Coal mining machine body control system

Abstract

The invention discloses a coal mining machine body control system, which belongs to the technical field of coal mining equipment control, and comprises a multi-dimensional sensing module, an interface modeling module, a path planning module, a collaborative support module, a posture regulation and control module, an efficiency evaluation module and an experience sharing module. A lightweight two-dimensional coal seam feature model is constructed, and an abnormal region is dynamically labeled, so that the calculation complexity is greatly reduced, the model construction time is shortened to a millisecond level, and the real-time control requirement is met; meanwhile, key geological features are reserved in the model, and a visual and efficient decision basis is provided for path planning; through dynamic adjustment of the time decay factor and the boundary priority coefficient, the model can adapt to a coal seam sudden change scene, the hysteresis problem caused by static modeling is avoided, and the adaptability of the system to complex geology is remarkably improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of coal mining equipment control, and particularly relates to a shearer body control system. BACKGROUND

[0002] The shearer is the core equipment of the fully mechanized coal mining face, and its running stability directly affects the coal mining efficiency and operation safety. There are problems such as response lag and insufficient precision. Under complex geological conditions such as inclined coal seams, floor undulations or roof pressure changes, the shearer body is prone to deflection, overturning or jamming, resulting in uneven cutting, equipment damage and even safety accidents.

[0003] However, the existing shearer body control system still has certain defects. The existing technology relies on a single sensor for data acquisition, lacks fusion processing of multi-source heterogeneous data, and causes incomplete and redundant geological information. Fixed rules or preset path planning are mostly used, which cannot dynamically adjust the cutting strategy according to real-time geological conditions. The shearer is mostly operated in isolation, and there is no control experience sharing mechanism among the shearers. The attitude control and support action are designed separately, and there is no cooperative linkage mechanism. Therefore, a shearer body control system is proposed. SUMMARY

[0004] The purpose of the present application is to provide a shearer body control system to solve the problems raised in the background.

[0005] To achieve the above purpose, the present application provides the following technical scheme: a shearer body control system, comprising a multi-dimensional perception module, an interface modeling module, a path planning module, a cooperative support module, an attitude control module, an efficiency evaluation module and an experience sharing module. The multi-dimensional perception module collects coal seam and surrounding rock geological data through an on-board sensor array. The interface modeling module constructs a real-time coal seam feature model according to the collected multi-source data. The path planning module generates control instructions by fuzzy decision of the cutting path according to the real-time coal seam feature model. The cooperative support module performs adaptive support action of the hydraulic support group according to the generated control instructions. The attitude control module performs closed-loop adjustment of the traction speed according to the collected body attitude data and the generated control instructions. The efficiency evaluation module performs associated matching of the control parameters and the geological conditions through the monitoring system operation index. The experience sharing module publishes and warns the control experience package within the group according to the optimized parameters after the associated matching.

[0006] Preferably, the multi-dimensional perception module is wirelessly connected to the interface modeling module, the interface modeling module is wirelessly connected to the path planning module, the path planning module is wirelessly connected to the collaborative support module, the collaborative support module is wirelessly connected to the attitude control module, the attitude control module is wirelessly connected to the performance evaluation module, and the performance evaluation module is wirelessly connected to the experience sharing module.

[0007] Preferably, the multi-dimensional sensing module includes a high-precision ground-penetrating radar installed on the coal mining machine drum to obtain information on coal seam thickness changes, interbedded rock locations, and hardness distribution by analyzing electromagnetic wave reflection signals; a hyperspectral imager installed on the coal mining machine body; vibration and acoustic sensors embedded in key positions of the coal mining machine rocker arm and cutting section to monitor the vibration spectrum and sound characteristics during the cutting process in real time; inertial measurement units (IMUs) and tilt sensors installed at key nodes of the coal mining machine body to monitor the pitch angle, tilt angle, and heading angle of the machine body; and a lidar installed at the head of the coal mining machine to preprocess the collected raw data.

[0008] Preferably, the interface modeling module receives the preprocessed data stream in real time and calculates the comprehensive geological characteristic index of the coal seam, as follows: , In the formula, Indicates the comprehensive geological characteristics index of the coal seam. This indicates the abrupt change in coal seam thickness. Indicates the reference coal seam thickness. This represents the reflectance of coal and rock at characteristic wavelengths in hyperspectral imaging. The reference reflectance of pure coal This represents the high-frequency vibration energy detected by the vibration sensor. Represents the reference vibration energy. This represents the dynamic weighting coefficient.

[0009] Preferably, the interface modeling module, based on the comprehensive geological characteristics of the coal seam, compresses them into a simplified two-dimensional feature map to construct a coal seam feature model, which is implemented as follows: In the formula, This represents the coal seam characteristic model at the current moment. This represents the coal seam characteristic model at the previous moment. Indicates the time decay factor. Indicates the boundary priority coefficient. This indicates a boundary update based on GCI. It represents the annotation of abnormal areas based on GCI; it automatically annotates geological features based on coal seam feature models, draws continuous curves in real time, marks thickness abrupt change points and abnormal area markers, and the annotation results are associated with the current cutting position.

[0010] Preferably, the path planning module acquires the coal seam feature model constructed in real time and analyzes the key features in the coal seam feature model; The key features in the coal seam feature model are converted into input variables of a fuzzy logic system, and the fuzzy membership function of the cut-off path is calculated, as follows: In the formula, Represents the fuzzy membership degree of path p Indicates the path safety score. represents the path risk index, k represents the membership adjustment coefficient, and the initial planning parameters for generating the cut path are denoted as k.

[0011] Preferably, the path planning module, under the premise of satisfying spatial constraints, optimizes the truncation path to achieve multiple objectives. It solves the multi-objective optimization problem through non-dominated sorting genetic algorithm to generate a Pareto optimal solution set. From the Pareto optimal solution set, it selects the most suitable path based on the current working conditions. This is implemented as follows: In the formula, This represents the overall optimization weight of path p. This represents the coal mining efficiency factor. Indicates the stress coefficient of the equipment. This represents the safety-efficiency balance factor. This represents the efficiency stress balance factor, extracts key control parameters from the optimized path, converts the parameters into an instruction format recognizable by the coal mining machine control system, and prioritizes multiple control instructions.

[0012] Preferably, the collaborative support module receives control commands in real time, analyzes the key geological features in the commands, matches an adaptive support mode from a preset strategy library based on the geological analysis results, generates a collaborative command sequence for the support group, drives the hydraulic support group to execute commands, synchronously starts roof pressure sensor monitoring, collects roof subsidence and support force data in real time, compares them with preset safety thresholds, and feeds back the support effect data to the coal mining machine control system in real time.

[0013] Preferably, the attitude control module receives pitch and tilt angle data provided by the fuselage attitude sensor, synchronously parses the control commands generated by the path planning module, and determines the correction priority based on attitude deviation and cutting drag information. Based on the correction requirements, the difference in traction speed between the left and right tracks is calculated. The speed adjustment is proportional to the cutting resistance. The calculated left and right track speed commands are sent to the traction motor controller in real time, and the differential drive of the traction motor is started synchronously. The actual attitude is continuously monitored through the current and speed data fed back by the traction motor.

[0014] Preferably, the performance evaluation module collects key operational indicators from each subsystem in real time, obtains the coal seam feature model constructed in real time from the interface modeling module, extracts current geological condition parameters, maps the control parameters generated by the path planning module with the current geological conditions, identifies operational indicators that are significantly affected by specific geological conditions through data comparison, and optimizes parameters based on the identification results.

[0015] Preferably, the experience sharing module encapsulates the triplet of geological conditions, parameter combinations, and performance results generated by the performance evaluation module into a structured experience package. It receives the coal seam feature model of the current coal mining machine in real time and extracts key geological parameters. It performs similarity matching with historical experience packages. When the matching degree exceeds a preset threshold, it triggers an experience package push command and transmits the experience package to the target coal mining machine in real time via the mine industrial Ethernet. Emergency experience packages prioritize network bandwidth. After receiving the experience package, the target coal mining machine verifies the matching of its geological conditions with the current working face. When the coal mining machine detects geological conditions associated with an experience package, it triggers an early warning. When a new experience package is generated, it compares it with the existing experience library. If the new package covers the same geological conditions and has better performance, it replaces the old version. If the new package targets a new geological type, it is added as an independent entry.

[0016] Compared with the prior art, the beneficial effects of the present invention are: 1. This invention constructs a lightweight two-dimensional coal seam feature model by fusing multi-source heterogeneous data and dynamically annotating abnormal areas, significantly reducing computational complexity and shortening model construction time to the millisecond level to meet real-time control requirements. At the same time, the model retains key geological features, providing an intuitive and efficient decision-making basis for path planning. Through dynamic adjustment of the time decay factor and boundary priority coefficient, the model can adapt to coal seam abrupt change scenarios, avoiding the lag problem caused by static modeling and significantly improving the system's adaptability to complex geology. 2. This invention achieves dynamic planning and adaptive adjustment of cutting paths by using a coal seam characteristic model combined with fuzzy logic and multi-objective optimization algorithms. By introducing fuzzy membership functions, a balance is achieved between safety, efficiency, and equipment stress. In gangue-containing areas, low-hardness paths are preferentially selected to reduce energy consumption and wear. By verifying the matching between the path and spatial constraints in real time, the feasibility of the planned path is ensured, and equipment failures caused by mechanical interference are avoided, thereby improving coal mining efficiency and safety. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the structure of a coal mining machine body control system according to the present invention; Figure 2 The present invention provides an operational flow diagram of a coal mining machine body control system. Figure One ; Figure 3The present invention provides an operational flow diagram of a coal mining machine body control system. Figure Two ; Figure 4 The present invention provides an operational flow diagram of a coal mining machine body control system. Figure Three . Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only 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. Example

[0019] Please see Figures 1-4 As shown, the present invention provides a technical solution including a multi-dimensional perception module, an interface modeling module, a path planning module, a collaborative support module, a posture control module, an effectiveness evaluation module, and an experience sharing module; The multi-dimensional sensing module collects geological data of coal seams and surrounding rocks through an airborne sensor array; The interface modeling module constructs a coal seam feature model in real time based on the collected multi-source data. The path planning module makes fuzzy decisions on cutting paths based on the coal seam feature model constructed in real time to generate control commands. The collaborative support module enables the hydraulic support group to perform adaptive support actions based on the generated control commands. The attitude control module performs closed-loop adjustment of the traction speed based on the collected fuselage attitude data and the generated control commands. The performance evaluation module monitors system operating indicators and performs correlation matching between control parameters and geological conditions. The experience-sharing module publishes and issues warnings for control experience packages within the group based on the optimized parameters obtained after association matching.

[0020] In this embodiment, the multi-dimensional perception module is wirelessly connected to the interface modeling module, the interface modeling module is wirelessly connected to the path planning module, the path planning module is wirelessly connected to the collaborative support module, the collaborative support module is wirelessly connected to the attitude control module, the attitude control module is wirelessly connected to the performance evaluation module, and the performance evaluation module is wirelessly connected to the experience sharing module.

[0021] In this embodiment, the multi-dimensional sensing module is equipped with a high-precision ground-penetrating radar on the coal mining machine drum. It obtains information on coal seam thickness changes, interbedded gangue locations, and hardness distribution by analyzing electromagnetic wave reflection signals. A hyperspectral imager covering the visible to near-infrared band is installed on the coal mining machine body. It identifies the compositional differences between coal and gangue through spectral analysis. Vibration and acoustic sensors are embedded in key positions of the coal mining machine rocker arm and cutting section to monitor the vibration spectrum and sound characteristics during the cutting process in real time.

[0022] Inertial measurement units (IMUs) and tilt sensors are installed at key nodes of the coal mining machine to monitor the pitch, tilt, and yaw angles of the machine. A lidar is installed at the head of the coal mining machine to construct three-dimensional point cloud data of the working face environment, assisting in geological structure identification and obstacle detection. The collected raw data is preprocessed and denoised to remove noise points caused by equipment vibration, environmental interference, and other factors, thereby improving data quality.

[0023] In this embodiment, the interface modeling module receives the preprocessed data stream in real time and calculates the comprehensive geological characteristic index of the coal seam, which is implemented as follows: In the formula, Indicates the comprehensive geological characteristics index of the coal seam. This indicates the abrupt change in coal seam thickness. Indicates the reference coal seam thickness. This represents the reflectance of coal and rock at characteristic wavelengths in hyperspectral imaging. The reference reflectance of pure coal This represents the high-frequency vibration energy detected by the vibration sensor. Represents the reference vibration energy. This represents the dynamic weighting coefficient.

[0024] In this embodiment, the interface modeling module, based on the comprehensive geological characteristics of the coal seam, compresses them into a simplified two-dimensional feature map to construct a coal seam feature model, which is implemented as follows: In the formula, This represents the coal seam characteristic model at the current moment, including boundary lines and anomaly region information. This represents the coal seam characteristic model at the previous moment. Indicates the time decay factor. Indicates the boundary priority coefficient. This indicates a boundary update based on GCI. This indicates anomaly region annotation based on GCI.

[0025] Geological features are automatically labeled based on the coal seam feature model, continuous curves are drawn in real time, and abrupt thickness change points and abnormal areas are marked. The labeling results are correlated with the current cutting position.

[0026] In this embodiment, the path planning module acquires the coal seam feature model constructed in real time, including the coordinate sequence of the boundary lines of the coal seam roof and floor, key points of the hardness distribution heat map, the types and locations of marked abnormal areas, and analyzes the key features in the coal seam feature model.

[0027] Specifically, based on historical data, a set of cutting decision rules is constructed for different geological conditions: In stable coal seam areas: maintain the conventional cutting path, prioritizing efficiency; For coal seams containing interbedded gangue: prioritize paths with lower hardness to avoid directly cutting through the gangue; Fault impact zone: Plan detour routes to ensure the integrity of the top and bottom slabs; Coal seam uplift / downlift zone: Adjust drum height according to boundary line fluctuations; The weights of various decision rules are dynamically adjusted based on the GCI index value in the coal seam characteristic model. Specifically, the key features in the coal seam feature model are converted into input variables of a fuzzy logic system, and the fuzzy membership function of the cut-off path is calculated, which is implemented as follows: In the formula, Let represent the fuzzy membership degree of path p, and let represent the comprehensive score of the path's safety and economy. The path safety score is represented by the boundary line volatility and distance to anomaly regions in the coal seam characteristic model. denoted as the path risk index, denoted as the sum of gangue enrichment and the abrupt change rate of the top and bottom plates, and k represents the membership adjustment coefficient.

[0028] Specifically, the initial planning parameters for generating the cutting path are generated, including drum height, traction speed, and cutting angle. The planned path is verified to meet the spatial constraints of the fully mechanized mining equipment. If the planned path intersects with an abnormal area, the path is adjusted to avoid the abnormal area, and the path with lower hardness is selected first.

[0029] In this embodiment, the path planning module optimizes the truncation path to achieve multiple objectives while satisfying spatial constraints. It solves the multi-objective optimization problem using non-dominated sorting genetic algorithm to generate a Pareto optimal solution set. From this Pareto optimal solution set, the most suitable path is selected based on the current working conditions. This is implemented as follows: In the formula, This represents the overall optimization weight of path p. This represents the coal mining efficiency factor. Indicates the stress coefficient of the equipment. This represents the safety-efficiency balance factor. This represents the efficiency stress balance factor, extracts key control parameters from the optimized path, converts the parameters into an instruction format recognizable by the coal mining machine control system, and prioritizes multiple control instructions.

[0030] In this embodiment, the collaborative support module receives control commands in real time, analyzes the key geological features in the commands, and determines the urgency of the support requirements.

[0031] Specifically, based on the geological analysis results, an adaptive support mode is matched from a preset strategy library: If it is predicted that the vehicle will enter the fracture zone, the belt pressure shifting strategy will be triggered. If the flatness data of the top plate is abnormal after cutting, activate the flatness fine-tuning strategy; Specifically, a coordinated instruction sequence is generated for the support group, which drives the hydraulic support group to execute the instructions. Simultaneously, the roof pressure sensor is activated to monitor and collect the roof subsidence and support stress data in real time. The data is compared with the preset safety threshold, and the support effect data is fed back to the coal mining machine control system in real time.

[0032] In this embodiment, the attitude control module receives pitch and tilt angle data provided by the fuselage attitude sensor, synchronously analyzes the control commands generated by the path planning module, focuses on analyzing the deviation between the current fuselage attitude and the target attitude, and determines the correction priority based on the attitude deviation and cutting drag information. If the fuselage tilts downwards significantly and the cutting resistance increases, prioritize initiating the bottom-biting correction mechanism. If the fuselage shifts laterally, initiate lateral correction to prevent it from veering off course. Based on the correction requirements, the difference in traction speed between the left and right tracks is calculated. The speed adjustment is proportional to the cutting resistance. The calculated left and right track speed commands are sent to the traction motor controller in real time, and the differential drive of the traction motor is started synchronously. The actual attitude is continuously monitored through the current and speed data fed back by the traction motor.

[0033] In this embodiment, the performance evaluation module collects key operating indicators from each subsystem in real time, obtains the coal seam feature model constructed in real time from the interface modeling module, extracts the current geological condition parameters, maps the control parameters generated by the path planning module with the current geological conditions, identifies that the operating indicators are significantly affected by specific geological conditions or control parameters through data comparison, and optimizes the parameters based on the identification results.

[0034] In this embodiment, the experience sharing module encapsulates the triplet of geological conditions, parameter combinations, and performance results generated by the performance evaluation module into a structured experience package. It receives the coal seam feature model of the current coal mining machine in real time, extracts key geological parameters, and performs similarity matching with historical experience packages. When the matching degree exceeds a preset threshold, it triggers an experience package push instruction.

[0035] Specifically, experience packages are transmitted to the target coal mining machine in real time via 5G or industrial Ethernet in the mine. Emergency experience packages take priority in using network bandwidth. After receiving the experience package, the target coal mining machine verifies the compatibility of its geological conditions with the current working face. When the coal mining machine detects geological conditions associated with the experience package, it triggers an early warning. When a new experience package is generated, it is compared with the existing experience library. If the new package covers the same geological conditions and has better results, it replaces the old version. If the new package is for a new geological type, it is added as an independent entry.

[0036] Working principle: By deploying high-precision ground-penetrating radar, hyperspectral imager, vibration and acoustic sensors, inertial measurement units, tilt sensors, and lidar in key parts such as the coal mining machine drum, body, rocker arm, and head, real-time data on coal seam thickness changes, interbedded rock distribution, coal and rock composition differences, cutting vibration spectrum, machine posture, and three-dimensional environmental data of the working face are collected; preprocessing algorithms are used to remove equipment vibration and environmental noise interference, and high-quality data streams are extracted. By receiving preprocessed multi-source data, and integrating features such as abrupt changes in coal seam thickness, hyperspectral reflectance, and vibration energy, a comprehensive geological characteristic index of the coal seam is calculated. Based on GCI, the coal seam boundary line and anomalous areas are dynamically updated, a lightweight two-dimensional feature model is constructed, and the geological features are labeled in real-time with their association with the current cutting position. The coal seam feature model provided by the interface modeling module is analyzed, and a cutting decision rule base is constructed by combining historical geological data. Geological features are transformed into path safety scores and risk indices through a fuzzy logic system, the path membership function is calculated, and initial cutting parameters (drum height, traction speed) are generated. After verifying path space constraints, the Pareto optimal solution set is generated through multi-objective optimization, a path suitable for the current working conditions is selected, and control commands are output. Control commands from the path planning module are received, geological features are analyzed, an adaptive support mode is matched from a preset strategy library, a hydraulic support group collaborative command sequence is generated, the supports are driven to adjust pressure and position, and roof subsidence and support stress data are simultaneously monitored and fed back to the coal mining machine control system. The inertial measurement unit receives... The system analyzes the deviation between the current attitude and the target attitude based on the tilt sensor's body attitude data and path planning commands. It prioritizes corrections based on the deviation and cutting resistance, calculates the difference in traction speed between the left and right tracks, and adjusts the body attitude via differential drive. It continuously monitors traction motor feedback data, dynamically corrects speed commands to maintain stable movement, and collects real-time operating indicators from subsystems such as the coal mining machine, hydraulic supports, and traction motors. Combined with geological condition parameters from the interface modeling module, it establishes a mapping relationship between control parameters and geological features. Through data comparison, it identifies key factors affecting operating indicators due to specific geological conditions or parameters and generates optimization suggestions. It encapsulates the geological conditions, parameter combinations, and performance results triplets generated by the performance evaluation module into structured experience packages, analyzes the current coal seam characteristic model of the coal mining machine in real-time, and extracts key geological parameters. It performs similarity matching with historical experience packages and pushes highly matched experience packages to the target equipment. Emergency experience packages are transmitted first; after the coal mining machine verifies the matching, it loads the parameter combinations. New experience packages are compared, replaced, or added to the experience library to achieve collective intelligent collaboration.

[0037] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their likenesses.

[0038] The present invention and its embodiments have been described above. This description is not restrictive, and the accompanying drawings are only one embodiment of the present invention; the actual structure is not limited thereto. In conclusion, if those skilled in the art are inspired by this description and design similar structures and embodiments without departing from the spirit of the invention, such designs should fall within the protection scope of the present invention.

Claims

1. A coal mining machine body control system, characterized in that: It includes a multi-dimensional perception module, an interface modeling module, a path planning module, a collaborative support module, a posture control module, a performance evaluation module, and an experience sharing module; The multi-dimensional sensing module collects geological data of coal seams and surrounding rocks through an airborne sensor array; The interface modeling module constructs a coal seam feature model in real time based on the collected multi-source data. The path planning module makes fuzzy decisions on cutting paths based on the coal seam feature model constructed in real time to generate control commands. The collaborative support module enables the hydraulic support group to perform adaptive support actions based on the generated control commands. The attitude control module performs closed-loop adjustment of the traction speed based on the collected fuselage attitude data and the generated control commands. The performance evaluation module monitors system operating indicators and performs correlation matching between control parameters and geological conditions. The experience-sharing module publishes and issues warnings for control experience packages within the group based on the optimized parameters obtained after association matching.

2. The coal mining machine body control system according to claim 1, characterized in that: The multi-dimensional sensing module includes a high-precision ground-penetrating radar installed on the coal mining machine drum to obtain information on coal seam thickness changes, interbedded rock locations, and hardness distribution by analyzing electromagnetic wave reflection signals; a hyperspectral imager installed on the coal mining machine body; vibration and acoustic sensors embedded in key positions of the coal mining machine rocker arm and cutting section to monitor the vibration spectrum and sound characteristics during the cutting process in real time; inertial measurement units (IMUs) and tilt sensors installed at key nodes of the coal mining machine body to monitor the pitch, tilt, and heading angles of the machine body; and a lidar installed at the head of the coal mining machine to preprocess the collected raw data.

3. The coal mining machine body control system according to claim 1, characterized in that: The interface modeling module receives the preprocessed data stream in real time and calculates the comprehensive geological characteristic index of the coal seam, as follows: In the formula, Indicates the comprehensive geological characteristics index of the coal seam. This indicates the abrupt change in coal seam thickness. Indicates the reference coal seam thickness. This represents the reflectance of coal and rock at characteristic wavelengths in hyperspectral imaging. The reference reflectance of pure coal This represents the high-frequency vibration energy detected by the vibration sensor. Represents the reference vibration energy. This represents the dynamic weighting coefficient.

4. The coal mining machine body control system according to claim 3, characterized in that: The interface modeling module, based on the comprehensive geological characteristics of the coal seam, compresses them into a simplified two-dimensional feature map to construct a coal seam feature model, which is implemented as follows: In the formula, This represents the coal seam characteristic model at the current moment. This represents the coal seam characteristic model at the previous moment. Indicates the time decay factor. Indicates the boundary priority coefficient. This indicates a boundary update based on GCI. It represents the annotation of abnormal areas based on GCI; it automatically annotates geological features based on coal seam feature models, draws continuous curves in real time, marks thickness abrupt change points and abnormal area markers, and the annotation results are associated with the current cutting position.

5. A coal mining machine body control system according to claim 1, characterized in that: The path planning module acquires the real-time constructed coal seam feature model, analyzes the key features in the coal seam feature model, converts the key features in the coal seam feature model into input variables of the fuzzy logic system, and calculates the fuzzy membership function of the truncation path, as follows: In the formula, Represents the fuzzy membership degree of path p. Indicates the path safety score. represents the path risk index, k represents the membership adjustment coefficient, and the initial planning parameters for generating the cut path are denoted as k.

6. A coal mining machine body control system according to claim 5, characterized in that: The path planning module optimizes the truncation path to achieve multiple objectives while satisfying spatial constraints. It solves the multi-objective optimization problem using non-dominated sorting genetic algorithm to generate a Pareto optimal solution set. From this set, the most suitable path is selected based on the current working conditions. This is implemented as follows: In the formula, This represents the overall optimization weight of path p. This represents the coal mining efficiency factor. Indicates the stress coefficient of the equipment. This represents the safety-efficiency balance factor. This represents the efficiency stress balance factor, extracts key control parameters from the optimized path, converts the parameters into an instruction format recognizable by the coal mining machine control system, and prioritizes multiple control instructions.

7. The coal mining machine body control system according to claim 1, characterized in that: The collaborative support module receives control commands in real time, analyzes the key geological features in the commands, matches the adaptive support mode from the preset strategy library based on the geological analysis results, generates a collaborative command sequence for the support group, drives the hydraulic support group to execute the commands, and simultaneously starts the roof pressure sensor to monitor and collect the roof subsidence and support force data in real time. The data is compared with the preset safety threshold, and the support effect data is fed back to the coal mining machine control system in real time.

8. A coal mining machine body control system according to claim 1, characterized in that: The attitude control module receives pitch and tilt angle data from the fuselage attitude sensor, synchronously analyzes the control commands generated by the path planning module, and determines the correction priority based on attitude deviation and cutting resistance information. According to the correction requirements, it calculates the difference in traction speed between the left and right tracks. The speed adjustment amount is proportional to the cutting resistance. The calculated left and right track speed commands are sent to the traction motor controller in real time, and the differential drive of the traction motor is started synchronously. The actual attitude is continuously monitored through the current and speed data fed back by the traction motor.

9. A coal mining machine body control system according to claim 1, characterized in that: The performance evaluation module collects key operational indicators from each subsystem in real time, obtains the coal seam feature model constructed in real time from the interface modeling module, extracts current geological condition parameters, maps the control parameters generated by the path planning module with the current geological conditions, identifies operational indicators that are significantly affected by specific geological conditions through data comparison, and optimizes parameters based on the identification results.

10. A coal mining machine body control system according to claim 1, characterized in that: The experience sharing module encapsulates the triplet of geological conditions, parameter combinations, and performance results generated by the performance evaluation module into a structured experience package. It receives the coal seam feature model of the current mining machine in real time and extracts key geological parameters. It performs similarity matching with historical experience packages. When the matching degree exceeds a preset threshold, an experience package push command is triggered, and the experience package is transmitted to the target mining machine in real time via the mine industrial Ethernet. Emergency experience packages prioritize network bandwidth. After receiving the experience package, the target mining machine verifies the matching of its geological conditions with the current working face. When the mining machine detects geological conditions associated with an experience package, an early warning is triggered. When a new experience package is generated, it is compared with the existing experience library. If the new package covers the same geological conditions and has better performance, the old version is replaced; if the new package targets a new geological type, it is added as an independent entry.

Images