Intelligent early warning method and system for monitoring stability of coal pillar in real time

Abstract

The invention discloses an intelligent early warning method and system for monitoring the stability of a coal pillar in real time. The intelligent early warning method comprises the following steps that stress distribution detection, crack extension detection, vibration signal detection, environmental parameter detection, data fusion analysis detection, early warning mechanism detection and emergency response detection are sequentially carried out according to a preset sequence; according to the invention, real-time monitoring and intelligent early warning are carried out on multiple key indexes of coal pillar stability; at present, a conventional coal pillar monitoring method only pays attention to the change of a single index, cannot comprehensively evaluate the stability of a coal pillar, and does not have an intelligent early warning function.

Description

Technical Field

[0001] The present invention belongs to the technical field of coal mine safety monitoring, and specifically relates to an intelligent early warning method and system for real-time monitoring of coal pillar stability. Background Art

[0002] In the process of coal mining, the stability of coal pillars is crucial to mine safety and production efficiency. As an important supporting structure in mining engineering, the stability of coal pillars directly affects the safe operation of mines. Existing coal pillar stability monitoring methods mainly rely on manual monitoring and regular inspections. These methods have problems such as low monitoring frequency, untimely data collection, and discontinuous monitoring data, making it difficult to achieve real-time and accurate stability assessment. In addition, existing monitoring methods often fail to detect subtle changes in coal pillars in a timely manner, resulting in potential safety hazards that are difficult to be effectively controlled in the early stages. Therefore, the development of an intelligent early warning method and system that can realize real-time monitoring of coal pillar stability has important practical significance and application value. Summary of the invention

[0003] The purpose of the present invention is to overcome the shortcomings of the prior art and provide an intelligent early warning method and system for real-time monitoring of coal pillar stability.

[0004] An intelligent early warning method for real-time monitoring of coal pillar stability.

[0005] During the coal mining process, stress distribution detection, crack expansion detection, vibration signal detection, environmental parameter detection, data fusion analysis detection, early warning mechanism detection and emergency response detection are carried out in sequence according to the preset order. If any of the detections fails, the coal pillar stability monitoring system fails the detection.

[0006] The stress distribution detection includes: initial stress detection, dynamic stress change detection and stress concentration area detection;

[0007] The crack expansion detection includes: crack morphology detection and crack expansion rate detection;

[0008] The vibration signal detection includes: microseismic signal detection and acoustic emission signal detection;

[0009] The environmental parameter detection includes: temperature detection, humidity detection and gas concentration detection;

[0010] The data fusion analysis detection includes: multi-source data integration detection and abnormal pattern recognition detection;

[0011] The early warning mechanism detection includes: threshold setting detection and graded early warning detection;

[0012] The emergency response detection includes: response time detection and disposal plan matching detection.

[0013] Furthermore, in the stress distribution detection,

[0014] The initial stress detection includes uniformity detection and local anomaly detection of the initial stress field of the coal pillar. If any of the detections fails, a warning is output;

[0015] The dynamic stress change detection includes simulating the stress changes during the mining process to detect whether there are stress fluctuations beyond the safety range;

[0016] If there is a stress fluctuation beyond the safety range, a warning is output;

[0017] The stress concentration area detection includes identifying whether there is stress concentration inside the coal pillar;

[0018] If stress concentration exists and no mitigation measures are taken, a warning is output;

[0019] If any of the initial stress test, dynamic stress change test, and stress concentration area test in the stress distribution test outputs a warning, the stress distribution test fails.

[0020] Furthermore, in the crack extension detection,

[0021] The crack morphology detection includes measuring the length, width and depth of the crack. If any measurement result exceeds a preset threshold, a warning is output;

[0022] The crack expansion rate detection includes simulating the crack expansion rate under different mining conditions to detect whether it exceeds the safe expansion rate;

[0023] If the crack expansion rate exceeds the safe expansion rate, a warning is output;

[0024] If any one of the crack morphology detection and crack extension rate detection in the crack extension detection outputs a warning, the crack extension detection fails.

[0025] Further, in the vibration signal detection,

[0026] The microseismic signal detection includes collecting microseismic signals around the coal pillar and detecting whether the frequency and amplitude are abnormal;

[0027] If the frequency or amplitude is abnormal, a warning is output;

[0028] The acoustic emission signal detection includes collecting the acoustic emission signal inside the coal pillar and detecting whether the energy release thereof exceeds a normal range;

[0029] If the energy release exceeds the normal range, a warning is output;

[0030] If any one of the microseismic signal detection and the acoustic emission signal detection in the vibration signal detection outputs a warning, the vibration signal detection fails.

[0031] Furthermore, in the environmental parameter detection,

[0032] The temperature detection includes detecting whether the ambient temperature of the coal pillar exceeds a safe range;

[0033] If it exceeds the safety range, a warning is output;

[0034] The humidity detection includes detecting whether the humidity of the environment around the coal pillar is abnormal;

[0035] If the humidity is abnormal, a warning is output;

[0036] The gas concentration detection includes detecting whether the gas concentration around the coal pillar reaches a dangerous level;

[0037] If the gas concentration reaches a dangerous level, a warning is output;

[0038] If any of the temperature detection, humidity detection and gas concentration detection in the environmental parameter detection outputs a warning, the environmental parameter detection fails.

[0039] Furthermore, in the data fusion analysis detection,

[0040] The multi-source data integration detection includes integrating the data of stress distribution, crack extension, vibration signal and environmental parameters to detect whether there is a data conflict;

[0041] If there is a data conflict, a warning is output;

[0042] The abnormal pattern recognition detection includes using a machine learning algorithm to perform abnormal pattern recognition on the integrated data to detect whether there is a potential risk;

[0043] If there is a potential risk, a warning is output;

[0044] If any of the multi-source data integration detection and abnormal pattern recognition detection in the data fusion analysis detection outputs a warning, the data fusion analysis detection fails.

[0045] Furthermore, in the early warning mechanism detection,

[0046] The threshold setting detection includes detecting whether the warning threshold is reasonable;

[0047] If the warning threshold is unreasonable, a warning is output;

[0048] The hierarchical warning detection includes simulating warning responses under different risk levels to detect whether the corresponding level of warning can be accurately triggered;

[0049] If the corresponding level of warning is not triggered accurately, a warning will be output;

[0050] If any of the threshold setting detection and graded warning detection in the early warning mechanism detection outputs a warning, the early warning mechanism detection fails.

[0051] Furthermore, in the emergency response detection,

[0052] The response time detection includes simulating the response time in an emergency situation and detecting whether the response is completed within the specified time;

[0053] If the response is not completed within the specified time, a warning is output;

[0054] The disposal plan matching detection includes detecting whether the emergency disposal plan matches the current risk level;

[0055] If the disposal scheme does not match, a warning is output;

[0056] If any of the response time test and disposal plan matching test in the emergency response test outputs a warning, the emergency response test fails.

[0057] The present invention also provides an intelligent early warning system for real-time monitoring of coal pillar stability, including: a stress distribution detection module, a crack extension detection module, a vibration signal detection module, an environmental parameter detection module, a data fusion analysis module, an early warning mechanism module and an emergency response module;

[0058] The stress distribution detection module is used to monitor the stress distribution of the coal pillar in real time to ensure that the stress changes are within a safe range;

[0059] The crack expansion detection module is used to monitor the shape and expansion rate of coal pillar cracks in real time to ensure that crack expansion does not threaten the stability of the coal pillar;

[0060] The vibration signal detection module is used to collect microseismic signals and acoustic emission signals around the coal pillar in real time to ensure that the vibration signal is within a normal range;

[0061] The environmental parameter detection module is used to monitor the temperature, humidity and gas concentration around the coal pillar in real time to ensure that the environmental parameters will not cause safety hazards;

[0062] The data fusion analysis module is used to integrate multi-source data and perform abnormal pattern recognition to ensure the accuracy of data analysis results;

[0063] The warning mechanism module is used to set reasonable warning thresholds and trigger graded warnings based on data analysis results to ensure the effectiveness of the warning mechanism;

[0064] The emergency response module is used to quickly respond to emergency situations and match appropriate disposal plans to ensure the timeliness and effectiveness of emergency response.

[0065] The invention provides an intelligent early warning method for real-time monitoring of coal pillar stability, which has simple operation, compact structure, and reasonable design, and provides safety guarantee for coal mining;

[0066] By introducing multi-source data fusion analysis technology and combining it with machine learning algorithms, an accurate assessment of coal pillar stability is achieved;

[0067] The safety of coal pillars in complex environments is ensured through comprehensive monitoring of coal pillar stress distribution, crack expansion, vibration signals and environmental parameters;

[0068] By establishing a hierarchical early warning mechanism and emergency response module, it is possible to issue early warnings in a timely manner and take effective measures when abnormalities occur in the coal pillar, thereby minimizing the probability of coal mine accidents.

[0069] In addition, the present invention adopts an abnormal pattern recognition algorithm based on support vector machine (SVM), the formula is as follows:

[0070]

[0071] Among them, x is the input data, αi is the Lagrange multiplier, yi is the target label, K(xi,x) is the kernel function, and b is the bias term. By learning from historical data, the algorithm can accurately identify abnormal patterns in the coal pillar state, thereby improving the accuracy of early warning.

[0072] The present invention has the following advantages:

[0073] The present invention performs real-time monitoring and intelligent early warning on multiple key indicators of coal pillar stability. Currently, conventional coal pillar monitoring methods only focus on the changes in a single indicator, are unable to comprehensively evaluate the stability of the coal pillar, and do not have an intelligent early warning function. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 The schematic diagram of the module structure of the intelligent early warning system for real-time monitoring of coal pillar stability provided in an embodiment of the present invention shows the composition of the stress distribution detection module, the crack extension detection module, the vibration signal detection module, the environmental parameter detection module, the data fusion analysis module, the early warning mechanism module and the emergency response module and their mutual relationship. DETAILED DESCRIPTION

[0075] The present invention provides an intelligent early warning method and system for real-time monitoring of coal pillar stability. The core of the system is to achieve comprehensive monitoring and intelligent early warning of coal pillar stability during coal mining through the collaborative work of multiple modules. Figure 1 As well as the technical details in the content of the invention, the specific implementation methods of the present invention are described in detail.

[0076] like Figure 1 As shown, the intelligent early warning system of the present invention includes a stress distribution detection module, a crack extension detection module, a vibration signal detection module, an environmental parameter detection module, a data fusion analysis module, an early warning mechanism module and an emergency response module. These modules are interconnected through data transmission and logic control to form a complete coal pillar stability monitoring system. In practical applications, the system is deployed at the coal mining site to achieve real-time monitoring of the coal pillar status through a sensor network, data acquisition equipment and a central processing unit.

[0077] First, the stress distribution detection module is the basic part of the whole system, which is used to monitor the stress distribution of the coal pillar in real time. In the specific implementation, the initial stress detection is completed by measuring the uniformity and local anomalies of the initial stress field of the coal pillar. For example, in the early stage of coal mining, high-precision strain gauges are arranged on the surface and key positions of the coal pillar to collect stress data and transmit them to the central processing unit. If the stress field is detected to be non-uniform or locally abnormal, the system will output a warning message. The dynamic stress change detection simulates the stress changes during the mining process and combines the real-time collected data to determine whether there is a stress fluctuation beyond the safety range. For example, during the advancement of the coal mining machine, the system will continuously monitor the change trend of the coal pillar stress and compare it with the preset safety threshold. If the stress fluctuation is found to be beyond the safety range, a warning will be triggered immediately. In addition, the stress concentration area detection uses the finite element analysis algorithm to identify whether there is stress concentration inside the coal pillar. If stress concentration is detected and no mitigation measures are taken, the system will also issue a warning. The above test results will serve as important input data for subsequent modules.

[0078] The crack extension detection module is responsible for real-time monitoring of the morphology and expansion rate of coal pillar cracks. In specific implementation, crack morphology detection uses laser scanners and ultrasonic detectors to accurately measure the length, width and depth of cracks. For example, when the crack length exceeds the preset threshold, the system will record the anomaly and output a warning. The crack extension rate detection simulates the crack extension speed under different mining conditions and combines historical data to predict future expansion trends. For example, under high-intensity mining conditions, the system will judge the stability of the coal pillar based on whether the crack extension rate exceeds the safe extension rate. If the crack extension rate is too high, the system will immediately issue a warning and prompt to take corresponding measures. The results of the crack extension detection will directly affect the analysis and decision-making of subsequent modules.

[0079] The vibration signal detection module is used to collect microseismic signals around the coal pillar and acoustic emission signals inside. In the specific implementation, the microseismic signal detection collects frequency and amplitude data through acceleration sensors arranged around the coal pillar. For example, when the frequency or amplitude of the microseismic signal fluctuates abnormally, the system will mark it as a potential risk and output a warning. The acoustic emission signal detection collects energy release data through an acoustic emission probe installed inside the coal pillar. For example, when the energy release of the acoustic emission signal exceeds the normal range, the system will determine that the coal pillar may have internal damage and issue a warning. The results of the vibration signal detection will be integrated with the data of other modules to improve the accuracy of the overall monitoring.

[0080] The environmental parameter detection module is responsible for real-time monitoring of the temperature, humidity and gas concentration around the coal pillar. In the specific implementation, the temperature detection collects the ambient temperature data around the coal pillar through the thermocouple sensor. For example, when the temperature exceeds the safe range, the system will issue a warning and prompt the possible fire hazard. The humidity detection collects the ambient humidity data around the coal pillar through the humidity sensor. For example, when the humidity rises abnormally, the system will determine that there may be a risk of water seepage and issue a warning. The gas concentration detection collects the gas concentration data around the coal pillar through the gas sensor. For example, when the gas concentration reaches a dangerous level, the system will immediately issue a warning and start the emergency response procedure. The results of the environmental parameter detection will provide important environmental background information for subsequent modules.

[0081] The data fusion analysis module is the core part of the whole system, responsible for integrating multi-source data and performing abnormal pattern recognition. In the specific implementation, the multi-source data integration detection integrates the data of stress distribution, crack extension, vibration signal and environmental parameters to detect whether there is a data conflict. For example, when there is a contradiction between the stress distribution data and the crack extension data, the system will output a warning and prompt for further verification. The abnormal pattern recognition detection analyzes the integrated data through a machine learning algorithm based on the support vector machine (SVM). The specific formula is as follows:

[0082]

[0083] Among them, x is the input data, αi is the Lagrange multiplier, yi is the target label, K(xi,x) is the kernel function, and b is the bias term. The algorithm can accurately identify abnormal patterns in the coal pillar state by learning from historical data. For example, when the system detects that multi-source data in a certain period of time all show abnormal trends, it will determine that the coal pillar may have potential risks and output a warning. The results of data fusion analysis will provide a scientific basis for the early warning mechanism module.

[0084] The early warning mechanism module is responsible for setting reasonable early warning thresholds and triggering graded early warnings based on the results of data analysis. In the specific implementation, the threshold setting detection determines the reasonable early warning threshold by analyzing historical data and current monitoring data. For example, when the stress fluctuation exceeds a certain value, the system will set it as the early warning threshold. The graded early warning detection simulates the early warning response under different risk levels to ensure that the corresponding level of early warning can be accurately triggered. For example, when the coal pillar state is at low risk, the system will issue a first-level early warning; when the coal pillar state is at high risk, the system will issue a third-level early warning and start the emergency response procedure. The design of the early warning mechanism module ensures that the system can issue accurate early warning information in a timely manner at different risk levels.

[0085] The emergency response module is responsible for responding quickly and matching appropriate disposal plans in emergency situations. In specific implementation, the response time detection simulates the response time in emergency situations to ensure that the system can complete the response within the specified time. For example, when the system detects that the coal pillar is in an abnormal state, it will start the emergency response program within 30 seconds. The disposal plan matching detection matches the most appropriate disposal plan by analyzing the current risk level. For example, when there is stress concentration in the coal pillar, the system will recommend taking pressure relief measures; when there is too fast expansion of cracks in the coal pillar, the system will recommend taking reinforcement measures. The design of the emergency response module ensures that the system can quickly take effective measures in an emergency to minimize the probability of coal mine accidents.

[0086] In summary, the present invention realizes comprehensive monitoring and intelligent early warning of coal pillar stability through the coordinated work of stress distribution detection module, crack extension detection module, vibration signal detection module, environmental parameter detection module, data fusion analysis module, early warning mechanism module and emergency response module. In practical applications, the system can significantly improve the safety of coal mining and provide important guarantee for coal mine safety production.

[0087] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent early warning method for real-time monitoring of coal pillar stability, characterized in that: The following steps are involved: Carry out stress distribution detection, crack extension detection, vibration signal detection, environmental parameter detection, data fusion analysis detection, early warning mechanism detection and emergency response detection in the preset order; The stress distribution detection includes initial stress detection, dynamic stress change detection and stress concentration area detection; The crack expansion detection includes crack morphology detection and crack expansion rate detection; The vibration signal detection includes microseismic signal detection and acoustic emission signal detection; The environmental parameter detection includes temperature detection, humidity detection and gas concentration detection; The data fusion analysis detection includes multi-source data integration detection and abnormal pattern recognition detection; The early warning mechanism detection includes threshold setting detection and graded early warning detection; The emergency response detection includes response time detection and disposal plan matching detection; If any of the tests fails, the coal pillar stability monitoring system fails the test.

2. The intelligent early warning method for real-time monitoring of coal pillar stability according to claim 1 is characterized in that: The initial stress detection includes uniformity detection and local anomaly detection of the initial stress field of the coal pillar. If any one of the detections fails, a warning is output.

3. The intelligent early warning method for real-time monitoring of coal pillar stability according to claim 1 is characterized in that: The dynamic stress change detection includes simulating stress changes during the mining process, detecting whether there is a stress fluctuation beyond the safety range, and outputting a warning if there is a stress fluctuation beyond the safety range.

4. The intelligent early warning method for real-time monitoring of coal pillar stability according to claim 1 is characterized in that: The crack morphology detection includes measuring the length, width and depth of the crack. If any measurement result exceeds a preset threshold, a warning is output.

5. The intelligent early warning method for real-time monitoring of coal pillar stability according to claim 1 is characterized in that: The environmental parameter detection includes detecting the temperature, humidity and gas concentration of the surrounding environment of the coal pillar. If any parameter exceeds the safe range, a warning is output.

6. The intelligent early warning method for real-time monitoring of coal pillar stability according to claim 1 is characterized in that: The data fusion analysis detection includes integrating the data of stress distribution, crack expansion, vibration signal and environmental parameters to detect whether there is a data conflict. If there is a data conflict, a warning is output.

7. The intelligent early warning method for real-time monitoring of coal pillar stability according to claim 1 is characterized in that: The emergency response detection includes simulating the response time in an emergency situation and detecting whether the response is completed within the specified time. If the response is not completed within the specified time, a warning is output.

Images