Sectional resistance adjusting supporting system and method

Abstract

The invention relates to the technical field of coal mine underground mining supporting, in particular to a segmented resistance adjusting supporting system and method. The segmented resistance adjusting supporting system comprises a hydraulic support set used for supporting an overlying rock layer; the sensing module is used for monitoring state parameters of a working face in real time, and the state parameters comprise support resistance, support poses, coal wall states and working conditions of a coal mining machine; the decision control module is in communication connection with the sensing module and is used for deciding and generating a resistance trimming instruction through an intelligent algorithm based on the state parameters; and the liquid supply module is connected with the decision control module and the hydraulic support group, and is used for receiving the resistance adjusting instruction and dynamically adjusting the liquid pressure of the hydraulic support group. The surrounding rock stress, the support state and the working condition of the coal mining machine are monitored in real time through the sensing module, intelligent decision making is conducted through the decision control module, the liquid supply module is driven to dynamically adjust the support setting force, dynamic and accurate adaptation of support parameters is achieved, and the support efficiency and safety are improved.

Description

Technical Field

[0001] This invention relates to the field of underground coal mine support technology, and in particular to a segmented resistance adjustment support system and method. Background Technology

[0002] Currently, hydraulic supports are the core support system for underground coal mining faces, and their performance directly affects the safety and efficiency of production. Specifically, existing hydraulic supports use emulsion as the working medium within the support columns, which are equipped with safety valves. During normal operation, emulsion pumps supply fluid to the columns, causing the support beams to contact the roof and achieve the preset initial support force. As mining progresses, roof pressure increases, and the pressure inside the columns rises. When the safety valve reaches its set value, it opens to release pressure, at which point the support is in a working resistance state. However, in this method, both the initial support force and the working resistance are fixed values, constituting a passive support mode that is ill-suited to the complex and variable stress environment of the surrounding rock underground. Especially during the mining process, the working face undergoes different stages such as "before periodic pressure – normal mining – after periodic pressure," resulting in significant changes in the stress state of the surrounding rock. Existing fixed-resistance support systems cannot respond to such dynamic stress fluctuations, easily leading to the following problems: During cyclic pressure periods, insufficient support resistance can cause roof subsidence or coal wall spalling; during normal mining, excessive resistance can result in energy waste and equipment wear, and even "over-support" or "under-support" phenomena in some areas, affecting mining efficiency and posing safety hazards. Furthermore, for hard coal seam mining, traditional support systems cannot actively utilize mine pressure to weaken the coal wall, resulting in high cutting resistance and low cutting efficiency for the coal mining machine, hindering high-yield and efficient coal mine development.

[0003] Therefore, there is an urgent need for an intelligent support system that can adjust the support parameters in real time according to the changes in surrounding rock stress and the working conditions of the coal mining machine, so as to achieve precise and adaptive support and improve the overall mining efficiency and safety of the working face. Summary of the Invention

[0004] Therefore, the technical problem to be solved by the present invention is to overcome the problems in the prior art, such as the inability to actively utilize mine pressure to weaken the coal wall, resulting in high cutting resistance and low cutting efficiency of the coal mining machine, which restricts the high-yield and high-efficiency advancement of coal mines.

[0005] To solve the above-mentioned technical problems, the present invention provides a segmented resistance adjustment support system, comprising: Hydraulic support assembly, used to support the overlying rock strata; The sensing module is used to monitor the status parameters of the working face in real time, including support resistance, support posture, coal wall condition and coal mining machine operating conditions. The decision control module is communicatively connected to the sensing module and is used to generate a resistance adjustment command based on the state parameters through an intelligent algorithm. The liquid supply module is connected to the decision control module and the hydraulic support assembly, and is used to receive the resistance adjustment command and dynamically adjust the liquid pressure of the hydraulic support assembly.

[0006] Preferably, the sensing module includes: A sensor array, mounted on a hydraulic support, is used to monitor the support resistance and position. The sensor array includes a column pressure sensor, an tilt sensor, and a mining height sensor. A three-dimensional laser scanning camera is installed under the working face support to monitor the crack extension and deformation of the coal face; The data access unit is used to access the cutting condition data of the coal mining machine, which includes drum load, cutting speed and cutting current.

[0007] Preferably, the decision control module includes: The server is used for real-time data analysis and to establish a coupled database. An independent controller, located under the hydraulic support, is used to receive and execute resistance adjustment commands.

[0008] Preferably, the intelligent algorithm is a fusion algorithm, which uses the position of the coal mining machine as a reference to perform spatiotemporal alignment and binding of support resistance, coal wall status and cutting resistance data at the same time and the same working face position, and performs training and optimization based on the coupled database; The intelligent algorithm includes a fuzzy PID control algorithm and a neural network prediction model. The neural network prediction model is used to predict the changing trends of surrounding rock stress, roof displacement, coal wall fissures and coal mining machine conditions based on historical data, predict the cycle pressure time and intensity, and generate optimized support parameters. The fuzzy PID control algorithm is used to dynamically output the target resistance adjustment amount of the hydraulic support, taking the support load, support posture, coal wall deformation and coal mining machine conditions as inputs, the controllable surrounding rock deformation and stable support conditions as constraints, and the minimum cutting resistance of the coal mining machine as the objective function.

[0009] Preferably, the decision control module employs different resistance adjustment strategies according to different mining stages, and the resistance adjustment strategies include: During the normal mining phase, the fluid supply module is controlled to reduce the support resistance, causing some of the overburden pressure to transfer to the coal face, thereby weakening the coal face. During the periodic pressurization phase, the liquid supply module is controlled to increase the initial support force of the support and enhance the stability of the top plate; During the post-cycle pressure phase, the control fluid supply module reduces the support resistance again.

[0010] Preferably, the liquid supply module includes an emulsion pump and a proportional control valve, wherein the proportional control valve adjusts the output pressure of the emulsion pump according to the resistance adjustment command issued by the decision control module.

[0011] The present invention also provides a segmented resistance adjustment support method, comprising: The state parameters of the working face are collected in real time by the sensing module. The state parameters include support resistance, support posture, coal wall condition and coal mining machine condition. Based on the aforementioned state parameters, a decision is made through an intelligent algorithm to generate a resistance adjustment command for the current mining stage. According to the resistance adjustment command, the liquid pressure supplied to the hydraulic support group is dynamically adjusted to adjust the initial support force of the support in stages.

[0012] Preferably, the step of generating a resistance adjustment command for the current mining stage by making a decision based on the state parameters using an intelligent algorithm includes: Based on the position of the coal mining machine, the support resistance, coal wall condition and cutting resistance data at the same time and the same working face are spatiotemporally aligned and bound. The neural network model is used to predict the changing trends of surrounding rock stress, roof displacement, coal wall fissures and coal mining machine conditions, and to predict periodic pressure. With controllable surrounding rock deformation and stable support operation as constraints, and minimizing the cutting resistance of the coal mining machine as the objective function, the optimal resistance adjustment scheme is solved by optimization algorithm. The target resistance adjustment amount of the hydraulic support is dynamically calculated and output using a fuzzy PID control algorithm.

[0013] Preferably, the generation of the resistance adjustment command for the current mining stage further includes: Identify the current mining stage of the working face; if it is in the normal mining stage or the post-period pressure stage, generate instructions to reduce support resistance. If the system is in the periodic pressure phase or an upcoming periodic pressure is predicted, an instruction is generated to increase the initial support force of the stent.

[0014] Preferably, the step of dynamically adjusting the liquid pressure supplied to the hydraulic support assembly according to the resistance adjustment command, and adjusting the initial support force of the support in stages, includes: Using real-time monitored support load, support posture, coal wall deformation, and coal mining machine operating parameters as feedback inputs, and with the constraints of maintaining the surrounding rock deformation within a preset threshold range and maintaining the stability of the support posture, and with the optimization objective of minimizing the cutting resistance of the coal mining machine, a closed-loop control algorithm is used to calculate and output pressure adjustment commands to the fluid supply module in real time, so as to achieve dynamic and adaptive adjustment of the initial support force of the support.

[0015] The technical solution of the present invention has the following advantages compared with the prior art: This invention discloses a segmented resistance-adjusting support system and method. A sensing module monitors the surrounding rock stress, support status, and coal mining machine operating conditions in real time. A decision control module intelligently makes decisions, driving the fluid supply module to dynamically adjust the initial support force of the supports. This allows the support system to proactively adapt to pressure fluctuations at different stages of mining. This effectively avoids the risk of roof subsidence caused by insufficient support during periodic pressure increases due to fixed-parameter support, as well as equipment wear and energy waste caused by over-support during normal mining. Thus, while ensuring safety, it significantly improves the overall efficiency of the support system and coordinates the support system with coal mining operations. During normal mining, by strategically reducing support resistance, some overburden pressure is transferred to the coal face, achieving proactive weakening of the hard coal body. This directly reduces the cutting resistance of the coal mining machine, solving the problem of low cutting efficiency in hard coal seams and ensuring high-yield and efficient coal mine operations. By employing fusion algorithms such as fuzzy PID and neural networks, it not only achieves precise closed-loop control of the current working conditions but also predicts the trend of surrounding rock stress changes and the timing and intensity of periodic pressure based on a coupled model built from historical data, enabling early warning and optimization of support parameters. This gives the system the ability to make advanced decisions and self-learn and self-optimize, transforming it from a passive response to intelligent proactive protection. Attached Figure Description

[0016] To make the content of this invention easier to understand, the invention will be further described in detail below with reference to specific embodiments and accompanying drawings, wherein: Figure 1 This is a structural diagram of a segmented resistance adjustment support system provided by the present invention; Figure 2 This is a flowchart of a segmented resistance adjustment support method provided by the present invention; Figure 3 This is a schematic diagram of the segmented resistance adjustment support method provided by the present invention. Detailed Implementation

[0017] The core of this invention is to provide a segmented resistance adjustment support system. The system uses a sensing module to monitor the surrounding rock stress, support status, and coal mining machine operating conditions in real time. The decision control module makes intelligent decisions and drives the fluid supply module to dynamically adjust the initial support force of the support. This achieves dynamic and precise adaptation of support parameters, improving support efficiency and safety.

[0018] To enable those skilled in the art to better understand the present invention, the invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Please refer to Figure 1. Figure 1 The present invention provides a logic diagram of a segmented resistance adjustment support system; the specific operation steps are as follows: Hydraulic support assembly, used to support the overlying rock strata; The sensing module includes parameters for real-time monitoring of the working face, such as support resistance, support posture, coal face condition, and coal mining machine operating conditions. The sensing module includes a sensor array mounted on the hydraulic support to monitor support resistance and posture; the sensor array includes a column pressure sensor, an inclination sensor, and a mining height sensor. A three-dimensional laser scanning camera is mounted under the working face support to monitor the extension and deformation of cracks in the coal face. A data access unit is used to access the cutting operation data of the coal mining machine, including drum load, cutting speed, and cutting current.

[0020] Specifically, the sensing module includes column pressure sensors, support tilt sensors, and mining height sensors on the hydraulic support, used to monitor support pressure and its position and orientation; a three-dimensional laser scanning camera is installed under the hydraulic support to observe the extension and deformation of coal wall cracks; the system needs to access the coal mining machine cutting condition monitoring data, including the drum load of the coal mining machine (measured by a torque sensor installed on the rocker arm), cutting speed (measured by the inertial navigation system of the coal mining machine), and cutting current (measured by the coal mining machine's electrical control system).

[0021] A decision control module, communicatively connected to the sensing module, is used to generate a resistance adjustment command based on the state parameters using an intelligent algorithm. The decision control module includes: The server is used for real-time data analysis and to establish a coupled database. An independent controller, located under the hydraulic support, is used to receive and execute resistance adjustment commands.

[0022] The intelligent algorithm is a fusion algorithm. Based on the position of the coal mining machine, it performs spatiotemporal alignment and binding of support resistance, coal wall condition and cutting resistance data at the same time and the same working face position, and performs training and optimization based on the coupled database. The intelligent algorithm includes a fuzzy PID control algorithm and a neural network prediction model. The neural network prediction model is used to predict the changing trends of surrounding rock stress, roof displacement, coal wall fissures and coal mining machine conditions based on historical data, predict the cycle pressure time and intensity, and generate optimized support parameters. The fuzzy PID control algorithm is used to dynamically output the target resistance adjustment amount of the hydraulic support, taking the support load, support posture, coal wall deformation and coal mining machine conditions as inputs, the controllable surrounding rock deformation and stable support conditions as constraints, and the minimum cutting resistance of the coal mining machine as the objective function.

[0023] Specifically, the decision control module adopts different resistance adjustment strategies according to different mining stages, and the resistance adjustment strategies include: During the normal mining phase, the fluid supply module is controlled to reduce the support resistance, causing some of the overburden pressure to transfer to the coal face, thereby weakening the coal face. During the periodic pressurization phase, the liquid supply module is controlled to increase the initial support force of the support and enhance the stability of the top plate; During the post-cycle pressure phase, the control fluid supply module reduces the support resistance again.

[0024] In one embodiment, the decision control module deploys edge computing nodes and a server cluster in the underground roadway to achieve real-time data analysis and historical data storage. Each support is equipped with an independent controller to receive and execute resistance adjustment commands. A fusion algorithm of "fuzzy PID + neural network" is adopted, with input features including three dimensions: support condition: roof / mining height subsidence rate, support resistance, support posture; surrounding rock condition (coal wall); coal mining machine condition: drum load, cutting speed, cutting current. The output is the target resistance adjustment amount of the hydraulic support or the pump station supply pressure.

[0025] Network communication module: Can use Wi-Fi or 5G wireless network communication.

[0026] Adaptive control mechanism: The system uses multi-source sensors, including column pressure monitoring, support posture monitoring, and 3D laser scanning, to monitor parameters such as surrounding rock deformation and coal mining machine operating conditions in real time. Through intelligent algorithm decision-making and PID control, it dynamically adjusts the initial support force of the support.

[0027] The fluid supply module, connected to the decision control module and the hydraulic support assembly, receives the resistance adjustment command and dynamically adjusts the fluid pressure of the hydraulic support assembly. The fluid supply module includes an emulsion pump, a proportional control valve, pipelines, and connecting accessories. The proportional control valve can steplessly adjust the fluid supply pressure of the emulsion pump according to different parameter setting signals.

[0028] This embodiment provides a segmented resistance-adjustable support system. A sensing module monitors the surrounding rock stress, support status, and coal mining machine operating conditions in real time. A decision control module intelligently makes decisions, driving the fluid supply module to dynamically adjust the initial support force of the supports. This allows the support system to proactively adapt to pressure fluctuations at different stages of mining. This effectively avoids the risk of roof subsidence caused by under-support during periodic pressure increases due to fixed-parameter support, as well as equipment wear and energy waste caused by over-support during normal mining. Thus, while ensuring safety, it significantly improves the overall efficiency of the support system and coordinates the support system with the coal mining operation. During normal mining, by strategically reducing the support resistance, some of the overburden pressure is transferred to the coal face, achieving proactive weakening of the hard coal body. This directly reduces the cutting resistance of the coal mining machine, solving the problem of low cutting efficiency in hard coal seams and ensuring high-yield and efficient coal mine operations. By employing fusion algorithms such as fuzzy PID and neural networks, it not only achieves precise closed-loop control of the current working conditions but also predicts the trend of surrounding rock stress changes and the timing and intensity of periodic pressure based on a coupled model built from historical data, enabling early warning and optimization of support parameters. This gives the system the ability to make advanced decisions and self-learn and self-optimize, transforming it from a passive response to intelligent proactive protection.

[0029] like Figure 2 As shown, Figure 2 The segmented resistance adjustment support method provided by the present invention is as follows: Step S201: Collect the status parameters of the working face in real time through the sensing module. The status parameters include support resistance, support posture, coal wall status and coal mining machine operating conditions. In one embodiment, pressure sensors are installed on the hydraulic support columns to monitor support resistance; tilt sensors and displacement sensors are installed on the support to monitor its position and orientation in real time, while a support height sensor can reflect the displacement of the overlying strata; a three-dimensional laser scanning camera is installed under the working face support to monitor coal face deformation in real time; the system accesses coal mining machine cutting condition monitoring data, including the drum load of the coal mining machine (measured by a torque sensor installed on the rocker arm), cutting speed (measured by the coal mining machine's inertial navigation system), and cutting current (measured by the coal mining machine's electrical control system). Multi-source sensors (stress, displacement, tilt, etc.) provide full coverage, enabling coordinated monitoring of the surrounding rock, cutting, and support conditions.

[0030] Step S202: Based on the state parameters, a decision is made through an intelligent algorithm to generate a resistance adjustment command for the current mining stage; Specifically, based on the position of the coal mining machine, the support resistance, coal wall condition and cutting resistance data at the same time and the same working face are spatiotemporally aligned and bound. The neural network model is used to predict the changing trends of surrounding rock stress, roof displacement, coal wall fissures and coal mining machine conditions, and to predict periodic pressure. With controllable surrounding rock deformation and stable support operation as constraints, and minimizing the cutting resistance of the coal mining machine as the objective function, the optimal resistance adjustment scheme is solved by optimization algorithm. The target resistance adjustment amount of the hydraulic support is dynamically calculated and output using a fuzzy PID control algorithm.

[0031] Identify the current mining stage of the working face; if it is in the normal mining stage or the post-period pressure stage, generate instructions to reduce support resistance. If the system is in the periodic pressure phase or an upcoming periodic pressure is predicted, an instruction is generated to increase the initial support force of the stent.

[0032] In one embodiment, using the "coal mining machine position" as a reference, the "support resistance - coal wall status - cutting resistance" data at the same time and the same working face position are bound together to achieve spatiotemporal alignment of the monitoring objects.

[0033] First, resistance thresholds for different mining stages are initially preset. When monitoring data exceeds the threshold, the fluid supply pressure of the support is automatically adjusted. After a period of testing, a neural network model is trained using historical data to predict trends in surrounding rock stress, roof displacement, coal wall fissures, and coal mining machine operating conditions. A coupled database of "surrounding rock-cutting-support" is established to store historical monitoring data and resistance adjustment response results, providing training samples for the intelligent algorithm and optimizing the resistance adjustment parameters. Subsequently, based on the optimization results, segmented resistance adjustment of the support system is implemented.

[0034] Step S203: According to the resistance adjustment command, dynamically adjust the liquid pressure supplied to the hydraulic support group to adjust the initial support force of the support in segments.

[0035] Specifically, the system uses real-time monitored support load, support posture, coal wall deformation, and coal mining machine operating parameters as feedback inputs. It takes maintaining the surrounding rock deformation within a preset threshold range and maintaining the stability of the support posture as constraints, and minimizing the cutting resistance of the coal mining machine as the optimization objective. Through a closed-loop control algorithm, the system calculates and outputs pressure adjustment commands to the fluid supply module in real time to achieve dynamic and adaptive adjustment of the initial support force.

[0036] In one embodiment, using support load, support posture, coal face deformation, and coal mining machine operating conditions as input data, and based on the coupled decision-making process of "surrounding rock-cutting-support," with "controllable surrounding rock deformation" and "stable support operating conditions" as constraints, and "minimum coal mining machine cutting resistance" as the objective function, a genetic algorithm is used to solve for the optimal resistance adjustment scheme. A PID fuzzy control algorithm is then employed to dynamically adjust the initial support force. A neural network model is introduced to predict the cycle and pressure time and intensity, providing early warnings 2-4 hours in advance and optimizing support parameters.

[0037] This embodiment provides a segmented resistance-adjusting support method. A sensing module monitors the surrounding rock stress, support status, and coal mining machine operating conditions in real time. A decision control module intelligently makes decisions, driving the fluid supply module to dynamically adjust the initial support force of the supports. This allows the support system to proactively adapt to pressure fluctuations at different stages of mining. This effectively avoids the risk of roof subsidence caused by under-support during periodic pressure increases due to fixed-parameter support, as well as equipment wear and energy waste caused by over-support during normal mining. Thus, while ensuring safety, it significantly improves the overall efficiency of the support system and coordinates the support system with the coal mining operation. During normal mining, by strategically reducing the support resistance, some of the overburden pressure is transferred to the coal face, achieving proactive weakening of the hard coal body. This directly reduces the cutting resistance of the coal mining machine, solving the problem of low cutting efficiency in hard coal seams and ensuring high-yield and efficient coal mine operations. By employing fusion algorithms such as fuzzy PID and neural networks, it not only achieves precise closed-loop control of the current working conditions but also predicts the trend of surrounding rock stress changes and the timing and intensity of periodic pressure based on a coupled model built from historical data, enabling early warning and optimization of support parameters. This gives the system the ability to make advanced decisions and self-learn and self-optimize, transforming it from a passive response to intelligent proactive protection.

[0038] Based on the above embodiments, this embodiment provides a detailed description of a segmented resistance adjustment support method, such as... Figure 3 As shown, the details are as follows: 1. System initialization and parameter preset: Before the system starts running, preset the initial control parameters in the decision control module: The working face is divided into three typical control units along the advancing direction: normal mining area, periodic pressure warning area, and strong pressure response area.

[0039] Set a basic resistance threshold range for each unit. For example, the target range for initial support force in the normal mining area is 18-22 MPa, and the range for periodic pressure warning area is 25-30 MPa.

[0040] The core constraints of the control algorithm are set as follows: roof subsidence rate <3 mm / h, coal wall deformation rate <5 mm / h.

[0041] 2. Real-time data monitoring and collection: After the system starts up, each sensing module begins to work: Pressure sensors, tilt sensors, and height sensors on the hydraulic support collect data on the support's resistance, attitude, and top plate displacement at a frequency of 10Hz.

[0042] A three-dimensional laser scanning camera continuously scans the coal face and uses point cloud analysis algorithms to calculate the crack development index and bulging deformation of the coal face in real time.

[0043] The system obtains real-time data on the drum torque, cutting speed, and motor current of the coal mining machine through a data interface.

[0044] All data is timestamped and tagged with the support location, and transmitted in real time to the decision control module via the network communication module.

[0045] 3. Multi-source data fusion and operating condition identification: After receiving the data, the edge computing server in the decision control module performs the following operations: Spatiotemporal alignment: Based on the position of the coal mining machine, the data of "support resistance - coal wall deformation - cutting current" within the same geological unit at the same time are bound together to form a unified working condition snapshot.

[0046] Feature extraction: Calculate key feature parameters, such as the gradient of support resistance, coal wall deformation acceleration, and the mean and fluctuation of cutting current.

[0047] Operating condition judgment: The extracted features are compared with historical databases and preset thresholds. For example, if the system detects that the support resistance is rising rapidly and continuously within 10 minutes and the roof sinking rate exceeds 2 mm / h, the system will preliminarily determine that it has entered the "precursor stage of periodic pressure".

[0048] 4. Intelligent decision-making and resistance adjustment command generation: Based on different recognition results, the system proceeds to the corresponding decision branch: The system was identified as "normal mining with a hard coal face." The neural network model predicted no strong pressure risk in the near future, but the cutting current remained high. At this point, the system, with "minimizing cutting resistance" as the optimization objective, used a genetic algorithm to find the optimal solution while satisfying the stability constraints of the roof and coal face. The decision was to reduce the initial support force of the current control unit from 24 MPa to 19 MPa.

[0049] The system identifies or predicts "periodic pressure," and the neural network model predicts a strong pressure surge will occur in two hours based on the pressure fluctuation pattern. The system immediately activates an early warning system and, with "maximizing roof stability" as the primary objective, decides to pre-increase the initial support force of the supports within the warning area to 28 MPa.

[0050] 5. Instruction Execution and Dynamic Control: Decision instructions are issued to the independent controllers of each support unit: The controller compares the received target pressure value (e.g., 19 MPa) with the actual value fed back by the pressure sensor, and calculates the control signal for the electro-hydraulic proportional control valve using a fuzzy PID algorithm.

[0051] The proportional valve precisely adjusts the opening size based on this signal, changing the flow rate and pressure of the emulsion entering the support column, so that the actual supporting force of the support smoothly and stably approaches the target value.

[0052] 6. Effectiveness Evaluation and System Self-Learning: After one resistance adjustment is completed, the system enters the performance evaluation and learning phase: Feedback on effectiveness: The system continuously monitors the changes in coal wall deformation and the response of the cutting current of the coal mining machine after resistance adjustment. For example, in Scenario 1, the system confirmed that after reducing the resistance, the cutting current decreased by 10% within 30 minutes, and the coal wall remained stable, indicating that the control was effective and successful.

[0053] Data recording: The complete data chain of this "control order - environmental response - effect evaluation" will be stored as a new sample in the "surrounding rock - cutting - support" coupled database.

[0054] Model updates: Edge servers periodically (e.g., every 24 hours) incrementally train the neural network prediction model using newly added sample data, optimizing its weight parameters to make the next prediction and decision more accurate.

[0055] Through the continuous operation of the aforementioned closed-loop workflow, this method has achieved a transformation from "static passive support" to "dynamic intelligent support" in this working face. After a month of industrial testing, while ensuring roof safety, the average cutting energy consumption of the coal mining machine was reduced by 11%, and the daily progress of the working face was increased by 9%, fully verifying the effectiveness and advancement of this method.

[0056] Obviously, the above embodiments are merely illustrative examples for clear explanation and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations here. However, obvious variations or modifications derived therefrom are still within the scope of protection of this invention.

Claims

1. A segmented resistance adjustment support system, characterized in that, include: Hydraulic support assembly, used to support the overlying rock strata; The sensing module is used to monitor the status parameters of the working face in real time, including support resistance, support posture, coal wall condition and coal mining machine operating conditions. The decision control module is communicatively connected to the sensing module and is used to generate a resistance adjustment command based on the state parameters through an intelligent algorithm. The liquid supply module is connected to the decision control module and the hydraulic support assembly, and is used to receive the resistance adjustment command and dynamically adjust the liquid pressure of the hydraulic support assembly.

2. The segmented resistance adjustment support system according to claim 1, characterized in that, The sensing module includes: A sensor array, mounted on a hydraulic support, is used to monitor the support resistance and position. The sensor array includes a column pressure sensor, an tilt sensor, and a mining height sensor. A three-dimensional laser scanning camera is installed under the working face support to monitor the crack extension and deformation of the coal face; The data access unit is used to access the cutting condition data of the coal mining machine, which includes drum load, cutting speed and cutting current.

3. The segmented resistance adjustment support system according to claim 1, characterized in that, The decision control module includes: The server is used for real-time data analysis and to establish a coupled database. An independent controller, located under the hydraulic support, is used to receive and execute resistance adjustment commands.

4. The segmented resistance adjustment support system according to claim 1, characterized in that, The intelligent algorithm is a fusion algorithm. Based on the position of the coal mining machine, it performs spatiotemporal alignment and binding of support resistance, coal wall status and cutting resistance data at the same time and the same working face position, and performs training and optimization based on the coupled database. The intelligent algorithm includes a fuzzy PID control algorithm and a neural network prediction model. The neural network prediction model is used to predict the changing trends of surrounding rock stress, roof displacement, coal wall fissures and coal mining machine conditions based on historical data, predict the periodic pressure time and intensity, and generate optimized support parameters. The fuzzy PID control algorithm is used to dynamically output the target resistance adjustment amount of the hydraulic support, taking the support load, support posture, coal wall deformation and coal mining machine conditions as inputs, the controllable surrounding rock deformation and stable support conditions as constraints, and the minimum cutting resistance of the coal mining machine as the objective function.

5. The segmented resistance adjustment support system according to claim 1, characterized in that, The decision control module employs different resistance adjustment strategies based on different mining stages, and the resistance adjustment strategies include: During the normal mining phase, the fluid supply module is controlled to reduce the support resistance, causing some of the overburden pressure to transfer to the coal face, thereby weakening the coal face. During the periodic pressurization phase, the liquid supply module is controlled to increase the initial support force of the support and enhance the stability of the top plate; During the post-cycle pressure phase, the control fluid supply module reduces the support resistance again.

6. The segmented resistance adjustment support system according to claim 1, characterized in that, The liquid supply module includes an emulsion pump and a proportional control valve. The proportional control valve adjusts the output pressure of the emulsion pump according to the resistance adjustment command issued by the decision control module.

7. A segmented resistance adjustment support method, characterized in that, include: The state parameters of the working face are collected in real time by the sensing module. The state parameters include support resistance, support posture, coal wall condition and coal mining machine condition. Based on the aforementioned state parameters, a decision is made through an intelligent algorithm to generate a resistance adjustment command for the current mining stage. According to the resistance adjustment command, the liquid pressure supplied to the hydraulic support group is dynamically adjusted to adjust the initial support force of the support in stages.

8. The segmented resistance adjustment support method according to claim 7, characterized in that, The step of generating a resistance adjustment command for the current mining stage by making decisions based on the state parameters and using an intelligent algorithm includes: Based on the position of the coal mining machine, the support resistance, coal wall condition and cutting resistance data at the same time and the same working face are spatiotemporally aligned and bound. The neural network model is used to predict the changing trends of surrounding rock stress, roof displacement, coal wall fissures and coal mining machine conditions, and to predict periodic pressure. With controllable surrounding rock deformation and stable support operation as constraints, and minimizing the cutting resistance of the coal mining machine as the objective function, the optimal resistance adjustment scheme is solved by optimization algorithm. The target resistance adjustment amount of the hydraulic support is dynamically calculated and output using a fuzzy PID control algorithm.

9. The segmented resistance adjustment support method according to claim 8, characterized in that, The generation of the resistance adjustment command for the current mining stage also includes: Identify the current mining stage of the working face; if it is in the normal mining stage or the post-period pressure stage, generate instructions to reduce support resistance. If the system is in the periodic pressure phase or an upcoming periodic pressure is predicted, an instruction is generated to increase the initial support force of the stent.

10. The segmented resistance adjustment support method according to claim 7, characterized in that, The step of dynamically adjusting the liquid pressure supplied to the hydraulic support assembly according to the resistance adjustment command, and adjusting the initial support force of the support in segments, includes: Using real-time monitored support load, support posture, coal wall deformation, and coal mining machine operating parameters as feedback inputs, and with the constraints of maintaining the surrounding rock deformation within a preset threshold range and maintaining the stability of the support posture, and with the optimization objective of minimizing the cutting resistance of the coal mining machine, a closed-loop control algorithm is used to calculate and output pressure adjustment commands to the fluid supply module in real time, so as to achieve dynamic and adaptive adjustment of the initial support force of the support.

Images