Linkage control method for communication between mining belt conveying system and working face

Abstract

The invention discloses a linkage control method for communication between a mining belt conveying system and a working face, and belongs to the field of intelligent mining, and the control method comprises the following specific steps: I, collecting and preprocessing multi-source heterogeneous data of the belt conveying system in real time, and constructing a real-time operation situation map based on the preprocessed multi-source heterogeneous data; according to the method, the problem that transportation control and communication states are separated in a traditional system is solved, the overall collaboration and response consistency of the system are improved, risk pre-evaluation is achieved, the probability of systematic accidents caused by improper control strategies is remarkably reduced, the anti-interference capacity and continuous operation capacity of the belt conveying system under extreme working conditions are improved, and the safety of the belt conveying system is improved. According to the method, control parameters and linkage logic can be finely optimized according to different working conditions, extensive or fixed logic control is avoided, the pertinence of a control strategy and engineering implementation are improved, operation and maintenance personnel can understand system behaviors easily, and the safety management level is improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent mining, and in particular to a linkage control method for communication between a mining belt conveyor system and the working face. Background Technology

[0002] As coal mine production moves towards intelligent, unmanned, and minimally staffed operations, underground belt conveyor systems have become a key hub connecting the coal mining face with the surface production system. Their operational status directly affects the safety, continuity, and economy of coal mine production.

[0003] Existing mining belt conveyor systems typically employ centralized control, with each piece of equipment relying primarily on fixed logic or simple interlocking relationships for coordinated operation. However, the level of integration with the face communication system is low, making it difficult to fully detect changes in face conditions and communication anomalies. Under complex operating conditions, factors such as belt load fluctuations, changes in equipment operating status, and unstable communication links can easily lead to delayed control command responses, insufficient system coordination, and even safety hazards. Furthermore, traditional control systems generally rely on human experience to handle sudden failures, lacking the ability to predict the evolution of faults and failing to verify safety and reliability before issuing control commands, thus hindering further improvements in mine intelligence. Therefore, inventing a linkage control method for mining belt conveyor systems and face communication is of paramount importance.

[0004] Existing methods for linking communication between mine belt conveyor systems and the working face generally suffer from a disconnect between transport control and communication status. This reduces the overall system coordination and response consistency, hinders proactive risk assessment, and significantly increases the probability of systemic accidents due to inappropriate control strategies. Furthermore, belt conveyor systems exhibit poor anti-interference capabilities and continuous operation under extreme conditions, and cannot finely optimize control parameters and linkage logic for different working conditions, resulting in coarse-grained or fixed-logic control. This reduces the specificity and engineering feasibility of control strategies and makes it difficult for maintenance personnel to understand system behavior. Therefore, we propose a new method for linking communication between mine belt conveyor systems and the working face. Summary of the Invention

[0005] The purpose of this invention is to address the deficiencies in the existing technology by proposing a linkage control method for communication between a mining belt conveyor system and the working face.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: A linkage control method for communication between a mining belt conveyor system and the working face, the specific steps of which are as follows: Ⅰ. Collect and preprocess multi-source heterogeneous data of the belt conveyor system in real time, and construct a real-time operation status map based on the preprocessed multi-source heterogeneous data; II. Based on the real-time data of the belt conveyor system, construct and synchronously update the transportation simulation model, and conduct simulation analysis on various fault scenarios and control strategies in a virtual scenario. III. Based on the simulation analysis results, optimize the control strategy, and at the same time, combine the local operating status of each equipment node along the line to establish a linkage control strategy that adapts to the current working conditions. IV. After the linkage control strategy is issued, each equipment node along the line makes local judgments based on its own sensing information and negotiates control with adjacent nodes through the local communication network; V. When operators issue control commands via voice or communication terminals, the command content is parsed and compared and verified with the current operating status and safety logic; VI. Real-time feedback on strategy execution effectiveness: When a real failure occurs in the transportation system, an emergency self-healing plan is generated by combining the fault feature library with historical simulation data.

[0007] As a further aspect of the present invention, the specific steps for constructing a real-time operational status map based on preprocessed multi-source heterogeneous data in step I are as follows: S1.1: Based on the highest and lowest timestamps of the collected multi-source heterogeneous data, and with the lowest timestamp as the lower limit and the highest timestamp as the upper limit, establish a global time interval, and construct a main time axis based on the global time interval. Then, detect the sampling time point on the main time axis that is closest to the sampling timestamp of each device node. S1.2: Calculate the time deviation between the sampling timestamp of the multi-source heterogeneous data and the corresponding sampling time point. If the time deviation is less than the preset maximum time deviation threshold, the sampling time of the corresponding multi-source heterogeneous data is mapped to the sampling time point. Otherwise, the heterogeneous data at the misaligned sampling time point is marked as a missing value. S1.3: Establish a sliding time window of a preset size for each heterogeneous data, then move the sliding time window step by step according to the set time step, and calculate the mean and standard deviation of each heterogeneous data in the sliding time window after each move. Based on the preset anomaly judgment rules, determine whether the water quality data at the current sampling time point is abnormal data. If the rules are met, the sampling time point is marked as abnormal and regarded as a missing value. S1.4: During each round of the sliding time window, median filtering is used to remove impulse noise from the heterogeneous data, linear interpolation is used to fill in missing values, and then the heterogeneous data are normalized to be unified into the same range. The preprocessed heterogeneous data are combined into the state characteristics of the belt conveyor system. Then, the historical belt conveyor system state characteristics are weighted and fused based on the exponential decay weight mechanism to generate the corresponding comprehensive state index. S1.5: Map the generated comprehensive status indicators to a predefined multi-dimensional situation space, take each sub-unit of the belt conveyor system as a node, take the physical or logical relationship as the edge between the corresponding nodes, and associate a set of corresponding status attributes with each type of node based on the corresponding comprehensive status indicators to form a complete operation situation diagram. After each data collection cycle is completed, update the attributes of each node in the operation situation diagram based on the newly generated comprehensive status indicators.

[0008] As a further aspect of the present invention, the specific manifestation of the state characteristics of the belt conveyor system described in S1.4 is as follows:

[0009] in, Representing time Characteristics of the belt conveyor system at any time; Representing time The current total load on the entire belt; Representing time Maximum deviation of motor current; Representing time Online rate of communication equipment; Representing time Current operating speed of the coal mining machine; Representing time The position coordinates of the coal mining machine along the working face; Representing time Current coal bunker level; The specific calculation formula for the comprehensive status index mentioned in S1.4 is as follows:

[0010] In the formula, Representing time Comprehensive status indicators at the time; Represents the attenuation coefficient; This represents the length of the integration time window.

[0011] As a further aspect of the present invention, the specific steps for constructing and synchronously updating the transportation simulation model in step II are as follows: S2.1: Deconstruct the belt conveyor system and its associated communication equipment, assign a unique identifier to each deconstructed unit, construct a geometric entity model of the belt conveyor system in a 3D modeling platform, and match corresponding spatial coordinates, size parameters, row parameter interfaces, state variable sets and behavioral constraint rules for each unit in the geometric entity model of the belt conveyor system based on the manufacturer's specifications. S2.2: Define the connection relationship and material flow direction between each device in the logic layer, establish a logical topology graph composed of nodes and directed edges, and then establish a corresponding dynamic behavior model based on dynamics and transmission characteristics to address the driving force, resistance and load effects during the operation of the belt conveyor system. S2.3: The real-time comprehensive status indicators reflected in the operation status diagram are broken down into a set of status parameters of the dynamic behavior model of the belt conveyor system, and the status parameter set is mapped to the corresponding twin parameter set. After the mapping is completed, the latest comprehensive status indicators are input into the dynamic behavior model of each unit of the belt conveyor system according to the prediction collection cycle. S2.4: After each data collection cycle, the state variables and model parameters of the dynamic behavior model of each unit of the belt conveyor system are updated and corrected. The deviation between the output of each dynamic behavior model and the feedback of the physical system is compared in real time. If the deviation exceeds the preset allowable range, the parameter self-correction mechanism is automatically triggered to adjust the internal parameters of the model. S2.5: After the states of each dynamic behavior model are synchronized and verified, the states of all objects are combined into a complete transportation simulation model, and the overall operating status of the belt conveyor system and communication system is reflected in real time through this transportation simulation model.

[0012] As a further aspect of the present invention, the specific manifestation of the dynamic behavior model described in S2.2 is as follows:

[0013] In the formula, Representing the The rate of change of a state response quantity with respect to time; Representing the The inherent dynamic characteristic coefficients of a virtual object; Representing the The state response quantity of a virtual object; Representing the External input influence coefficient of a virtual object; Representative effect on the first The control or disturbance input of a virtual object.

[0014] As a further embodiment of the present invention, the geometric entity model in S2.1 includes functional units such as a driving unit, a bearing unit, a tensioning unit, and a communication node unit.

[0015] As a further aspect of the present invention, the specific steps for simulating and analyzing various fault scenarios and control strategies in step II are as follows: S3.1: Based on the current operating status and control objectives, generate multiple candidate linkage control strategies. Each candidate linkage control strategy contains different combinations of control parameters, execution order, and linkage logic. Then, input each candidate control strategy into the transportation simulation model to drive the transportation simulation model to run according to the corresponding control logic. S3.2: During the simulation, the transportation simulation model calculates the evolution trajectory of the belt conveyor system state in real time, presets three typical fault modes, and establishes parameterized injection rules for each type. Then, a unique fault identifier is used to mark each fault, and a set of corresponding fault triggering condition functions are associated with each fault mode. When multiple faults are triggered simultaneously during the simulation, the running data of the transportation simulation model is monitored in real time, and the state perturbation equation for multi-fault parallel simulation is constructed. S3.3: Start multiple independent simulations for each candidate control strategy. In each simulation, randomly select the fault type, occurrence location, start time and duration, and generate a set of fault scenarios. At the same time, record the system state trajectory and performance index sequence for each scenario. Then, based on the state trajectory of multiple independent simulations, calculate the robustness score of each candidate control strategy using weighted failure probability. S3.4: Perform time series clustering on the performance index sequences of each simulated state trajectory to obtain multiple typical response clusters, and calculate the average risk characteristics of each response cluster. If the average risk characteristics are higher than the preset risk threshold, mark the fault combination corresponding to the cluster as a "high-risk mode", and analyze the impact propagation path of each identified high-risk mode in the belt conveyor system. S3.5: During the statistical simulation process, functional interruption, performance degradation or switching events caused by the influence of candidate control strategies or faults are recorded, and the continuity evaluation index of each candidate control strategy is calculated. The evaluation results of each candidate control strategy in terms of average risk characteristics, robustness score and continuity evaluation index are comprehensively calculated to form a comprehensive simulation evaluation result. S3.6: Sort the candidate control strategies from high to low according to the comprehensive simulation evaluation results, and take the candidate control strategies with comprehensive simulation evaluation results higher than the preset threshold as the optional linkage control schemes under multi-fault scenarios.

[0016] As a further aspect of the present invention, the typical failure modes described in S3.2 specifically include sensor failure, communication link interruption, and actuator jamming; Among them, the sensor failure injection rule is to set the output of a specified virtual sensor to a constant value, zero value, or random drift. Communication link interruption: Cuts off data exchange between a node in the twin and other nodes within a preset time period; Actuator jamming: The angular velocity of a motor is forcibly locked to a constant while ignoring the input.

[0017] As a further aspect of the present invention, the specific steps for optimizing the control strategy based on the simulation analysis results in step III are as follows: S4.1: After completing multi-strategy simulation and risk assessment, the multiple sets of evaluation data generated by each selected linkage control scheme under various fault scenarios are reorganized according to the control target dimension. At the same time, the constraints that need to be met for control optimization under the current operating condition are determined, and each constraint is converted into a corresponding mathematical inequality. The constraints include equipment physical limits, communication reliability, and linkage logic safety requirements. S4.2: Calculate the sensitivity index of each parameter in each candidate control strategy, and mark the parameters with sensitivity indices higher than the preset threshold as key parameters. Rearrange the execution order of control commands according to the simulation results, and calculate the comprehensive risk cost of each adjusted control strategy. If the comprehensive risk cost is higher than the preset threshold, adjust the key parameters and the order of control commands. S4.3: After the initial optimization of the instruction sequence and parameter range, analyze whether there are logical conflicts, redundant triggers or missing dependencies between different control actions in each linkage control strategy. If there are logical conflicts, correct them according to the simulation feedback. After completing parameter adjustment, sequence rearrangement and logical correction, the system integrates the optimization results to form the final optimized control strategy.

[0018] Compared with the prior art, the beneficial effects of the present invention are as follows: The linkage control method for communication between the mine's belt conveyor system and the working face is based on collected multi-source heterogeneous data. It extracts the minimum and maximum timestamps of each data point, constructs a global time interval, and generates a main time axis. Time alignment of the multi-source data is achieved through time deviation judgment, and data that cannot be aligned is marked as missing values. Subsequently, a sliding time window is established for various types of heterogeneous data. Statistical features within the window are calculated as the time step increases. Anomaly detection rules are used to identify abnormal data, and noise suppression and missing value repair are completed through median filtering and linear interpolation. The processed data is then normalized to form a dataset with a unified scale.

[0019] Based on this, the preprocessed multi-source data is combined into the state characteristics of the belt conveyor system, and an exponential decay weighting mechanism is used to fuse historical state characteristics to generate comprehensive state indicators. Each comprehensive state indicator is mapped to a multi-dimensional situation space, with system sub-units as nodes and physical or logical relationships as edges, constructing an operational situation diagram. Node attributes are dynamically updated according to the data acquisition cycle. Then, the belt conveyor system and communication equipment are structurally deconstructed to construct a three-dimensional geometric entity model and a logical topology model, establishing a dynamic behavior model. The operational situation indicators are mapped to twin parameters. Simultaneously, multiple candidate linkage control strategies are generated based on the transportation simulation model, and multiple types of parameterized faults are introduced into the transportation simulation model for parallel simulation. The risk, robustness, and continuity of each strategy are evaluated through multiple random fault scenarios. The simulation results are comprehensively evaluated and ranked to select feasible strategies, and these strategies are then combined with constraints. Parameter sensitivity analysis, instruction sequence optimization, and logic consistency correction form the final optimized linkage control strategy for safe, stable, and continuous operation under multiple fault scenarios. This overcomes the problem of disconnect between transportation control and communication status in traditional systems, improves the overall system coordination and response consistency, enables proactive risk assessment, significantly reduces the probability of systemic accidents caused by inappropriate control strategies, and enhances the anti-interference capability and continuous operation capability of belt conveyor systems under extreme conditions. It can finely optimize control parameters and linkage logic for different operating conditions, avoids coarse or fixed logic control, improves the pertinence and engineering feasibility of control strategies, and helps maintenance personnel understand system behavior and improve safety management. Attached Figure Description

[0020] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof.

[0021] Figure 1 This is a flowchart of a linkage control method for communication between a mining belt conveyor system and the working face, as proposed in this invention. Figure 2 A schematic diagram illustrating the establishment and updating of a transportation simulation model for a linkage control method between a mine belt conveyor system and the working face, as proposed in this invention. Figure 3 This is a simulation analysis diagram of a linkage control method for communication between a mining belt conveyor system and the working face, as proposed in this invention. Detailed Implementation

[0022] Example, refer to Figure 1-3 A linkage control method for communication between a mining belt conveyor system and the working face, the specific steps of which are as follows: Real-time acquisition and preprocessing of multi-source heterogeneous data from the belt conveyor system, and construction of a real-time operational status map based on the preprocessed multi-source heterogeneous data.

[0023] Specifically, based on the highest and lowest timestamps of the collected multi-source heterogeneous data, and with the lowest timestamp as the lower limit and the highest timestamp as the upper limit, a global time interval is established, and a main time axis is constructed based on the global time interval. Then, the sampling timestamp of each device node is detected as being closest to the sampling time point on the main time axis. The time deviation between the multi-source heterogeneous data sampling timestamp and the corresponding sampling time point is calculated. If the time deviation is less than a preset maximum time deviation threshold, the corresponding multi-source heterogeneous data sampling time is mapped to that sampling time point; otherwise, the heterogeneous data at the misaligned sampling time point is marked as a missing value. A sliding time window of a preset size is established for each heterogeneous data point. Then, the sliding time window is gradually moved according to a set time step, and the mean and standard deviation of each heterogeneous data point within the sliding time window after each movement are calculated. Based on preset anomaly judgment rules, it is determined whether the water quality data at the current sampling time point is an anomaly. According to the rules, if the sampling time point is satisfied, it is marked as an anomaly and considered as a missing value. During each round of the sliding time window, median filtering is used to remove impulse noise from the heterogeneous data, linear interpolation is used to fill in the missing values, and then the heterogeneous data are normalized to be unified into the same range. The preprocessed heterogeneous data are combined into the state features of the belt conveyor system. Then, the historical belt conveyor system state features are weighted and fused based on the exponential decay weight mechanism to generate corresponding comprehensive state indicators. The generated comprehensive state indicators are mapped to a predefined multi-dimensional situation space. Each sub-unit of the belt conveyor system is used as a node, and the physical or logical relationship is used as the edge between the corresponding nodes. Based on the corresponding comprehensive state indicators, a set of corresponding state attribute sets is associated with each type of node to form a complete operation situation diagram. After each data collection cycle is completed, the attributes of each node in the operation situation diagram are updated based on the newly generated comprehensive state indicators.

[0024] It should be noted that the specific manifestations of the state characteristics of a belt conveyor system are as follows:

[0025] in, Representing time Characteristics of the belt conveyor system at any time; Representing time The current total load on the entire belt; Representing time Maximum deviation of motor current; Representing time Online rate of communication equipment; Representing time Current operating speed of the coal mining machine; Representing time The position coordinates of the coal mining machine along the working face; Representing time Current coal bunker level; The specific calculation formula for the comprehensive status index is as follows:

[0026] In the formula, Representing time Comprehensive status indicators at the time; Represents the attenuation coefficient; This represents the length of the integration time window.

[0027] Based on real-time data from the belt conveyor system, a transportation simulation model is constructed and updated synchronously. In a virtual scenario, simulation analysis is performed on various fault scenarios and control strategies.

[0028] Specifically, the belt conveyor system and its associated communication equipment are structurally deconstructed, and each deconstructed unit is assigned a unique identifier. A geometric entity model of the belt conveyor system is constructed in a 3D modeling platform. Based on the manufacturer's specifications, corresponding spatial coordinates, dimensional parameters, line parameter interfaces, state variable sets, and behavioral constraint rules are matched to each unit in the geometric entity model of the belt conveyor system. The connection relationships between the devices and the material flow direction are defined at the logical layer, and a logical topology graph composed of nodes and directed edges is established. Then, based on dynamics and transmission characteristics, corresponding dynamic behavior models are established for the driving force, resistance, and load effects during the operation of the belt conveyor system. The real-time comprehensive status indicators reflected in the operation status diagram are decomposed into changes in the dynamic behavior model of the belt conveyor system. A situational parameter set is generated and mapped to a corresponding twin parameter set. After mapping, the latest comprehensive status indicators are input into the dynamic behavior models of each unit of the belt conveyor system according to the predicted acquisition cycle. After each acquisition cycle, the state variables and model parameters of the dynamic behavior models of each unit of the belt conveyor system are updated and corrected. The deviation between the output of each dynamic behavior model and the feedback of the physical system is compared in real time. If the deviation exceeds the preset allowable range, the parameter self-correction mechanism is automatically triggered to adjust the internal parameters of the model. After the states of each dynamic behavior model are synchronized and verified, the states of all objects are combined into a complete transportation simulation model, which reflects the overall operating status of the belt conveyor system and the communication system in real time.

[0029] Specifically, based on the current operational status and control objectives, multiple candidate linkage control strategies are generated. Each candidate linkage control strategy includes different combinations of control parameters, execution order, and linkage logic. These candidate control strategies are then input into the transportation simulation model, driving the model to operate according to the corresponding control logic. During the simulation, the transportation simulation model calculates the evolution trajectory of the belt conveyor system's state in real time. Three typical fault modes are preset, and parameterized injection rules are established for each mode. Each fault is then labeled with a unique fault identifier, and a set of corresponding fault triggering condition functions is associated with each fault mode. When multiple faults are triggered simultaneously during the simulation, the operational data of the transportation simulation model is monitored in real time. State disturbance equations for multi-fault parallel simulation are constructed, and multiple independent simulations are initiated for each candidate control strategy. Each simulation randomly selects the fault type, location, start time, and duration, generating a set of fault scenarios. Simultaneously, the system state trajectory and performance index sequence for each scenario are recorded. Subsequently, based on the state trajectories from multiple independent simulations, the robustness score of each candidate control strategy was calculated using a weighted failure probability. Time series clustering was performed on the performance index sequences of each simulated state trajectory to obtain multiple typical response clusters, and the average risk characteristics of each response cluster were calculated. If the average risk characteristics were higher than a preset risk threshold, the fault combination corresponding to the cluster was marked as a "high-risk mode." The propagation path of the identified high-risk modes in the belt conveyor system was analyzed, and the functional interruption, performance degradation, or switching events caused by the candidate control strategies or faults during the simulation were statistically analyzed. The continuity evaluation index of each candidate control strategy was calculated, and the evaluation results of each candidate control strategy in terms of average risk characteristics, robustness score, and continuity evaluation index were comprehensively calculated to form a comprehensive simulation evaluation result. The candidate control strategies were sorted from high to low according to the comprehensive simulation evaluation results, and the candidate control strategies with comprehensive simulation evaluation results higher than the preset threshold were selected as optional linkage control schemes in multi-fault scenarios.

[0030] In addition, it should be noted that the geometric solid model includes functional units such as driving unit, bearing unit, tensioning unit, and communication node unit; Typical failure modes include sensor failure, communication link interruption, and actuator jamming. Among them, the sensor failure injection rule is to set the output of a specified virtual sensor to a constant value, zero value, or random drift. Communication link interruption: Cuts off data exchange between a node in the twin and other nodes within a preset time period; Actuator jamming: Forcibly locking the angular velocity of a motor to a constant while ignoring the input; The specific manifestations of the dynamic behavior model are as follows:

[0031] In the formula, Representing the The rate of change of a state response quantity with respect to time; Representing the The inherent dynamic characteristic coefficients of a virtual object; Representing the The state response quantity of a virtual object; Representing the External input influence coefficient of a virtual object; Representative effect on the first The control or disturbance input of a virtual object.

[0032] Based on the simulation analysis results, the control strategy is optimized, and a linkage control strategy adapted to the current working conditions is established by combining the local operating status of each equipment node along the line.

[0033] Specifically, after completing multi-strategy simulation and risk assessment, the multiple sets of evaluation data generated by the selected linkage control schemes under various fault scenarios are reorganized according to the control objective dimension. At the same time, the constraints that need to be met for control optimization under the current operating condition are determined, and each constraint is converted into a corresponding mathematical inequality. The constraints include equipment physical limits, communication reliability, and linkage logic safety requirements. The sensitivity index of each parameter in each candidate control strategy is calculated, and parameters with sensitivity indices higher than a preset threshold are marked as key parameters. The execution order of control commands is rearranged according to the simulation results, and the comprehensive risk cost of each adjusted control strategy is calculated. If the comprehensive risk cost is higher than the preset threshold, the key parameters and the order of control commands are adjusted. After the initial optimization of the command order and parameter range, it is analyzed whether there are logical conflicts, redundant triggers, or missing dependencies between different control actions in each linkage control strategy. If logical conflicts exist, they are corrected according to simulation feedback. After completing parameter adjustment, order rearrangement, and logical correction, the system integrates the optimization results to form the final optimized control strategy.

[0034] After the linkage control strategy is issued, each equipment node along the line makes local judgments based on its own sensing information and negotiates control with neighboring nodes through the local communication network.

[0035] When operators issue control commands via voice or communication terminals, the command content is parsed and compared and verified with the current operating status and safety logic.

[0036] The system provides real-time feedback on the effectiveness of strategy execution. When a real failure occurs in the transportation system, it generates an emergency self-healing plan by combining the fault feature library with historical simulation data.

[0037] The above description is merely an example and illustration of the structure of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the structure of the invention or exceed the scope defined in the claims, all of which should fall within the protection scope of the present invention.

Claims

1. A linkage control method for communication between a mining belt conveyor system and the working face, characterized in that, The specific steps of this control method are as follows: Ⅰ. Collect and preprocess multi-source heterogeneous data of the belt conveyor system in real time, and construct a real-time operation status map based on the preprocessed multi-source heterogeneous data; II. Based on the real-time data of the belt conveyor system, construct and synchronously update the transportation simulation model, and conduct simulation analysis on various fault scenarios and control strategies in a virtual scenario. III. Based on the simulation analysis results, optimize the control strategy, and at the same time, combine the local operating status of each equipment node along the line to establish a linkage control strategy that adapts to the current working conditions. IV. After the linkage control strategy is issued, each equipment node along the line makes local judgments based on its own sensing information and negotiates control with adjacent nodes through the local communication network; V. When operators issue control commands via voice or communication terminals, the command content is parsed and compared and verified with the current operating status and safety logic; VI. When a real failure occurs in the transportation system, an emergency self-healing plan is generated by combining the fault feature library with historical simulation data.

2. The linkage control method for communication between a mining belt conveyor system and the working face according to claim 1, characterized in that, The specific steps for constructing the real-time operational status map based on the preprocessed multi-source heterogeneous data in step I are as follows: S1.1: Based on the highest and lowest timestamps of the collected multi-source heterogeneous data, and with the lowest timestamp as the lower limit and the highest timestamp as the upper limit, establish a global time interval, and construct a main time axis based on the global time interval. Then, detect the sampling time point on the main time axis that is closest to the sampling timestamp of each device node. S1.2: Calculate the time deviation between the sampling timestamp of the multi-source heterogeneous data and the corresponding sampling time point. If the time deviation is less than the preset maximum time deviation threshold, the sampling time of the corresponding multi-source heterogeneous data is mapped to the sampling time point. Otherwise, the heterogeneous data at the misaligned sampling time point is marked as a missing value. S1.3: Establish a sliding time window of a preset size for each heterogeneous data, then move the sliding time window step by step according to the set time step, and calculate the mean and standard deviation of each heterogeneous data in the sliding time window after each move. Based on the preset anomaly judgment rules, determine whether the water quality data at the current sampling time point is abnormal data. If the rules are met, the sampling time point is marked as abnormal and regarded as a missing value. S1.4: During each round of the sliding time window, median filtering is used to remove impulse noise from the heterogeneous data, linear interpolation is used to fill in missing values, and then the heterogeneous data are normalized to be unified into the same range. The preprocessed heterogeneous data are combined into the state characteristics of the belt conveyor system. Then, the historical belt conveyor system state characteristics are weighted and fused based on the exponential decay weight mechanism to generate the corresponding comprehensive state index. S1.5: Map the generated comprehensive status indicators to a predefined multi-dimensional situation space, take each sub-unit of the belt conveyor system as a node, take the physical or logical relationship as the edge between the corresponding nodes, and associate a set of corresponding status attributes with each type of node based on the corresponding comprehensive status indicators to form a complete operation situation diagram. After each data collection cycle is completed, update the attributes of each node in the operation situation diagram based on the newly generated comprehensive status indicators.

3. The linkage control method for communication between a mining belt conveyor system and the working face according to claim 2, characterized in that, The specific manifestations of the state characteristics of the belt conveyor system described in S1.4 are as follows: in, Representing time Characteristics of the belt conveyor system at any time; Representing time The current total load on the entire belt; Representing time Maximum deviation of motor current; Representing time Online rate of communication equipment; Representing time Current operating speed of the coal mining machine; Representing time The position coordinates of the coal mining machine along the working face; Representing time Current coal bunker level; The specific calculation formula for the comprehensive status index mentioned in S1.4 is as follows: In the formula, Representing time Comprehensive status indicators at the time; Represents the attenuation coefficient; This represents the length of the integration time window.

4. The linkage control method for communication between a mining belt conveyor system and the working face according to claim 2, characterized in that, The specific steps for constructing and synchronously updating the transportation simulation model described in step II are as follows: S2.1: Deconstruct the belt conveyor system and its associated communication equipment, assign a unique identifier to each deconstructed unit, construct a geometric entity model of the belt conveyor system in a 3D modeling platform, and match corresponding spatial coordinates, size parameters, row parameter interfaces, state variable sets and behavioral constraint rules for each unit in the geometric entity model of the belt conveyor system based on the manufacturer's specifications. S2.2: Define the connection relationship and material flow direction between each device in the logic layer, establish a logical topology graph composed of nodes and directed edges, and then establish a corresponding dynamic behavior model based on dynamics and transmission characteristics to address the driving force, resistance and load effects during the operation of the belt conveyor system. S2.3: The real-time comprehensive status indicators reflected in the operation status diagram are broken down into a set of status parameters of the dynamic behavior model of the belt conveyor system, and the status parameter set is mapped to the corresponding twin parameter set. After the mapping is completed, the latest comprehensive status indicators are input into the dynamic behavior model of each unit of the belt conveyor system according to the prediction collection cycle. S2.4: After each data collection cycle, the state variables and model parameters of the dynamic behavior model of each unit of the belt conveyor system are updated and corrected. The deviation between the output of each dynamic behavior model and the feedback of the physical system is compared in real time. If the deviation exceeds the preset allowable range, the parameter self-correction mechanism is automatically triggered to adjust the internal parameters of the model. S2.5: After the states of each dynamic behavior model are synchronized and verified, the states of all objects are combined into a complete transportation simulation model, and the overall operating status of the belt conveyor system and communication system is reflected in real time through this transportation simulation model.

5. The linkage control method for communication between a mining belt conveyor system and the working face according to claim 4, characterized in that, The specific steps for simulating each fault scenario and control strategy as described in step II are as follows: S3.1: Based on the current operating status and control objectives, generate multiple candidate linkage control strategies. Each candidate linkage control strategy contains different combinations of control parameters, execution order, and linkage logic. Then, input each candidate control strategy into the transportation simulation model to drive the transportation simulation model to run according to the corresponding control logic. S3.2: During the simulation, the transportation simulation model calculates the evolution trajectory of the belt conveyor system state in real time, presets three typical fault modes, and establishes parameterized injection rules for each type. Then, a unique fault identifier is used to mark each fault, and a set of corresponding fault triggering condition functions are associated with each fault mode. When multiple faults are triggered simultaneously during the simulation, the running data of the transportation simulation model is monitored in real time, and the state perturbation equation for multi-fault parallel simulation is constructed. S3.3: Start multiple independent simulations for each candidate control strategy. In each simulation, randomly select the fault type, occurrence location, start time and duration, and generate a set of fault scenarios. At the same time, record the system state trajectory and performance index sequence for each scenario. Then, based on the state trajectory of multiple independent simulations, calculate the robustness score of each candidate control strategy using weighted failure probability. S3.4: Perform time series clustering on the performance index sequences of each simulated state trajectory to obtain multiple typical response clusters, and calculate the average risk characteristics of each response cluster. If the average risk characteristics are higher than the preset risk threshold, mark the fault combination corresponding to the cluster as a "high-risk mode", and analyze the impact propagation path of each identified high-risk mode in the belt conveyor system. S3.5: During the statistical simulation process, functional interruption, performance degradation or switching events caused by the influence of candidate control strategies or faults are recorded, and the continuity evaluation index of each candidate control strategy is calculated. The evaluation results of each candidate control strategy in terms of average risk characteristics, robustness score and continuity evaluation index are comprehensively calculated to form a comprehensive simulation evaluation result. S3.6: Sort the candidate control strategies from high to low according to the comprehensive simulation evaluation results, and select the candidate control strategy with the best comprehensive simulation evaluation results as the control scheme with the best overall performance under the multi-fault scenario.

6. The linkage control method for communication between a mining belt conveyor system and the working face according to claim 1, characterized in that, The specific steps for optimizing the control strategy based on the simulation analysis results described in step III are as follows: S4.1: After completing multi-strategy simulation and risk assessment, the multiple sets of evaluation data generated by each selected linkage control scheme under various fault scenarios are reorganized according to the control target dimension. At the same time, the constraints that need to be met for control optimization under the current operating condition are determined, and each constraint is converted into a corresponding mathematical inequality. The constraints include equipment physical limits, communication reliability, and linkage logic safety requirements. S4.2: Calculate the sensitivity index of each parameter in each candidate control strategy, and mark the parameters with sensitivity indices higher than the preset threshold as key parameters. Rearrange the execution order of control commands according to the simulation results, and calculate the comprehensive risk cost of each adjusted control strategy. If the comprehensive risk cost is higher than the preset threshold, adjust the key parameters and the order of control commands. S4.3: After the initial optimization of the instruction sequence and parameter range, analyze whether there are logical conflicts, redundant triggers or missing dependencies between different control actions in each linkage control strategy. If there are logical conflicts, correct them according to the simulation feedback. After completing parameter adjustment, sequence rearrangement and logical correction, the system integrates the optimization results to form the final optimized control strategy.

Images