CN117722170A - Method and device for automatically controlling drilling operation - Google Patents
Method and device for automatically controlling drilling operation Download PDFInfo
- Publication number
- CN117722170A CN117722170A CN202410178485.7A CN202410178485A CN117722170A CN 117722170 A CN117722170 A CN 117722170A CN 202410178485 A CN202410178485 A CN 202410178485A CN 117722170 A CN117722170 A CN 117722170A
- Authority
- CN
- China
- Prior art keywords
- control
- representing
- drilling
- drill
- action
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005553 drilling Methods 0.000 title claims abstract description 122
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000008569 process Effects 0.000 claims abstract description 13
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 9
- 230000009471 action Effects 0.000 claims description 38
- 238000012549 training Methods 0.000 claims description 31
- 238000003066 decision tree Methods 0.000 claims description 18
- 230000015572 biosynthetic process Effects 0.000 claims description 16
- 238000012544 monitoring process Methods 0.000 claims description 13
- 238000013528 artificial neural network Methods 0.000 claims description 12
- 238000007637 random forest analysis Methods 0.000 claims description 12
- 230000000694 effects Effects 0.000 claims description 9
- 238000012935 Averaging Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 239000002002 slurry Substances 0.000 claims description 6
- 230000008030 elimination Effects 0.000 claims description 5
- 238000003379 elimination reaction Methods 0.000 claims description 5
- 238000005299 abrasion Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 abstract description 2
- 238000012502 risk assessment Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 19
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000005086 pumping Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000009430 construction management Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention discloses a method and a device for adopting automatic control in drilling operation, and particularly relates to the field of automatic control of drilling operation; and in the process of eliminating the stuck control, the stuck risk assessment is carried out by utilizing a machine learning algorithm, so that the risk prediction can be carried out on the stuck control, and the automation of drilling operation is improved.
Description
Technical Field
The invention relates to the field of automatic control of drilling operation, in particular to a method and a device for adopting automatic control in drilling operation.
Background
Drilling tool control in drilling operations refers to the precise manipulation and management of tools (including drill pipe, drill bit, drill tool assembly, etc.) during drilling. Such control is primarily concerned with adjusting and optimizing various parameters of the drilling operation to improve drilling efficiency, ensure operational safety, and minimize drilling costs.
The quality of the existing drilling operation is mainly determined by the experience of operators, and deviation is easy to occur. The field construction management difficulty is high, the labor intensity of drillers is high, the drilling operation is carried out in a manual operation mode, and each procedure needs an operator to judge and operate.
Disclosure of Invention
The invention aims to automatically control the existing drilling, automatically process parameter data related to drilling operation by combining an artificial intelligent algorithm, and solve the problems of control deviation, high management difficulty and the like.
The method for automatically controlling the drilling operation comprises the following steps:
s1, data acquisition;
s2, drilling control, drill-down control, drill-up control, reaming/reaming control and drill sticking removal control are respectively carried out through a system terminal according to the acquired data;
the drilling control specifically comprises the following substeps:
s201, defining a state space and an action space, wherein the state space represents the input of the DQN model, the state space at least comprises a bit position, a bit rotating speed, an axial force, a feeding speed, a slurry flow, formation hardness and bit abrasion, and the action space at least comprises rotating speed control, axial force control and bit replacement;
s202, evaluating the effect of each action by defining a return function;
using the mean square error to evaluate the difference between the predicted Q value and the target Q value, for each training step, the network is updated using the following loss function:
；
wherein the saidRepresenting a loss function, said->Representing neural network parameters, said->Representing the averaging or expectation of training data, said +.>Indicating immediate return and status +.>Take action->Immediate return of time, said +.>Representing a discount factor, said->Has a value between 0 and 1, said +.>Is indicated in new state->All possible actions->Maximum value of Q value of said +.>Parameters representing the target network, said +.>Representing parameters of the current neural network, said +.>Representing the current state space, said +.>Representing the current state +.>Action taken downwards, said ++>Representing execution of an action->The next state after that, the ∈>Representing a new state->A downward motion;
s203, adjusting drilling parameters in real time through the trained model, and selecting the optimal action as output.
Further, in the step S2, the drill-down control specifically includes: the drilling tool is sent to a preset depth through closed-loop control, and the implementation process is as follows:
；
wherein the saidRepresenting a new depth position of the drilling tool, said +.>Representing the current depth position of the drilling tool, said +.>Represents the feed-down speed, said +.>Representing a time interval.
Further, in the step S2, the drill-up control specifically includes: and monitoring the state of the drill rod through image processing and feature recognition, and extracting the drill rod.
Further, in the step S2, excluding the stuck control specifically includes the following substeps:
s211, monitoring the motion state of a drill bit and drilling parameters, wherein the drilling parameters comprise feed speed, drill bit rotating speed, axial force, torque, pumping pressure, slurry flow and formation drillability information;
s212, extracting features, analyzing the features through a random forest algorithm and predicting the stuck risk.
Further, the step S212 specifically further includes the following sub-steps:
s2121, constructing a model through decision trees, and training each tree by using a randomly selected feature subset;
s2122, training the decision tree by using information gain as a splitting standard for each tree, wherein the information gain calculation flow is as follows:
；
wherein the saidRepresenting the gain of the information, said->Representing an measure of the degree of non-purity, said +.>Representing a parent node, said->Indicate->A dataset of individual child nodes, said +.>Indicate->The number of samples of a child node, said +.>Representing the number of samples of the parent node;
s2123, each tree gives a prediction result, and the final output of the random forest model is the average value or a plurality of tickets of all decision tree outputs.
Further, after the drilling control, the method further includes step S204: the realization control module of the external control terminal pops up a prompt to inform an operator to execute the coring operation.
An apparatus for employing automation control in a drilling operation, comprising:
the external control terminal is used for starting and stopping drilling control, reaming/reaming control and drill sticking removal control and displaying control data;
the internal control system is used for outputting corresponding data results to the external control terminal according to the acquired parameter data,
wherein the external control terminal includes:
the drilling control on-off module is used for on-off the drilling control;
the drill-down control opening and closing module is used for opening and closing drill-down control;
the drill starting control start-stop module is used for starting and stopping the drill starting control;
the reaming/reaming control opening and closing module is used for opening and closing reaming/reaming control;
the drill clamping removal control opening and closing module is used for opening and closing the drill clamping removal;
the display control module is used for displaying the current drilling operation data;
the internal control system includes:
the drilling control unit is used for optimizing drilling control in a drilling environment through the DQN model;
the drill-down control unit is used for automatically detecting and adjusting the angle and the position of the drill rod;
the tripping control unit is used for monitoring the state of the drill rod through image processing and feature recognition;
and the drill sticking elimination control unit is used for analyzing the characteristics through a random forest algorithm and predicting the drill sticking risk.
Further, the drilling control unit includes:
a state space and action space defining subunit for defining a state space and an action space, wherein the state space represents an input of the DQN model, the state space at least including a bit position, a bit rotational speed, an axial force, a feed speed, a formation hardness, and bit wear, the action space at least including rotational speed control, axial force control, and bit replacement;
a reward function definition subunit for evaluating the effect of each action by defining a reward function;
a model training subunit for estimating the difference between the predicted Q value and the target Q value using the mean square error, and for each training step updating the network using the following loss function:
；
wherein the saidRepresenting a loss function, said->Representing neural network parameters, said->Representing the averaging or expectation of training data, said +.>Indicating immediate return and status +.>Take action->Immediate return of time, said +.>Representing a discount factor, said->Has a value between 0 and 1, said +.>Is indicated in new state->All possible actions->Maximum value of Q value of said +.>Parameters representing the target network, said +.>Representing parameters of the current neural network, said +.>Representing the current state space, said +.>Representing the current state +.>Action taken downwards, said ++>Representing execution of an action->The next state after that, the ∈>Representing a new state->A downward motion;
s203, adjusting drilling parameters in real time through the trained model, and selecting the optimal action as output.
Further, the drill sticking elimination control unit includes:
the parameter state acquisition subunit is used for monitoring the motion state of the drill bit and drilling parameters, wherein the drilling parameters comprise feed speed, drill bit rotating speed, axial force, torque, pump pressure and formation drillability information;
the model construction subunit is used for constructing a model through decision trees and respectively training each tree by using the randomly selected feature subsets;
the model training subunit is used for training the decision tree by using the information gain as a splitting standard for each tree, wherein the calculation flow of the information gain is as follows:
；
wherein the saidRepresenting the gain of the information, said->Representing an measure of the degree of non-purity, said +.>Representing a parent node, said->Indicate->A dataset of individual child nodes, said +.>Indicate->The number of samples of a child node, said +.>Representing the number of samples of the parent node;
and the prediction output subunit is used for giving a prediction result to each tree, and outputting the average value or a plurality of tickets of all decision tree outputs by the final output of the random forest model.
The beneficial effects of the invention are as follows:
according to the invention, the state space, the action space and the return function are designed by combining the deep Q learning, so that the model can learn an effective drilling strategy, the drilling operation can be optimized, the efficiency is improved, and the drill bit abrasion and the overall cost are reduced; and in the process of eliminating the stuck control, the stuck risk assessment is carried out by utilizing a machine learning algorithm, so that the risk prediction can be carried out on the stuck control, and the automation of drilling operation is improved.
Drawings
FIG. 1 is a flow chart of a drilling control principle of a method for automatic control in drilling operation according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an external control terminal employing automatic control in drilling operation according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a terminal device according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a product for implementing a method for automated control in a drilling operation according to an embodiment of the present invention.
Detailed Description
The technical solution of the present invention will be described in further detail with reference to the accompanying drawings, but the scope of the present invention is not limited to the following description.
For the purpose of making the technical solution and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the particular embodiments described herein are illustrative only and are not intended to limit the invention, i.e., the embodiments described are merely some, but not all, of the embodiments of the invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by a person skilled in the art without making any inventive effort, are intended to be within the scope of the present invention. It is noted that relational terms such as "first" and "second", and the like, are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.
Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
The features and capabilities of the present invention are described in further detail below in connection with the examples.
A method for employing automation control in a drilling operation, comprising the steps of:
s1, data acquisition;
s2, drilling control, drill-down control, drill-up control, reaming/reaming control and drill sticking removal control are respectively carried out through a system terminal according to the acquired data;
as shown in fig. 1, the drilling control specifically includes the following sub-steps:
s201, defining a state space and an action space, wherein the state space represents the input of the DQN model, the state space at least comprises a bit position, a bit rotating speed, an axial force, a feeding speed, a slurry flow, formation hardness and bit abrasion, and the action space at least comprises rotating speed control, axial force control and bit replacement;
s202, evaluating the effect of each action by defining a return function;
using the mean square error to evaluate the difference between the predicted Q value and the target Q value, for each training step, the network is updated using the following loss function:
；
wherein the saidRepresenting a loss function, said->Representing neural network parameters, said->Representing the averaging or expectation of training data, said +.>Indicating immediate return and status +.>Take action->Immediate return of time, said +.>Representing a discount factor, said->Has a value between 0 and 1, said +.>Is indicated in new state->All possible actions->Maximum value of Q value of said +.>Parameters representing the target network, said +.>Representing parameters of the current neural network, said +.>Representing the current state space, said +.>Representing the current state +.>Action taken downwards, said ++>Representing execution of an action->The next state after that, the ∈>Representing a new state->A downward motion;
s203, adjusting drilling parameters in real time through the trained model, and selecting the optimal action as output.
Further, the axial force represents the vertical force applied directly to the bit, and the axial force needs to be adjusted to achieve optimal drilling efficiency during drilling, depending on different characteristics of the formation (e.g., hardness, fracture, etc.).
Further, the formation drillability information described in this embodiment is the resistance of the formation to the drill bit or the ease of drilling when drilling activities are performed.
Further, for the DQN model of the present embodiment, the input layer corresponds to the dimension of the state space, and includes a plurality of depth hidden layers, each layer includes a large number of neurons, a nonlinear activation function (e.g. ReLU) is used to increase the expressive power of the model, and the output layer predicts the Q value for each possible action, which specifically includes: storing a "state-action-return-new state" sequence during drilling; storing the experiences using a fixed size buffer, the new experience replacing the oldest experience when the buffer is full; during training, small batches of data are randomly extracted from the buffer area, so that time correlation among the data is broken, and learning efficiency is improved.
Further, in the step S2, the drill-down control specifically includes: the drilling tool is sent to a preset depth through closed-loop control, and the implementation process is as follows:
；
wherein the saidRepresenting a new depth position of the drilling tool, said +.>Representing the current depth position of the drilling tool, said +.>Represents the feed-down speed, said +.>Representing a time interval.
Further, in the step S2, the drill-up control specifically includes: and monitoring the state of the drill rod through image processing and feature recognition, and extracting the drill rod.
Further, in the step S2, excluding the stuck control specifically includes the following substeps:
s211, monitoring the motion state of a drill bit and drilling parameters, wherein the drilling parameters comprise feed speed, drill bit rotating speed, axial force, torque, pumping pressure, slurry flow and formation drillability information;
s212, extracting features, analyzing the features through a random forest algorithm and predicting the stuck risk.
Further, the step S212 specifically further includes the following sub-steps:
s2121, constructing a model through decision trees, and training each tree by using a randomly selected feature subset;
s2122, training the decision tree by using information gain as a splitting standard for each tree, wherein the information gain calculation flow is as follows:
wherein the saidRepresenting the gain of the information, said->Representing an measure of the degree of non-purity, said +.>Representing a parent node, said->Indicate->A dataset of individual child nodes, said +.>Indicate->The number of samples of a child node, said +.>Representing the number of samples of the parent node;
s2123, each tree gives a prediction result, and the final output of the random forest model is the average value or a plurality of tickets of all decision tree outputs.
Further, after the drilling control, the method further includes step S204: the realization control module of the external control terminal pops up a prompt to inform an operator to execute the coring operation. Specifically, in automatic drilling systems, a "coring" window prompt or operator interface is provided to inform an operator that a predetermined coring depth or condition has been reached and that a coring operation is desired. The control terminal automatically controls the coring tool to a specified depth and then cuts and extracts core samples from the formation.
An apparatus for employing automation control in a drilling operation, comprising:
the external control terminal is used for starting and stopping drilling control, reaming/reaming control and drill sticking removal control and displaying control data;
the internal control system is used for outputting corresponding data results to the external control terminal according to the acquired parameter data,
wherein the external control terminal includes:
the drilling control on-off module is used for on-off the drilling control;
the drill-down control opening and closing module is used for opening and closing drill-down control;
the drill starting control start-stop module is used for starting and stopping the drill starting control;
the reaming/reaming control opening and closing module is used for opening and closing reaming/reaming control;
the drill clamping removal control opening and closing module is used for opening and closing the drill clamping removal;
the display control module is used for displaying the current drilling operation data;
the internal control system includes:
the drilling control unit is used for optimizing drilling control in a drilling environment through the DQN model;
the drill-down control unit is used for automatically detecting and adjusting the angle and the position of the drill rod;
the tripping control unit is used for monitoring the state of the drill rod through image processing and feature recognition;
and the drill sticking elimination control unit is used for analyzing the characteristics through a random forest algorithm and predicting the drill sticking risk.
Further, the drilling control unit includes:
a state space and action space defining subunit for defining a state space and an action space, wherein the state space represents an input of the DQN model, the state space at least including a bit position, a bit rotational speed, an axial force, a feed speed, a formation hardness, and bit wear, the action space at least including rotational speed control, axial force control, and bit replacement;
a reward function definition subunit for evaluating the effect of each action by defining a reward function;
a model training subunit for estimating the difference between the predicted Q value and the target Q value using the mean square error, and for each training step updating the network using the following loss function:
；
wherein the saidRepresenting a loss function, said->Representing neural network parameters, said->Representing the averaging or expectation of training data, said +.>Indicating immediate return and status +.>Take action->Immediate return of time, said +.>Representing a discount factor, said->Has a value between 0 and 1, said +.>Is indicated in new state->All possible actions->Maximum value of Q value of said +.>Parameters representing the target network, said +.>Representing parameters of the current neural network, said +.>Representing the current state space, said +.>Representing the current state +.>Action taken downwards, said ++>Representing execution of an action->The next state after that, the ∈>Representing a new state->A downward motion;
s203, adjusting drilling parameters in real time through the trained model, and selecting the optimal action as output.
Further, the drill sticking elimination control unit includes:
the parameter state acquisition subunit is used for monitoring the motion state of the drill bit and drilling parameters, wherein the drilling parameters comprise feed speed, drill bit rotating speed, axial force, torque, pump pressure and formation drillability information;
the model construction subunit is used for constructing a model through decision trees and respectively training each tree by using the randomly selected feature subsets;
the model training subunit is used for training the decision tree by using the information gain as a splitting standard for each tree, wherein the calculation flow of the information gain is as follows:
；
wherein the saidRepresenting the gain of the information, said->Representing an measure of the degree of non-purity, said +.>Representing a parent node, said->Indicate->A dataset of individual child nodes, said +.>Indicate->The number of samples of a child node, said +.>Representing the number of samples of the parent node;
and the prediction output subunit is used for giving a prediction result to each tree, and outputting the average value or a plurality of tickets of all decision tree outputs by the final output of the random forest model.
Further, it should be noted that, for the external control terminal disclosed in this embodiment, the control manner includes, but is not limited to, a joystick, a control button, and a wireless remote controller, as a preferred implementation manner, 3 independent engines are connected to the external control terminal in this embodiment, and conventionally, the external control terminal is started/stopped 3 times by manual operation, and the terminal disclosed in this embodiment can start/stop 3 engines only by one key, and can synchronously regulate the throttle of 3 engines at the same time.
Furthermore, for the automatic drilling disclosed in this embodiment, the driller controls the operating rod in the traditional manner, and adjusts parameters such as the rotation speed, the drilling pressure, the pump quantity and the like required in the drilling process in real time according to the on-site working condition, the drilling control start-stop module can perform the drilling function only by one key, the driller does not need to adjust the parameters midway, the system can automatically identify the rock stratum, and a series of parameters in the drilling process can be automatically adjusted.
Further, for the one-key tripping/tripping disclosed in this embodiment, the conventional manner is to manually operate the tripping/tripping by a driller, so that the simultaneous tripping of threads at two ends of a drill rod cannot be performed at one time easily in the tripping process, an auxiliary person is required to perform the secondary tripping operation, the tripping/tripping control on-off module can realize that only one key is required in the tripping and tripping processes to finish the operations of adding the drill rod and detaching the drill rod, and the auxiliary person is not required to perform the secondary tripping operation in the detaching of the drill rod.
Further, for the display control module disclosed in this embodiment, the conventional drilling machine only displays various parameters through the mechanical instrument, and the remote real-time monitoring platform of the display control module can collect and display various parameters of the equipment.
Preferably, the conventional method is to record by manpower, the accuracy of the data is not high, the real-time performance is crossed, and the data storage function of the embodiment has the functions of local and remote transmission, and the data is accurate and timely.
Further, as a preferred embodiment, the external control terminal further includes a self-checking module and a manual module; the self-checking module system comprises hardware diagnosis, software integrity check, communication link test and the like, the self-checking is automatically executed when the system is started, and the self-checking module system can be triggered manually at regular intervals or according to the needs, and can prevent/avoid accidents in holes, such as drilling sticking, drilling burying, drilling burning and the like, by detecting the change of parameters. The manual module allows an operator to manually control drilling operations under certain conditions, such as system failure, complex geological conditions, or certain job requirements, and in a manual mode, the operator can directly adjust parameters such as rotational speed, axial force, pump speed, etc. of the drill bit, bypassing automatic control.
Further, as a preferred implementation manner of the foregoing embodiment, as shown in fig. 2, a specific embodiment of an external control terminal adopting automatic control in drilling operation is provided, where, as shown in the drawing, the specific embodiment includes a scram switch 1, a start/stop switch 2, a wire connection port 3, a hydraulic system 4, a protection cover 5, a housing 6, a pressure gauge 7, a drilling control button 8, a weight-on-bit return button 9, an oil cylinder push rod 10, a weight-on-bit adjusting knob 11, a winch push rod 12, a mud pump control knob 13, a power head push rod 14, an accelerator push rod 15, a gripper operating rod 16 and a display table 17, where, the housing 6 is a rectangular housing, a display table 17 is installed on one side of the top of the housing 6, pressure gauges 7, drilling control buttons 8, weight-on-bit return buttons 9, scram switches 1, start/stop switches 2 and wire connection ports 3 are respectively embedded on two sides of the display table, the protection cover 5 is installed on the top of the display table, an oil cylinder 10, a weight-on-bit adjusting knob 11, a winch push rod 12, a mud pump control knob 13, a power head push rod 14, and an accelerator push rod 15 are connected to one side of the hydraulic system 4, and the hydraulic system is connected to one side of the housing 4.
Further, as a preferred implementation of the present example, a terminal device for use in drilling operations with automation control is proposed, as in fig. 3, the terminal device 200 comprising at least one memory 210, at least one processor 220 and a bus 230 connecting the different platform systems.
Memory 210 may include readable media in the form of volatile memory, such as Random Access Memory (RAM) 211 and/or cache memory 212, and may further include Read Only Memory (ROM) 213.
The memory 210 further stores a computer program, which may be executed by the processor 220, so that the processor 220 executes a method for performing automatic control in any one of the drilling operations in the embodiments of the present application, and a specific implementation manner of the method is consistent with the implementation manner and the achieved technical effects described in the embodiments, and some contents are not repeated. Memory 210 may also include a program/utility 214 having a set (at least one) of program modules 215 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.
Accordingly, the processor 220 may execute the computer programs described above, as well as the program/utility 214.
Bus 230 may be a local bus representing one or more of several types of bus structures including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or using any of a variety of bus architectures.
Terminal device 200 can also communicate with one or more external devices 240, such as a keyboard, pointing device, bluetooth device, etc., as well as one or more devices capable of interacting with the terminal device 200, and/or with any device (e.g., router, modem, etc.) that enables the terminal device 200 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 250. Also, terminal device 200 can communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet, through network adapter 260. Network adapter 260 may communicate with other modules of terminal device 200 via bus 230. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with terminal device 200, including, but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, data backup storage platforms, and the like.
Further, as a preferred implementation of the present example, a computer readable storage medium employing automated control in drilling operations is provided, the computer readable storage medium having instructions stored thereon which, when executed by a processor, implement an automated control method in any of the drilling operations described above. The specific implementation manner of the method is consistent with the implementation manner and the achieved technical effect described in the above embodiments, and some of the details are not repeated.
Fig. 4 shows a program product 300 provided by the present embodiment for implementing the above method, which may employ a portable compact disc read-only memory (CD-ROM) and comprise program code, and which may be run on a terminal device, such as a personal computer. However, the program product 300 of the present invention is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. Program product 300 may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable storage medium may also be any readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing. Program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).
The foregoing has shown and described the basic principles and main features of the present invention and the advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
The foregoing is merely a preferred embodiment of the invention, and it is to be understood that the invention is not limited to the form disclosed herein but is not to be construed as excluding other embodiments, but is capable of numerous other combinations, modifications and environments and is capable of modifications within the scope of the inventive concept, either as taught or as a matter of routine skill or knowledge in the relevant art. And that modifications and variations which do not depart from the spirit and scope of the invention are intended to be within the scope of the appended claims.
Claims (9)
1. A method for employing automated control in a drilling operation, comprising the steps of:
s1, data acquisition;
s2, drilling control, drill-down control, drill-up control, reaming/reaming control and drill sticking removal control are respectively carried out through a system terminal according to the acquired data;
the drilling control specifically comprises the following substeps:
s201, defining a state space and an action space, wherein the state space represents the input of the DQN model, the state space at least comprises a bit position, a bit rotating speed, an axial force, a feeding speed, a slurry flow, formation hardness and bit abrasion, and the action space at least comprises rotating speed control, axial force control and bit replacement;
s202, evaluating the effect of each action by defining a return function; using the mean square error to evaluate the difference between the predicted Q value and the target Q value, for each training step, the network is updated using the following loss function:
；
wherein the saidRepresenting a loss function, said->Representing neural network parameters, said->Representing the averaging or expectation of training data, said +.>Indicating immediate return and status +.>Take action->Immediate return of time, said +.>Representing a discount factor, said->Has a value between 0 and 1, said +.>Is indicated in new state->All possible actions->Maximum value of Q value of said +.>Parameters representing the target network, said +.>Representing parameters of the current neural network, said +.>Representing the current state space, said +.>Representing the current state +.>Action taken downwards, said ++>Representing execution of an action->The next state after that, the ∈>Representing a new state->A downward motion;
s203, adjusting drilling parameters in real time through the trained model, and selecting the optimal action as output.
2. The method for automatically controlling drilling operation according to claim 1, wherein in S2, the drill-down control is specifically: the drilling tool is sent to a preset depth through closed-loop control, and the implementation process is as follows:
；
wherein the saidRepresenting a new depth position of the drilling tool, said +.>Indicating the current drilling toolDepth position of said->Represents the feed-down speed, said +.>Representing a time interval.
3. The method for automatically controlling drilling operation according to claim 1, wherein in S2, the drill-up control is specifically: and monitoring the state of the drill rod through image processing and feature recognition, and extracting the drill rod.
4. A method for automated control in drilling operations according to claim 1, wherein the excluding stuck control in S2 comprises the sub-steps of:
s211, monitoring the motion state of a drill bit and drilling parameters, wherein the drilling parameters comprise feed speed, drill bit rotating speed, axial force, torque, pump pressure, slurry flow and formation drillability information;
s212, extracting features, analyzing the features through a random forest algorithm and predicting the stuck risk.
5. The method for using automated control in drilling operations according to claim 4, wherein S212 further comprises the sub-steps of:
s2121, constructing a model through decision trees, and training each tree by using a randomly selected feature subset;
s2122, training the decision tree by using information gain as a splitting standard for each tree, wherein the information gain calculation flow is as follows:
；
wherein the saidRepresenting the gain of the information, said->Representing an measure of the degree of non-purity, said +.>Representing a parent node, saidIndicate->A dataset of individual child nodes, said +.>Indicate->The number of samples of a child node, said +.>Representing the number of samples of the parent node;
s2123, each tree gives a prediction result, and the final output of the random forest model is the average value or a plurality of tickets of all decision tree outputs.
6. A method of automated control in a drilling operation as recited in claim 1, further comprising, after drilling control, S204: the realization control module of the external control terminal pops up a prompt to inform an operator to execute the coring operation.
7. An apparatus for automated control in drilling operations, the apparatus being based on a method for automated control in drilling operations according to any one of claims 1-6, comprising:
the external control terminal is used for starting and stopping drilling control, reaming/reaming control and drill sticking removal control and displaying control data;
the internal control system is used for outputting corresponding data results to the external control terminal according to the acquired parameter data,
wherein the external control terminal includes:
the drilling control on-off module is used for on-off the drilling control;
the drill-down control opening and closing module is used for opening and closing drill-down control;
the drill starting control start-stop module is used for starting and stopping the drill starting control;
the reaming/reaming control opening and closing module is used for opening and closing reaming/reaming control;
the drill clamping removal control opening and closing module is used for opening and closing the drill clamping removal;
the display control module is used for displaying the current drilling operation data;
the internal control system includes:
the drilling control unit is used for optimizing drilling control in a drilling environment through the DQN model;
the drill-down control unit is used for automatically detecting and adjusting the angle and the position of the drill rod;
the tripping control unit is used for monitoring the state of the drill rod through image processing and feature recognition;
and the drill sticking elimination control unit is used for analyzing the characteristics through a random forest algorithm and predicting the drill sticking risk.
8. An apparatus for employing automated control in a drilling operation as recited in claim 7, wherein said drilling control unit comprises:
a state space and action space defining subunit for defining a state space and an action space, wherein the state space represents an input of the DQN model, the state space at least including a bit position, a bit rotational speed, an axial force, a feed speed, a formation hardness, and bit wear, the action space at least including rotational speed control, axial force control, and bit replacement;
a reward function definition subunit for evaluating the effect of each action by defining a reward function;
a model training subunit for estimating the difference between the predicted Q value and the target Q value using the mean square error, and for each training step updating the network using the following loss function:
；
wherein the saidRepresenting a loss function, said->Representing neural network parameters, said->Representing the averaging or expectation of training data, said +.>Indicating immediate return and status +.>Take action->Immediate return of time, said +.>Representing a discount factor, said->Has a value between 0 and 1, said +.>Is indicated in new state->All possible actions->Maximum value of Q value of said +.>Parameters representing the target network, said +.>Representing parameters of the current neural network, said +.>Representing the current state space, said +.>Representing the current state +.>Action taken downwards, said ++>Representing execution of an action->The next state after that, the ∈>Representing a new state->A downward motion;
and the model output subunit is used for adjusting drilling parameters in real time through the trained model and selecting the optimal action as output.
9. An apparatus for automated control in a drilling operation as recited in claim 7, wherein said drill sticking rejection control unit comprises:
the parameter state acquisition subunit is used for monitoring the motion state of the drill bit and drilling parameters, wherein the drilling parameters comprise feed speed, drill bit rotating speed, axial force, torque, pump pressure and formation drillability information;
the model construction subunit is used for constructing a model through decision trees and respectively training each tree by using the randomly selected feature subsets;
the model training subunit is used for training the decision tree by using the information gain as a splitting standard for each tree, wherein the calculation flow of the information gain is as follows:
；
wherein the saidRepresenting the gain of the information, said->Representing an measure of the degree of non-purity, said +.>Representing a parent node, saidIndicate->A dataset of individual child nodes, said +.>Indicate->The number of samples of a child node, said +.>Representing the number of samples of the parent node;
and the prediction output subunit is used for giving a prediction result to each tree, and outputting the average value or a plurality of tickets of all decision tree outputs by the final output of the random forest model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410178485.7A CN117722170A (en) | 2024-02-09 | 2024-02-09 | Method and device for automatically controlling drilling operation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410178485.7A CN117722170A (en) | 2024-02-09 | 2024-02-09 | Method and device for automatically controlling drilling operation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117722170A true CN117722170A (en) | 2024-03-19 |
Family
ID=90209241
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410178485.7A Pending CN117722170A (en) | 2024-02-09 | 2024-02-09 | Method and device for automatically controlling drilling operation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117722170A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070056772A1 (en) * | 2003-12-23 | 2007-03-15 | Koederitz William L | Autoreaming systems and methods |
| CN109594967A (en) * | 2018-11-27 | 2019-04-09 | 南通世盾信息技术有限公司 | A kind of lock of tool drilling detection method for early warning based on well logging big data |
| CN111456666A (en) * | 2020-06-01 | 2020-07-28 | 洲际海峡能源科技有限公司 | Automatic control method and system for intelligent scratching of soft pump pressure |
| CN112539052A (en) * | 2020-12-04 | 2021-03-23 | 北京探矿工程研究所 | Control device, method, medium and equipment for optimizing dropping speed of drilling tool |
| US20220074275A1 (en) * | 2020-09-04 | 2022-03-10 | Sichuan Honghua Petroleum Equipment Co., Ltd. | Methods for tripping a drilling rig or a workover rig |
| CN115628009A (en) * | 2022-10-13 | 2023-01-20 | 南京工业大学 | Intelligent borehole trajectory control method based on reinforcement learning |
| CN116761927A (en) * | 2020-11-06 | 2023-09-15 | 吉奥奎斯特系统公司 | Intelligent guided well evaluation |
-
2024
- 2024-02-09 CN CN202410178485.7A patent/CN117722170A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070056772A1 (en) * | 2003-12-23 | 2007-03-15 | Koederitz William L | Autoreaming systems and methods |
| CN109594967A (en) * | 2018-11-27 | 2019-04-09 | 南通世盾信息技术有限公司 | A kind of lock of tool drilling detection method for early warning based on well logging big data |
| CN111456666A (en) * | 2020-06-01 | 2020-07-28 | 洲际海峡能源科技有限公司 | Automatic control method and system for intelligent scratching of soft pump pressure |
| US20220074275A1 (en) * | 2020-09-04 | 2022-03-10 | Sichuan Honghua Petroleum Equipment Co., Ltd. | Methods for tripping a drilling rig or a workover rig |
| CN116761927A (en) * | 2020-11-06 | 2023-09-15 | 吉奥奎斯特系统公司 | Intelligent guided well evaluation |
| CN112539052A (en) * | 2020-12-04 | 2021-03-23 | 北京探矿工程研究所 | Control device, method, medium and equipment for optimizing dropping speed of drilling tool |
| CN115628009A (en) * | 2022-10-13 | 2023-01-20 | 南京工业大学 | Intelligent borehole trajectory control method based on reinforcement learning |
Non-Patent Citations (1)
| Title |
|---|
| 刘建明等: "一种基于PCA-RF 的卡钻预测方法", 北京信息科技大学学报, vol. 36, no. 1, 22 February 2021 (2021-02-22), pages 18 - 22 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110148285B (en) | Intelligent oil well parameter early warning system based on big data technology and early warning method thereof | |
| RU2510971C2 (en) | In situ real-time communication via internet with well dispatcher for permanent well optimisation | |
| CN102395754B (en) | A method and system for monitoring a drilling operation | |
| US9280517B2 (en) | System and method for failure detection for artificial lift systems | |
| CN109064037B (en) | Foundation pit construction risk management and control method, system and equipment | |
| WO2018029454A1 (en) | Method and system for analysing drilling data | |
| CN111622735B (en) | Environment-friendly drilling machine automatic control and monitoring system and method based on Internet of things | |
| CN114402267A (en) | Rod pump fault prediction based on well site machine learning | |
| WO2015168708A2 (en) | System and console for monitoring and managing well site operations | |
| NO322338B1 (en) | Procedure for monitoring drilling parameters | |
| CN113931258B (en) | Self-diagnosis method and non-negative pressure-superposed water supply equipment | |
| US20210348490A1 (en) | Oilfield system | |
| US11475316B2 (en) | Intelligent drilling rig control system commissioning, diagnostics and maintenance | |
| KR102174722B1 (en) | Instrumentation control system that predicts failure by machine learning the noise received from the on-site machinery | |
| US20190345810A1 (en) | Intelligent monitoring for drilling process automation | |
| WO2021053545A1 (en) | Machine learning control for automatic kick detection and blowout prevention | |
| CN115841247A (en) | Digital drilling risk monitoring method and device | |
| EP3368739B1 (en) | Automation of energy industry processes using stored standard best practices procedures | |
| CN117722170A (en) | Method and device for automatically controlling drilling operation | |
| CN110806859A (en) | Modular drilling data monitoring and design system based on machine learning | |
| US20150014056A1 (en) | Dynamic response apparatus and methods triggered by conditions | |
| EP3354843B1 (en) | Systems and methods for drilling productivity analysis | |
| WO2020152029A1 (en) | Managing an installed base of artificial intelligence modules | |
| Devi et al. | A Hybrid Structural Building Data Mining System Based On the Data Tracking Through Devices | |
| Zhu | A Data-Driven Decision Model: A Case Study on Drawworks in Offshore Oil & Gas Industry |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |