used to better control the penetration rate and rotational speed and thereby mitigate borehole failure.

One or more embodiments may be implemented on a computing system specifically designed to achieve an improved technological result. When implemented in a computing system, the features and elements of the disclosure provide a significant technological advancement over computing systems that do not implement the features and elements of the disclosure. A combination of mobile, desktop, server, router, switch, embedded device, or other types of hardware may be improved by including the features and elements described in the disclosure.

For example, as shown in FIG. 14A, the computing system (1400) may include one or more computer processor(s) (1402), non-persistent storage device(s) (1404), persistent storage device(s) (1406), a communication interface (1408) (e.g., Bluetooth interface, infrared interface, network interface, optical interface, etc.), and numerous other elements and functionalities that implement the features and elements of the disclosure. The computer processor(s) (1402) may be an integrated circuit for processing instructions. The computer processor(s) (1402) may be one or more cores, or micro-cores, of a processor. The computer processor(s) (1402) includes one or more processors. The computer processor(s) (1402) may include a central processing unit (CPU), a graphics processing unit (GPU), a tensor processing unit (TPU), combinations thereof, etc.

The input device(s) (1410) may include a touchscreen, keyboard, mouse, microphone, touchpad, electronic pen, or any other type of input device. The input device(s) (1410) may receive inputs from a user that are responsive to data and messages presented by the output device(s) (1412). The inputs may include text input, audio input, video input, etc., which may be processed and transmitted by the computing system (1400) in accordance with one or more embodiments. The communication interface (1408) may include an integrated circuit for connecting the computing system (1400) to a network (not shown) (e.g., a local area network (LAN), a wide area network (WAN) such as the Internet, mobile network, or any other type of network) or to another device, such as another computing device, and combinations thereof.

Further, the output device(s) (1412) may include a display device, a printer, external storage, or any other output device. One or more of the output device(s) (1412) may be the same or different from the input device(s) (1410). The input device(s) (1410) and output device(s) (1412) may be locally or remotely connected to the computer processor(s) (1402). Many different types of computing systems exist, and the aforementioned input device(s) (1410) and output device(s) (1412) may take other forms. The output device(s) (1412) may display data and messages that are transmitted and received by the computing system (1400). The data and messages may include text, audio, video, etc., and include the data and messages described above in the other figures of the disclosure.

Software instructions in the form of computer readable program code to perform embodiments may be stored, in whole or in part, temporarily or permanently, on a non-transitory computer readable medium such as a solid state drive (SSD), compact disk (CD), digital video disk (DVD), storage device, a diskette, a tape, flash memory, physical memory, or any other computer readable storage medium. Specifically, the software instructions may correspond to computer readable program code that, when executed by the computer processor(s) (1402), is configured to perform one or more embodiments, which may include transmitting, receiving, presenting, and displaying data and messages described in the other figures of the disclosure.

The computing system (1400) in FIG. 14A may be connected to, or be a part of, a network. For example, as shown in FIG. 14B, the network (1420) may include multiple nodes (e.g., node X (1422) and node Y (1424), as well as extant intervening nodes between node X (1422) and node Y (1424)). Each node may correspond to a computing system, such as the computing system shown in FIG. 14A, or a group of nodes combined may correspond to the computing system shown in FIG. 14A. By way of an example, embodiments may be implemented on a node of a distributed system that is connected to other nodes. By way of another example, embodiments may be implemented on a distributed computing system having multiple nodes, where each portion may be located on a different node within the distributed computing system. Further, one or more elements of the aforementioned computing system (1400) may be located at a remote location and connected to the other elements over a network.

The nodes (e.g., node X (1422) and node Y (1424)) in the network (1420) may be configured to provide services for a client device (1426). The services may include receiving requests and transmitting responses to the client device (1426). For example, the nodes may be part of a cloud computing system. The client device (1426) may be a computing system, such as the computing system shown in FIG. 14A. Further, the client device (1426) may include or perform all or a portion of one or more embodiments.

The computing system of FIG. 14A may include functionality to present data (including raw data, processed data, and combinations thereof) such as results of comparisons and other processing. For example, presenting data may be accomplished through various presenting methods. Specifically, data may be presented by being displayed in a user interface, transmitted to a different computing system, and stored. The user interface may include a graphical user interface (GUI) that displays information on a display device. The GUI may include various GUI widgets that organize what data is shown, as well as how data is presented to a user. Furthermore, the GUI may present data directly to the user, e.g., data presented as actual data values through text, or rendered by the computing device into a visual representation of the data, such as through visualizing a data model.

With respect to physical objects, the term “connected to” contemplates at least two meanings, unless stated otherwise. In a first meaning, “connected to” means that component A was, at least at some point, separate from component B, but then was later joined to component B in either a fixed or a removably attached arrangement. In a second meaning, “connected to” means that component A could have been integrally formed with component B. Thus, for example, a bottom of a pan is “connected to” a wall of the pan. The term “connected to” may be interpreted as the bottom and the wall being separate components that are snapped together, welded, or are otherwise fixedly or removably attached to each other. However, the bottom and the wall may be deemed “connected” when formed contiguously together as a monocoque body.

In addition, the term “directly connected to” means that component A and component B are connected immediately adjacent to each other. For example, component A and component B may share a common point of contact in at least one area of both components. However, the common point of contact may be a connector (e.g., a bolt, a screw, etc.), in which case it is possible that component A is “directly connected to” component B without a direct contact between the surfaces of component A and component B. However, in any case, if component A and component B are “directly connected to” each other, then no intervening parts, other than possibly a connector, exist between component A and component B.

In the context of computers and electronic communication, the terms “connected to” or “in communication with” contemplate multiple meanings. The terms may mean an direct or indirect (e.g., through another component or network). A connection may be wired or wireless. A connection may be a temporary, permanent, or a semi-permanent communication channel between two entities.

The various descriptions of the figures may be combined and may include, or be included within, the features described in the other figures of the application. The various elements, systems, components, and steps shown in the figures may be omitted, repeated, combined, or altered as shown in the figures. Accordingly, the scope of the present disclosure should not be considered limited to the specific arrangements shown in the figures.

In the application, ordinal numbers (e.g., first, second, third, etc.) may be used as an adjective for an element (i.e., any noun in the application). The use of ordinal numbers is not to imply or create any particular ordering of the elements, nor to limit any element to being only a single element unless expressly disclosed, such as by the use of the terms “before,” “after,” “single,” and other such terminology. Rather, ordinal numbers distinguish between the elements. By way of an example, a first element is distinct from a second element, and the first element may encompass more than one element and succeed (or precede) the second element in an ordering of elements.

Further, unless expressly stated otherwise, the conjunction “or” is an inclusive “or” and, as such, automatically includes the conjunction “and,” unless expressly stated otherwise. Further, items joined by the conjunction “or” may include any combination of the items with any number of each item, unless expressly stated otherwise.

In the above description, numerous specific details are set forth in order to provide a more thorough understanding of the disclosure. However, it will be apparent to one of ordinary skill in the art that the technology may be practiced without these specific details. In other instances, well-known features have not been described in detail to avoid unnecessarily complicating the description. Further, other embodiments not explicitly described above can be devised which do not depart from the scope of the claims as disclosed herein. Accordingly, the scope should be limited only by the attached claims.