CN118167275B - Method and system for stably rotating mechanical arm of underground coal mine drilling machine - Google Patents
Method and system for stably rotating mechanical arm of underground coal mine drilling machine Download PDFInfo
- Publication number
- CN118167275B CN118167275B CN202410605503.5A CN202410605503A CN118167275B CN 118167275 B CN118167275 B CN 118167275B CN 202410605503 A CN202410605503 A CN 202410605503A CN 118167275 B CN118167275 B CN 118167275B
- Authority
- CN
- China
- Prior art keywords
- drilling
- constraint condition
- speed
- control algorithm
- deep
- 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.)
- Active
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1628—Programme controls characterised by the control loop
- B25J9/163—Programme controls characterised by the control loop learning, adaptive, model based, rule based expert control
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1679—Programme controls characterised by the tasks executed
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B44/00—Automatic control systems specially adapted for drilling operations, i.e. self-operating systems which function to carry out or modify a drilling operation without intervention of a human operator, e.g. computer-controlled drilling systems; Systems specially adapted for monitoring a plurality of drilling variables or conditions
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Geology (AREA)
- Mining & Mineral Resources (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Environmental & Geological Engineering (AREA)
- Fluid Mechanics (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Earth Drilling (AREA)
Abstract
The invention relates to the technical field of speed control, and discloses a steady rotation method and a steady rotation system of a mechanical arm of an underground coal mine drilling machine.
Description
Technical Field
The invention relates to the technical field of speed control, in particular to a method and a system for stably rotating a mechanical arm of an underground coal mine drilling machine.
Background
The underground coal mine drilling machine is used as key equipment in the coal mine exploitation process, the drilling machine manipulator is connected with the drill rod and the drill bit, is a driving part for driving the drill rod and the drill bit to stably rotate, and the rotation stability of the underground coal mine drilling machine is important for guaranteeing the drilling quality and improving the drilling efficiency, and plays a critical role in the drilling technology in the coal mine resource exploration field. In the actual operation process, the underground stratum structure is complex, the coal seam is positioned between adjacent rock layers, multiple rock layers are required to be continuously drilled in order to drill coal mines with different depths, and as the differences of the rock layers with different depths in the aspects of type, thickness, hardness and the like are not known, the mechanical arm drives the drill rod to drill at a certain speed, so that the drill rod cannot effectively generate different resistances to the drill rod on different strata, the drill rod cannot be further adapted to stratum changes to be damaged, the drilling efficiency is reduced, and particularly, in softer strata, the drill bit can be worn or damaged too early due to high-speed drilling; in harder formations, low drilling rates may result in poor drilling efficiency and even stuck drill; the different stratum has different resistances to the drill bit, so that the required drilling power is different, if the drill bit is drilled at a fixed speed all the time, the energy consumption is unreasonable, namely, the energy is wasted in the easy-to-drill stratum, and the drilling speed is possibly influenced by insufficient power in the difficult-to-drill stratum.
Disclosure of Invention
In order to solve the technical problems, the invention provides a method and a system for stably rotating a mechanical arm of an underground coal mine drilling machine, so as to realize different drilling speeds according to the structural characteristics of stratum with different depths and achieve the purpose of stable drilling.
The invention provides a method for stably rotating a mechanical arm of an underground coal mine drilling machine, which comprises the following steps:
Step S1, constructing a support vector regression model, and embedding a segmentation control algorithm and a feedback control algorithm, wherein the segmentation control algorithm is used for controlling the speed of shallow drilling, and the feedback control algorithm is used for controlling the speed of deep drilling;
step S2, a first constraint condition is set for the segmentation control algorithm, and a second constraint condition is set for the feedback control algorithm;
The first constraint condition is: ; the second constraint condition is: ；
Wherein, Representing the lower speed bound for the segment control algorithm to control shallow boreholes,Representing the upper speed bound for the control of shallow boreholes by the segment control algorithm,Representing the lower speed bound for the feedback control algorithm to control deep boreholes,Representing the upper speed limit of the feedback control algorithm for controlling the deep drilling;
step S3, a first basic loss function is set for the segmentation control algorithm, and a second basic loss function is set for the feedback control algorithm;
step S4, respectively defining a penalty function of the first constraint condition and a penalty function of the second constraint condition according to the first constraint condition and the second constraint condition;
step S5, defining a loss function according to the first basic loss function, the penalty function of the first constraint condition, the second basic loss function and the penalty function of the second constraint condition;
Step S6, minimizing a loss function to minimize an error between the actual drilling speed and the predicted drilling speed so as to obtain a trained support vector regression model;
and S7, inputting real-time data to be drilled into a trained support vector regression model, and outputting drilling speed.
Further, the shallow drilling depth is 100m-500m, and the deep drilling depth is 500m-2000m.
Further, in the step S4, a penalty function of the first constraint condition and a penalty function of the second constraint condition are defined according to the first constraint condition and the second constraint condition, respectively, and specifically include the following steps:
step 41, if the predicted drilling rate exceeds the upper speed limit of the first constraint condition and/or the predicted drilling rate exceeds the upper speed limit of the second constraint condition, setting an upper limit exceeding penalty formula ；
Step S42, if the predicted drilling speed is lower than the lower speed limit of the first constraint condition and/or the predicted drilling speed is lower than the lower speed limit of the second constraint condition, setting a lower-limit penalty formula；
Step S43, obtaining punishment functions of the first constraint condition and/or the second constraint condition according to the upper-bound punishment formula and the lower-bound punishment formula+。
Further, the above upper bound penalty formula:
；
In the method, in the process of the invention, Representing an out-of-bounds penalty formula,Representing the i-th predicted value of the current value,Representing an upper speed limit and n representing the number of predicted values.
Further, the lower bound penalty formula is:
；
In the method, in the process of the invention, Representing a lower-than-lower-bound penalty formula,Representing the i-th predicted value of the current value,Representing a lower speed limit and n representing the number of predicted values.
Further, the loss function is:
；
In the method, in the process of the invention, Representing a loss function and,Representing a first basis loss function of the first model,Representing a second basis loss function, which is a function of the second basis,Representing an out-of-bounds penalty formula,Representing a lower-than-lower-bound penalty formula,AndRepresenting model weights.
Further, the step S1 of the segment control algorithm is configured to control a shallow drilling speed, and specifically includes: dividing shallow drilling into three stages of a coal seam approaching layer, a main coal seam and a coal seam underlying rock stratum according to the speed of the shallow drilling and the geological information of the shallow drilling, controlling the drilling speed of the coal seam approaching layer to be V 1 by a sectional control algorithm, setting the drilling speed of the main coal seam to be V 2 by the sectional control algorithm, and setting the drilling speed of the coal seam underlying rock stratum to be V 3,V2>V1>V3 by the sectional control algorithm;
The shallow drilling geological information is obtained through the shallow drilling, and the shallow drilling geological information comprises a shallow drilling geological type, a shallow drilling geological hardness and a shallow drilling geological thickness.
Further, the feedback control algorithm in step S1 is configured to control a deep drilling speed, and specifically includes: dividing the deep drilling into three stages of a coal seam approaching layer to a shallow coal seam, a main coal seam to a deep coal seam, a coal seam underlying rock layer and a final hole layer according to the speed of the deep drilling and the geological information of the deep drilling; the feedback control algorithm controls the drilling speed from the coal seam approach layer to the shallow coal to be V 4, controls the drilling speed from the main coal seam to the deep coal to be V 5, and controls the drilling speed from the coal seam underlying stratum to the end hole layer to be V 6,V5>V4>V6.
Further, the deep borehole geological information is obtained through the deep borehole, and the deep borehole geological information comprises a deep borehole geological type, a deep borehole geological hardness, a deep borehole geological thickness, a deep borehole geological pressure, and a deep borehole geological structure.
The invention also discloses a steady rotation system of the underground coal mine drilling machine manipulator, which is used for executing the steady rotation method of the underground coal mine drilling machine manipulator, and comprises the following modules:
Support vector regression model: the method comprises the steps of supporting a vector regression model, embedding a segment control algorithm and a feedback control algorithm, wherein the segment control algorithm is used for controlling the speed of shallow drilling, and the feedback control algorithm is used for controlling the speed of deep drilling;
Constraint condition setting module: the method comprises the steps of connecting with a support vector regression model, setting a first constraint condition for a segmentation control algorithm and setting a second constraint condition for a feedback control algorithm;
The basic loss function setting module: the constraint condition setting module is connected with the constraint condition setting module and is used for setting a first basic loss function for the segmentation control algorithm and a second basic loss function for the feedback control algorithm;
Penalty function setting module: the constraint condition setting module is connected with the basic loss function setting module and used for respectively defining a penalty function of the first constraint condition and a penalty function of the second constraint condition according to the first constraint condition and the second constraint condition;
the loss function definition module: the penalty function setting module is connected with the basic penalty function setting module and is used for defining a penalty function according to the first basic penalty function, the penalty function of the first constraint condition, the second basic penalty function and the penalty function of the second constraint condition;
Training module: the system comprises a loss function definition module, a support vector regression module and a control module, wherein the loss function definition module is connected with the support vector regression module and is used for minimizing a loss function so that the error between the actual drilling speed and the predicted drilling speed is minimized to obtain a trained support vector regression model;
and a result output module: and the training module is connected with the training module, inputs real-time data to be drilled into the trained support vector regression model, and outputs the drilling speed.
The invention has the following beneficial effects:
1. According to the invention, the drilling depth is divided into shallow drilling and deep drilling, the drilling speed of the shallow drilling is controlled by the segmentation control algorithm, the drilling speed of the deep drilling is controlled by the feedback control algorithm, and different drilling speeds are set according to the structural characteristics of stratum with different depths, so that the purpose of stable drilling is achieved, the drilling machine can adapt to stratum changes, the probability of damage of a drill rod in the drilling process is reduced, the energy waste is reduced, and the drilling speed is improved.
2. The invention sets constraint conditions for the speed ranges to be controlled by the sectional control algorithm and the feedback control algorithm respectively, sets a punishment function based on the constraint conditions, applies the punishment function to the loss function of the model, adjusts the error to be minimum, predicts the obtained speed value within the constraint conditions, so that the model can predict the drilling speed more accurately, and the model predicts drilling holes with different depths to obtain a predicted result, namely the drilling speed with which the current drilling depth can stably rotate.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for smooth rotation of a manipulator of an underground coal mine drilling machine provided by the embodiment 1 of the invention;
fig. 2 is a schematic structural diagram of a steady rotation system of a mechanical arm of an underground coal mine drilling machine provided in embodiment 2 of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the invention, are within the scope of the invention.
Example 1: fig. 1 is a flowchart of a method for smooth rotation of a manipulator of an underground coal mine drilling machine provided in embodiment 1 of the present invention. The method specifically comprises the following steps:
Step S1, constructing a support vector regression model, and embedding a segmentation control algorithm and a feedback control algorithm, wherein the segmentation control algorithm is used for controlling the speed of shallow drilling and specifically comprises the following steps: dividing shallow drilling into three stages of a coal seam approaching layer, a main coal seam and a coal seam underlying rock stratum according to the speed of the shallow drilling and the geological information of the shallow drilling, controlling the drilling speed of the coal seam approaching layer to be V 1 by a segmentation control algorithm, setting the drilling speed of the main coal seam to be V 2 by the segmentation control algorithm, setting the drilling speed of the coal seam underlying rock stratum to be V 3 by the segmentation control algorithm, and controlling the drilling speed of the coal seam approaching layer to be V 1 to be 1.0-1.8 m/min in order to ensure stable rotation of a drill rod and maximally reduce abrasion because the coal seam approaching layer gradually approaches the coal seam and the stratum contains more rock fragments or hard interlayers; most coal mines are stored in a main coal seam, when a drill rod enters the main coal seam, the coal quality of the main coal seam is uniform, gangue is contained in the main coal seam, the drilling speed is ensured to be stable when drilling in the coal seam, coal sample breakage caused by too high speed is avoided, and the drilling speed V 2 of the main coal seam is controlled to be 1.3-2.0 m/min; the rock layer is arranged on the lower side of the main coal seam, the hardness of the rock layer is increased compared with that of the coal seam, the drilling difficulty is high, and in order to ensure the drilling quality of a drill rod, the drilling speed V 3 of the rock layer under the coal seam is controlled to be 0.6-1.5 m/min; therefore, the present embodiment arranges the drilling rates of the shallow drill holes from large to small: v 2>V1>V3;
The feedback control algorithm is used for controlling the speed of deep drilling and specifically comprises the following steps: dividing the deep drilling into three stages of a coal seam approaching layer to a shallow coal seam, a main coal seam to a deep coal seam, a coal seam underlying rock layer and a final hole layer according to the speed of the deep drilling and the geological information of the deep drilling; the feedback control algorithm controls the drilling speed of the coal seam from the near layer to the shallow layer to V 4, the feedback control algorithm controls the drilling speed of the main coal seam to the deep layer to V 5, the feedback control algorithm controls the drilling speed of the lower strata of the coal seam to the end hole layer to V 6, the coal seam from the near layer to the shallow layer gradually approaches the coal seam and starts to enter the shallow layer part of the coal seam, rock fragments and a hard interlayer exist in the stratum, in order to ensure stable rotation of a drill rod, the drilling speed is moderate, the coal seam from the near layer to the shallow layer in the deep drilling is similar to the coal seam from the near layer in the shallow layer drilling, and the drilling speed of the coal seam from the near layer to the shallow layer coal is controlled to be 0.8-1.5 m/min compared with the drilling speed of the near layer of the shallow layer due to the fact that the depth of the deep uncontrollable factors are more; the stratum structure from the main coal seam to the deep coal seam is similar to that of the main coal seam in the shallow drilling hole, coal quality is uniform, and gangue is contained in the coal seam, but geological conditions for deep drilling holes are complex, in the embodiment, the drilling speed from the main coal seam to the deep coal seam is lower than that of the main coal seam in the shallow drilling hole, and V 5 is controlled to be 1.0-1.8 m/min; the coal bed is placed down the rock layer and is close to the termination depth of drilling in the coal bed downside of the terminal hole layer, the hardness increases gradually, the drilling degree of difficulty is big, when carrying out rock layer drilling or exploitation operation in the coal mining process, misoperation leads to the release of toxic gas, and is harmful to human health, perhaps even fatal, the drilling rate at this stage should slow down, this embodiment will control V6 to 0.5~0.8m/min, consequently, this embodiment will deep drilling's drilling rate go on from big to little range: v 5>V4>V6;
the shallow drilling and the deep drilling are divided according to the drilling depth of the drilling machine according to the drilling speed of the drilling machine, and the shallow drilling and the deep drilling are further divided;
Specifically, firstly, the drilling depth and the drilling speed of mechanical hand drilling are obtained, the drilling depth and the drilling speed of different stratum structures in the past operation record are obtained from a control system of a drilling machine, and raw data are collected by a sensor or measuring equipment, so that the obtained data have the problems of noise, error or inconsistent formats, and the like, therefore, data preprocessing and analysis are required to be carried out to extract useful information, data cleaning and data conversion operations are required to be carried out on the drilling depth data, and the aim is to remove invalid data such as abnormal values, repeated data and the like, and convert analog signals into digital signals; time synchronization is needed for drilling speed data, matching of the drilling speed and a corresponding time stamp is ensured, smoothing processing is carried out on the speed data so as to reduce noise and fluctuation, speed calculation is carried out finally, and the drilling speed is calculated according to the acquired drilling depth and time data; then, dividing the drilling depth according to the obtained drilling speed, wherein the drilling depth comprises shallow drilling and deep drilling; in terms of drilling depth, shallow drilling is drilling with the drilling depth of 100-500 m, so that the shallow drilling is used for shallow geological exploration to facilitate subsequent coal mine exploitation, while deep drilling is drilling with the drilling depth of 500-2000 m, and is used for deep mineral resource exploration to facilitate exploitation of deep coal mine; for the change of stratum structure, the change of the bottom layer of shallow drilling is relatively small, the geological condition is relatively simple, the stratum structure of deep drilling is complex, stratum structures with different hardness and different characteristics are included, the geological condition is relatively complex, the complexity is reflected on the types and the characteristics of stratum, the influence of extreme environments such as high temperature and high pressure on drilling equipment can be further realized, the risks of stratum collapse, drill bit blocking and the like are easy to occur by adopting high-speed drilling, and in sum, the stratum structure of shallow drilling and the stratum structure of deep drilling are obviously different in the aspects of drilling depth, stratum change, geological condition complexity, drilling risk and the like, the drilling depth is divided by the embodiment, and drilling speeds of drilling at different depths are adopted, so that the drilling rod can rotate stably by controlling the drilling process of a mechanical arm;
In addition, shallow drilling geological information and deep drilling geological information are obtained through drilling speeds, specifically, the shallow drilling geological information is obtained through the shallow drilling, and the shallow drilling geological information comprises shallow drilling geological types, shallow drilling geological hardness and shallow drilling geological thickness; the deep-hole geological information is obtained through the deep-hole, and the deep-hole geological information comprises a deep-hole geological type, deep-hole geological hardness, deep-hole geological thickness, deep-hole geological pressure and deep-hole geological structure.
Step S2, a first constraint condition is set for the segmentation control algorithm, and a second constraint condition is set for the feedback control algorithm;
The first constraint condition is: ; the second constraint condition is: ；
Wherein, Representing the lower speed bound for the segment control algorithm to control shallow boreholes,Representing the upper speed bound for the control of shallow boreholes by the segment control algorithm,Representing the lower speed bound for the feedback control algorithm to control deep boreholes,Representing the upper speed limit of the feedback control algorithm for controlling the deep drilling;
In this embodiment, constraint conditions are set for the segment control algorithm and the feedback control algorithm respectively, so that the model can more accurately predict the variation trend of the drilling speed, ensure that the predicted result accords with the actual situation, and different drilling depths may have different requirements on the drilling speed.
Step S3, a first basic loss function is set for the segmentation control algorithm, and a second basic loss function is set for the feedback control algorithm;
The design of the basic loss function is to quantify the difference between the predicted value and the actual value of the model, and the algorithm can continuously adjust the model parameters and optimize the model performance by minimizing the basic loss function, so that the predicted result is more similar to the actual condition; further, for the segment control algorithm, the inlet point and the outlet point are set in each stage and can be independently executed, and the first basic loss function is set to help ensure that each stage can be accurately controlled according to a preset target; the feedback control algorithm processes the error signal and sends the control signal, so that the system has better robustness, and the second basic loss function is arranged to help the feedback control algorithm to process the error signal more accurately, so that when the feedback control algorithm faces different stratum structures, the second basic loss function can improve the input corresponding speed and tracking precision.
Step S4, respectively defining a penalty function of the first constraint condition and a penalty function of the second constraint condition according to the first constraint condition and the second constraint condition;
step S41, if the predicted drilling speed exceeds the upper speed limit of the first constraint condition and/or the predicted drilling speed exceeds the upper speed limit of the second constraint condition, setting an upper limit exceeding penalty formula ；
；
In the method, in the process of the invention,Representing an out-of-bounds penalty formula,Representing the i-th predicted value of the current value,Represents the upper speed limit and n represents the maximum number of predicted values;
Step S42, if the predicted drilling speed is lower than the lower speed limit of the first constraint condition and/or the predicted drilling speed is lower than the lower speed limit of the second constraint condition, setting a lower-limit penalty formula ：
；
In the method, in the process of the invention,Representing a lower-than-lower-bound penalty formula,Representing the i-th predicted value of the current value,Represents a lower speed limit and n represents the number of predicted values;
Step S43, obtaining punishment functions of the first constraint condition and/or the second constraint condition according to the upper-bound punishment formula and the lower-bound punishment formula +。
Step S5, defining a loss function according to the first basic loss function, the penalty function of the first constraint condition, the second basic loss function and the penalty function of the second constraint condition;
The loss function is:
；
In the method, in the process of the invention, Representing a loss function and,Representing a first basis loss function of the first model,Representing a second basis loss function, which is a function of the second basis,Representing an out-of-bounds penalty formula,Representing a lower-than-lower-bound penalty formula,AndRepresenting model weights.
Step S6, minimizing a loss function to minimize an error between the actual drilling speed and the predicted drilling speed so as to obtain a trained support vector regression model;
According to the embodiment, the shallow drilling speed, the shallow drilling geological information, the deep drilling speed and the deep drilling geological information are used as training sets to train the support vector regression model, a trained support vector regression model is obtained, meanwhile, a loss function is minimized, and the error between the actual drilling speed and the predicted drilling speed is minimized, so that the trained support vector regression model is obtained;
In the embodiment, a penalty function based on a first constraint condition and/or a second constraint condition is added into a loss function, and when the predicted speed exceeds the upper speed limit and/or the lower speed limit in the constraint conditions, a certain penalty is given to the model, so that the model is close to the constraint conditions in the training process, predicted values violating the constraint are avoided as much as possible, if the predicted speed violates the constraint conditions, the total loss is increased due to the increase of the value of the penalty function, and therefore, in the optimizing process, the model can strive to find a group of parameters, so that the predicted speed is not only close to the actual speed as much as possible, but also meets the speed constraint conditions;
s7, inputting real-time data to be drilled into a trained support vector regression model, and outputting drilling speed;
and inputting the stratum structure to be drilled, the drilling geological information, the drilling geological hardness, the drilling geological thickness and the drilling geological pressure into a trained support vector regression model, and directly outputting the drilling speed of each stratum to be drilled.
Example 2: fig. 2 is a schematic structural diagram of a steady rotation system of a mechanical arm of an underground coal mine drilling machine provided in embodiment 2 of the present invention. The steady rotation system of the underground coal mine drilling machine manipulator is used for executing the steady rotation method of the underground coal mine drilling machine manipulator in the embodiment 1, and comprises the following modules:
Support vector regression model: the method comprises the steps of supporting a vector regression model, embedding a segment control algorithm and a feedback control algorithm, wherein the segment control algorithm is used for controlling the speed of shallow drilling, and the feedback control algorithm is used for controlling the speed of deep drilling;
Constraint condition setting module: the method comprises the steps of connecting with a support vector regression model, setting a first constraint condition for a segmentation control algorithm and setting a second constraint condition for a feedback control algorithm;
The basic loss function setting module: the constraint condition setting module is connected with the constraint condition setting module and is used for setting a first basic loss function for the segmentation control algorithm and a second basic loss function for the feedback control algorithm;
Penalty function setting module: the constraint condition setting module is connected with the basic loss function setting module and used for respectively defining a penalty function of the first constraint condition and a penalty function of the second constraint condition according to the first constraint condition and the second constraint condition;
the loss function definition module: the penalty function setting module is connected with the basic penalty function setting module and is used for defining a penalty function according to the first basic penalty function, the penalty function of the first constraint condition, the second basic penalty function and the penalty function of the second constraint condition;
Training module: the system comprises a loss function definition module, a support vector regression module and a control module, wherein the loss function definition module is connected with the support vector regression module and is used for minimizing a loss function so that the error between the actual drilling speed and the predicted drilling speed is minimized to obtain a trained support vector regression model;
and a result output module: and the training module is connected with the training module, inputs real-time data to be drilled into the trained support vector regression model, and outputs the drilling speed.
Example 3: the embodiment discloses an electronic device, which comprises one or more processors and a memory.
The processor may be a Central Processing Unit (CPU) or other form of processing unit having data processing and/or instruction execution capabilities, and may control other components in the electronic device to perform the desired functions.
The memory may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, random Access Memory (RAM) and/or cache memory (cache), and the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, and the like. One or more computer program instructions may be stored on the computer readable storage medium that can be executed by a processor to perform the method of smooth rotation of a downhole coal mine drilling rig manipulator and/or other desired functions of any of the embodiments of the application described above. Various content such as initial arguments, thresholds, etc. may also be stored in the computer readable storage medium.
In one example, the electronic device may further include: input devices and output devices, which are interconnected by a bus system and/or other forms of connection mechanisms (not shown). The input means may comprise, for example, a keyboard, a mouse, etc. The output device can output various information to the outside, including early warning prompt information, braking force and the like. The output means may include, for example, a display, speakers, a printer, and a communication network and remote output devices connected thereto, etc.
In addition, the electronic device may include any other suitable components depending on the particular application.
In addition to the methods and apparatus described above, embodiments of the application may also be a computer program product comprising computer program instructions which, when executed by a processor, cause the processor to perform the steps of a method of smooth rotation of a downhole coal mine drilling rig manipulator provided by any of the embodiments of the application.
The computer program product may write program code for performing operations of embodiments of the present application 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.
Furthermore, embodiments of the present application may also be a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, cause the processor to perform the steps of a method for smooth rotation of a downhole coal mine drilling machine manipulator provided by any of the embodiments of the present application.
The computer readable storage medium 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 may include, 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.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.
Claims (10)
1. The method for stably rotating the mechanical arm of the underground coal mine drilling machine is characterized by comprising the following steps of:
Step S1, constructing a support vector regression model, and embedding a segmentation control algorithm and a feedback control algorithm, wherein the segmentation control algorithm is used for controlling the speed of shallow drilling, and the feedback control algorithm is used for controlling the speed of deep drilling;
step S2, a first constraint condition is set for the segmentation control algorithm, and a second constraint condition is set for the feedback control algorithm;
The first constraint condition is: ; the second constraint condition is: ；
Wherein, Representing the lower speed bound for the segment control algorithm to control shallow boreholes,Representing the upper speed bound for the control of shallow boreholes by the segment control algorithm,Representing the lower speed bound for the feedback control algorithm to control deep boreholes,Representing the upper speed limit of the feedback control algorithm for controlling the deep drilling;
step S3, a first basic loss function is set for the segmentation control algorithm, and a second basic loss function is set for the feedback control algorithm;
step S4, respectively defining a penalty function of the first constraint condition and a penalty function of the second constraint condition according to the first constraint condition and the second constraint condition;
step S5, defining a loss function according to the first basic loss function, the penalty function of the first constraint condition, the second basic loss function and the penalty function of the second constraint condition;
Step S6, minimizing a loss function to minimize an error between the actual drilling speed and the predicted drilling speed so as to obtain a trained support vector regression model;
and S7, inputting real-time data to be drilled into a trained support vector regression model, and outputting drilling speed.
2. The steady rotation method of a mechanical arm of a downhole coal mine drilling machine according to claim 1, wherein the shallow drilling depth is 100m-500m, and the deep drilling depth is 500m-2000m.
3. The method for smooth rotation of a downhole coal mine drilling machine manipulator according to claim 1, wherein the step S4 defines a penalty function of the first constraint condition and a penalty function of the second constraint condition according to the first constraint condition and the second constraint condition, respectively, specifically comprising the steps of:
step S41, if the predicted drilling speed exceeds the upper speed limit of the first constraint condition and/or the predicted drilling speed exceeds the upper speed limit of the second constraint condition, setting an upper limit exceeding penalty formula ；
Step S42, if the predicted drilling speed is lower than the lower speed limit of the first constraint condition and/or the predicted drilling speed is lower than the lower speed limit of the second constraint condition, setting a lower-limit penalty formula；
Step S43, obtaining punishment functions of the first constraint condition and/or the second constraint condition according to the upper-bound punishment formula and the lower-bound punishment formula+。
4. A method of smooth rotation of a downhole coal mine drilling rig manipulator according to claim 3, wherein the above upper bound penalty formula:
；
In the method, in the process of the invention, Representing an out-of-bounds penalty formula,Representing the i-th predicted value of the current value,Representing an upper speed limit and n representing the number of predicted values.
5. A method of smooth rotation of a downhole coal mine drilling machine manipulator according to claim 3, wherein the lower bound penalty formula is:
；
In the method, in the process of the invention, Representing a lower-than-lower-bound penalty formula,Representing the i-th predicted value of the current value,Representing a lower speed limit and n representing the number of predicted values.
6. The method of smooth rotation of a downhole coal mine drilling machine manipulator of claim 1, wherein the loss function is:
；
In the method, in the process of the invention, Representing a loss function and,Representing a first basis loss function of the first model,Representing a second basis loss function, which is a function of the second basis,Representing an out-of-bounds penalty formula,Representing a lower-than-lower-bound penalty formula,AndRepresenting model weights.
7. The method for smooth rotation of a mechanical arm of an underground coal mine drilling machine according to claim 1, wherein the segment control algorithm in step S1 is used for controlling the shallow drilling speed, and specifically comprises: dividing shallow drilling into three stages of a coal seam approaching layer, a main coal seam and a coal seam underlying rock stratum according to the speed of the shallow drilling and the geological information of the shallow drilling, wherein the drilling speed of the coal seam approaching layer is controlled to be V 1 by a sectional control algorithm, the drilling speed of the main coal seam is set to be V 2 by the sectional control algorithm, and the drilling speed of the coal seam underlying rock stratum is set to be V 3,V2>V1>V3 by the sectional control algorithm;
The shallow drilling geological information is obtained through the shallow drilling, and the shallow drilling geological information comprises a shallow drilling geological type, a shallow drilling geological hardness and a shallow drilling geological thickness.
8. The method for smooth rotation of a mechanical arm of an underground coal mine drilling machine according to claim 1, wherein the feedback control algorithm in step S1 is used for controlling the deep drilling speed, and specifically comprises: dividing the deep drilling into three stages of a coal seam approaching layer to a shallow coal seam, a main coal seam to a deep coal seam, a coal seam underlying rock layer and a final hole layer according to the speed of the deep drilling and the geological information of the deep drilling; the feedback control algorithm controls the drilling speed from the coal seam approach layer to the shallow coal to be V 4, controls the drilling speed from the main coal seam to the deep coal to be V 5, and controls the drilling speed from the coal seam underlying stratum to the end hole layer to be V 6,V5>V4>V6.
9. The method for stably rotating the mechanical arm of the underground coal mine drilling machine according to claim 8,
The deep-hole geological information is obtained through the deep-hole, and the deep-hole geological information comprises a deep-hole geological type, deep-hole geological hardness, deep-hole geological thickness, deep-hole geological pressure and deep-hole geological structure.
10. A steady rotation system of a downhole coal mine drilling machine manipulator for executing the steady rotation method of the downhole coal mine drilling machine manipulator according to any one of claims 1-9, characterized by comprising the following modules:
Support vector regression model: the method comprises the steps of supporting a vector regression model, embedding a segment control algorithm and a feedback control algorithm, wherein the segment control algorithm is used for controlling the speed of shallow drilling, and the feedback control algorithm is used for controlling the speed of deep drilling;
Constraint condition setting module: the method comprises the steps of connecting with a support vector regression model, setting a first constraint condition for a segmentation control algorithm and setting a second constraint condition for a feedback control algorithm;
The basic loss function setting module: the constraint condition setting module is connected with the constraint condition setting module and is used for setting a first basic loss function for the segmentation control algorithm and a second basic loss function for the feedback control algorithm;
Penalty function setting module: the constraint condition setting module is connected with the basic loss function setting module and used for respectively defining a penalty function of the first constraint condition and a penalty function of the second constraint condition according to the first constraint condition and the second constraint condition;
the loss function definition module: the penalty function setting module is connected with the basic penalty function setting module and is used for defining a penalty function according to the first basic penalty function, the penalty function of the first constraint condition, the second basic penalty function and the penalty function of the second constraint condition;
Training module: the system comprises a loss function definition module, a support vector regression module and a control module, wherein the loss function definition module is connected with the support vector regression module and is used for minimizing a loss function so that the error between the actual drilling speed and the predicted drilling speed is minimized to obtain a trained support vector regression model;
and a result output module: and the training module is connected with the training module, inputs real-time data to be drilled into the trained support vector regression model, and outputs the drilling speed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410605503.5A CN118167275B (en) | 2024-05-16 | 2024-05-16 | Method and system for stably rotating mechanical arm of underground coal mine drilling machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410605503.5A CN118167275B (en) | 2024-05-16 | 2024-05-16 | Method and system for stably rotating mechanical arm of underground coal mine drilling machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118167275A CN118167275A (en) | 2024-06-11 |
| CN118167275B true CN118167275B (en) | 2024-07-19 |
Family
ID=91359203
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410605503.5A Active CN118167275B (en) | 2024-05-16 | 2024-05-16 | Method and system for stably rotating mechanical arm of underground coal mine drilling machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118167275B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104806226A (en) * | 2015-04-30 | 2015-07-29 | 北京四利通控制技术股份有限公司 | Intelligent drilling expert system |
| CA3051281A1 (en) * | 2018-08-07 | 2020-02-07 | Frank's International, Llc | Connection analyzed make-up systems and methods |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10012025B2 (en) * | 2013-10-18 | 2018-07-03 | Baker Hughes, A Ge Company, Llc | Lateral motion drill bit model |
| US10185306B2 (en) * | 2015-02-27 | 2019-01-22 | Board Of Regents, The University Of Texas System | Utilizing look-up tables representing all models in an automation control architecture to independently handle uncertainties in sensed data in oil and gas well construction |
| US10746009B2 (en) * | 2016-06-02 | 2020-08-18 | Baker Hughes, A Ge Company, Llc | Depth-based borehole trajectory control |
| CN110456646B (en) * | 2019-08-23 | 2021-01-29 | 中国矿业大学 | Design method of anchor rod drilling machine drill arm swing angle self-adaptive sliding mode control system based on EKF |
| GB2595549B (en) * | 2020-03-26 | 2022-06-29 | Landmark Graphics Corp | Physical parameter projection for wellbore drilling |
| CN114662390B (en) * | 2022-03-22 | 2023-09-29 | 西南石油大学 | A drilling loss pressure prediction method based on SVR algorithm |
| CN114718478B (en) * | 2022-04-18 | 2024-12-06 | 中国石油大学(华东) | A deepwater riser system recoil control method, system and hardware device |
| CN118151163B (en) * | 2024-05-10 | 2024-07-23 | 莱州亚通重型装备有限公司 | Automatic positioning method and system for underground coal mine drilling machine clamp holder based on radar technology |
-
2024
- 2024-05-16 CN CN202410605503.5A patent/CN118167275B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104806226A (en) * | 2015-04-30 | 2015-07-29 | 北京四利通控制技术股份有限公司 | Intelligent drilling expert system |
| CA3051281A1 (en) * | 2018-08-07 | 2020-02-07 | Frank's International, Llc | Connection analyzed make-up systems and methods |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118167275A (en) | 2024-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10657441B2 (en) | Model generation for real-time rate of penetration prediction | |
| US10669834B2 (en) | Game theoretic control architecture for drilling system automation | |
| US20230288603A1 (en) | System and method for combining curves in oilfield drilling and production operations | |
| US20210017847A1 (en) | Method of modeling fluid flow downhole and related apparatus and systems | |
| US20150029034A1 (en) | System and console for monitoring and managing well site operations | |
| US11261719B2 (en) | Use of surface and downhole measurements to identify operational anomalies | |
| US11846748B2 (en) | Deep learning seismic attribute fault predictions | |
| US11466564B2 (en) | Systems and methods for downhole memory tool activation and control | |
| Jafarizadeh et al. | A new robust predictive model for lost circulation rate using convolutional neural network: A case study from Marun Oilfield | |
| CN118167275B (en) | Method and system for stably rotating mechanical arm of underground coal mine drilling machine | |
| CN117350103A (en) | Drilling parameter optimization method and system based on digital twin system | |
| US11913334B2 (en) | Downhole controller assisted drilling of a constant curvature in a borehole | |
| WO2023146554A1 (en) | Real-time curvature estimation for autonomous directional drilling | |
| US11143019B2 (en) | Real time estimation of fracture geometry from the poro-elastic response measurements | |
| US11761326B2 (en) | Automated scheduling of sensors for directional drilling | |
| US20210065050A1 (en) | Dynamic drilling dysfunction codex | |
| US20230100038A1 (en) | Combined soft and stiff-string torque and drag model | |
| CN113279747B (en) | System and method for preparing drilling mud formula and performance parameters | |
| WO2022182390A1 (en) | Diagnostic trouble code signature classification for downhole tool fault identification | |
| Løken et al. | Automated drilling algorithms implementation on a laboratory drilling rig | |
| US20240191611A1 (en) | Periodic predictive drilling based on active and historic data | |
| Wu et al. | Improvement of Rate of Penetration in Drilling Process based on TCN-Vibration Recognition | |
| KR102189160B1 (en) | Method and system for control of offshore drilling equipment using finite state machine | |
| CN117846564A (en) | Method for realizing downhole closed-loop control of borehole track | |
| Gu et al. | A Journey Towards Safer and Faster Drilling: Real-Time Advisory With Digital Twins and AI |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |