Intelligent short-distance coal seam mining working face support monitoring method and system

Abstract

The invention provides an intelligent short-distance coal seam mining working face support monitoring method and system, and belongs to the technical field of coal seam mining. The method comprises the following steps: inputting coal seam geologic feature data of a target area into a correlation model to obtain a coal seam prediction result of the target area; initial supporting scheme matching of the supporting structure is executed based on the coal seam prediction result, after supporting of the supporting structure is conducted according to the initial supporting scheme, real-time monitoring data flow of the supporting structure is obtained, the real-time monitoring data flow is input into the mapping relation model, and a mining-induced stress prediction result of the target area is obtained; and monitoring the supporting condition of the supporting structure according to the coal seam prediction result and the mining-induced stress prediction result of the target area, and adjusting the supporting scheme of the supporting structure when monitoring that the supporting condition is abnormal. Therefore, in the mining process, the supporting effect of the supporting structure is effectively evaluated, weak links and potential risk points are identified, and the supporting safety and stability of a short-distance coal seam mining working face are ensured.

Description

Technical Field

[0001] This invention relates to the field of coal seam mining technology, specifically to an intelligent method for monitoring and supporting close-range coal seam mining faces, an intelligent system for monitoring and supporting close-range coal seam mining faces, a machine-readable storage medium, and an electronic device. Background Technology

[0002] Machine learning algorithms are used to comprehensively analyze parameters such as the geological structure, thickness, and dip angle of coal seams to predict their distribution and trends. This provides important reference data for support monitoring in near-field coal seam mining faces. However, in actual mining, coal seam changes may deviate from the predicted results, necessitating real-time monitoring of the stress state and deformation of the support structure to ensure safety. How to effectively evaluate the support effect of the support structure during mining, identify weak points and potential risks, and adjust support parameters to ensure the safety and stability of near-field coal seam mining faces is a pressing issue that needs to be addressed. Summary of the Invention

[0003] The purpose of this invention is to provide an intelligent method and system for monitoring support in close-range coal seam mining operations, so as to at least solve the above-mentioned problems of how to effectively evaluate the support effect of the support structure during the mining process, identify weak links and potential risk points, and adjust support parameters to ensure the support safety and stability of close-range coal seam mining operations.

[0004] To achieve the above objectives, the first aspect of the present invention provides an intelligent method for monitoring and supporting close-range coal seam mining faces, comprising: The geological characteristics of coal seams in the target area are input into an association model used to predict the distribution and changing trends of coal seams, so as to obtain the prediction results of coal seams in the target area. Based on the obtained coal seam prediction results, the initial support scheme matching of the support structure is performed. After the support structure is supported according to the matched initial support scheme, the real-time monitoring data stream of the support structure is obtained. The real-time monitoring data stream is input into the mapping relationship model for predicting the mining stress of the target area to obtain the mining stress prediction results of the target area. Based on the coal seam prediction results and mining stress prediction results of the target area, the support status of the support structure in the target area is monitored, and the support scheme of the support structure is adjusted when abnormalities are detected.

[0005] Optional, the rules for establishing the association model include: Historical coal seam geological feature data are acquired, and each historical coal seam geological feature data is cleaned and normalized; the historical coal seam geological feature data includes at least one or more of the following: coal seam geological structure, coal seam thickness, coal seam dip angle, coal seam depth, and coal content. An initial correlation model is established using support vector machines. The processed historical coal seam geological feature data and the corresponding coal seam distribution and change trend data are used as the first training set. The initial correlation model is trained and iteratively optimized using the first training set until the prediction deviation RMSE is less than or equal to the preset threshold, thus obtaining the correlation model.

[0006] Optionally, the rules for acquiring real-time monitoring data streams of the support structure include: The system acquires real-time stress and deformation data of the support structure from sensors deployed at the coal seam mining face in the target area; the sensor deployment scheme is determined based on the stress points and deformation areas of the support structure determined by the matched initial support scheme. The stress state data and deformation data of the support structure are acquired and transmitted to the ground monitoring center to form a real-time monitoring data stream of the support structure.

[0007] Optionally, before inputting the real-time monitoring data stream into the mapping model, the method further includes: After preprocessing the real-time monitoring data stream using a time series analysis algorithm, outliers exceeding the preset normal range in the preprocessed real-time monitoring data stream are removed using the 3σ principle, and wavelet transform is used for noise reduction.

[0008] Optionally, the rules for establishing the mapping relationship model include: The stress state, deformation data, and corresponding mining stress of the historical support structure are obtained as the second training set. An initial relational model is established using a long short-term memory neural network, and the initial relational model is trained using a second training set to obtain a mapping relational model.

[0009] Optionally, the support status of the support structure in the target area may be monitored, including: Based on the predicted mining stress in the target area, determine the hazard level of the mining stress in the target area; The fuzzy comprehensive evaluation method is used to integrate the coal seam prediction results of the target area, the real-time monitoring data stream of the support structure, and the hazard level of the mining-induced stress in the target area to assess the safety status of the support structure.

[0010] Optionally, based on the predicted mining stress in the target area, a hazard level assessment of the mining stress in the target area is performed, including: When the predicted stress of mining in the target area is within the first preset range, the risk level of the stress of mining in the target area is determined to be a Level 1 warning. When the predicted stress of mining in the target area exceeds the first preset range, the risk level of mining stress in the target area is determined to be a Level II warning.

[0011] A second aspect of the present invention provides an intelligent close-range coal seam mining face support monitoring system, comprising: The coal seam prediction module is used to input the geological feature data of coal seams in the target area into the correlation model used to predict the distribution and change trend of coal seams, so as to obtain the coal seam prediction results in the target area. The mining-induced stress prediction module is used to perform initial support scheme matching of the support structure based on the obtained coal seam prediction results. After the support structure is supported according to the matched initial support scheme, the module obtains the real-time monitoring data stream of the support structure and inputs the real-time monitoring data stream into the mapping relationship model for predicting the mining-induced stress of the target area to obtain the mining-induced stress prediction results of the target area. The support status monitoring module is used to monitor the support status of the support structure in the target area based on the coal seam prediction results and mining stress prediction results, and to adjust the support scheme of the support structure when abnormalities are detected.

[0012] In a third aspect, the present invention provides a machine-readable storage medium storing instructions that, when executed by a processor, configure the processor to perform the aforementioned intelligent close-range coal seam mining face support monitoring method.

[0013] In a fourth aspect, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the aforementioned intelligent close-range coal seam mining face support monitoring method.

[0014] The above technical solution provides an intelligent method and system for monitoring support in near-distance coal seam mining faces. It inputs geological characteristic data of the coal seam in the target area into a correlation model used to predict the distribution and changing trends of the coal seam, thereby obtaining coal seam prediction results for the target area. Based on the obtained coal seam prediction results, an initial support scheme matching is performed. After the support structure is supported according to the matched initial support scheme, real-time monitoring data streams of the support structure are acquired. These real-time monitoring data streams are input into a mapping relationship model used to predict mining-induced stress in the target area, thereby obtaining mining-induced stress prediction results for the target area. Based on the predicted coal seam distribution and changing trends and the predicted mining-induced stress in the target area, the support of the near-distance coal seam mining face is monitored. By comprehensively analyzing the coal seam prediction results, mining-induced stress prediction results, and real-time monitoring data streams, the support effect of the support structure is effectively evaluated during the mining process, weak links and potential risk points are identified, providing a decision-making basis for support optimization design and safety management, adjusting the support scheme, and ensuring the support safety and stability of the near-distance coal seam mining face.

[0015] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0016] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart of an intelligent close-range coal seam mining face support monitoring method provided by one embodiment of the present invention; Figure 2 This is a flowchart of another intelligent close-range coal seam mining face support monitoring method provided by one embodiment of the present invention; Figure 3 This is a block diagram of an intelligent close-range coal seam mining face support and monitoring system provided in one embodiment of the present invention; Figure 4 This is a schematic diagram of an electronic device structure provided by a preferred embodiment of the present invention.

[0017] Explanation of reference numerals in the attached figures 10 - Electronic device, 100 - Processor, 101 - Memory, 102 - Computer program. Detailed Implementation

[0018] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0019] Figure 1 This is a flowchart of an intelligent close-range coal seam mining face support monitoring method provided by one embodiment of the present invention. Figure 2 This is a flowchart of another intelligent close-range coal seam mining face support monitoring method provided by one embodiment of the present invention. Figure 1 and Figure 2 As shown, this invention provides an intelligent method for monitoring and supporting coal seam mining faces in close proximity, comprising: S110: Input the geological feature data of the coal seams in the target area into the correlation model used to predict the distribution and change trend of coal seams, so as to obtain the coal seam prediction results in the target area; Specifically, the geological characteristics data of coal seams in the target area are obtained, and the data are input into the correlation model to obtain the prediction results of the distribution and changing trends of coal seams in the target area.

[0020] In some embodiments of this example, the rules for establishing the association model include: acquiring historical coal seam geological feature data, and performing data cleaning and normalization on the historical coal seam geological feature data one by one; wherein, the historical coal seam geological feature data includes at least one or more of the following: coal seam geological structure, coal seam thickness, coal seam dip angle, coal seam depth, and coal content; establishing an initial association model using a support vector machine, using the processed historical coal seam geological feature data and the corresponding coal seam distribution and change trend data as the first training set, and using the first training set to train and iteratively optimize the initial association model until the prediction deviation RMSE is less than or equal to a preset threshold, thereby obtaining the association model.

[0021] Specifically, firstly, a training sample dataset containing data on coal seam geological structure, thickness parameters, and dip angle parameters is obtained from known coal seam areas, with a sample size of no less than 1000. Then, a support vector machine (SVM) algorithm is used to train the training sample dataset. The hyperparameters of the algorithm are optimized through grid search and cross-validation, ultimately establishing a nonlinear correlation model between coal seam geological feature data and coal seam distribution and change trends. Next, parameters such as coal seam geological structure, thickness, and dip angle in the target area are obtained. These feature parameters are input into the trained correlation model to obtain prediction results of coal seam distribution and change trends in that area. To evaluate the predictive performance of the correlation model, actual coal seam exploration and mining data for the target area are obtained, and the root mean square error (RMSE) between the predicted results and the actual data is calculated as a measure of model prediction bias. If the prediction bias RMSE is greater than a preset threshold, the kernel function type, penalty coefficient, and kernel function parameters of the correlation model need to be adjusted according to the prediction bias, iterating and optimizing until the prediction bias RMSE is less than or equal to the preset threshold. Finally, to further improve the generalization performance of the correlation model, new geological feature data of known coal seam areas, such as coal seam data of adjacent mining areas, can be obtained and added to the original training sample dataset. An ensemble learning method, such as the AdaBoost algorithm, can be used to retrain the updated training sample dataset. At the same time, the model performance can be evaluated by combining new validation sample data, and finally a more accurate and robust coal seam distribution and change trend prediction model can be obtained.

[0022] In the above implementation process, to evaluate the accuracy of the prediction results, 100 sets of known exploration data for the coal seam were obtained. The prediction results were compared and analyzed with the known exploration data, and evaluation indicators such as precision, recall, and F1 score were calculated. The final evaluation result was a prediction accuracy of 93%. Based on the prediction accuracy evaluation result, it was determined whether the current prediction model needed further optimization and adjustment. If the prediction accuracy was below 90%, the model needed optimization. During optimization, based on the sample data of prediction errors, a grid search was performed on the model's penalty factor C and radial basis function γ, and the model was retrained to obtain an optimized coal seam distribution change trend prediction model, thereby improving the model's prediction accuracy.

[0023] S120: Based on the obtained coal seam prediction results, perform initial support scheme matching for the support structure, and after supporting the support structure according to the matched initial support scheme, obtain the real-time monitoring data stream of the support structure, and input the real-time monitoring data stream into the mapping relationship model for predicting the mining stress of the target area to obtain the mining stress prediction results of the target area. Specifically, real-time monitoring data streams are acquired and input into a mapping model to obtain predicted mining stresses. The mapping model is trained using a second training set, which includes historical stress states and deformation data of the support structure and corresponding mining stresses.

[0024] In some embodiments of this example, the rules for acquiring the real-time monitoring data stream of the support structure include: acquiring the stress state data and deformation data of the support structure collected in real time by sensors deployed at the coal seam mining face in the target area; wherein, the sensor deployment scheme is determined based on the stress points and deformation areas of the support structure determined by the matching initial support scheme. Specifically, the deployment of sensors fully considered the complex geological conditions and potential stress distribution characteristics of the nearby coal seam mining face, ensuring that the installation position and monitoring angle of each sensor could accurately cover the key stress points and deformation-sensitive areas of the support structure. Simultaneously, the sensor sampling frequency and data transmission protocol underwent rigorous debugging to guarantee the continuity, stability, and timeliness of the real-time monitoring data stream, providing reliable data support for subsequent support structure condition assessment and early warning analysis.

[0025] The stress state data and deformation data of the support structure are acquired and transmitted to the ground monitoring center to form a real-time monitoring data stream of the support structure.

[0026] Specifically, stress sensors and displacement sensors are deployed at the close-range coal seam mining face to collect real-time stress and deformation data of the support structure. The collected monitoring data is then transmitted to the ground monitoring center to form a real-time monitoring data stream.

[0027] In detail, YJ-KX-02 stress sensors and YJ-WY-01 displacement sensors are deployed at the coal seam mining face to collect data on the stress state and deformation of the support structure. The monitoring data is then transmitted to the ground monitoring center in real time at a frequency of 1 second via ZigBee wireless transmission technology.

[0028] In some embodiments of this example, before inputting the real-time monitoring data stream into the mapping relationship model, the method further includes: preprocessing the real-time monitoring data stream using a time series analysis algorithm, removing outliers in the preprocessed real-time monitoring data stream that exceed a preset normal range using the 3σ principle, and performing noise reduction processing using wavelet transform.

[0029] In some implementations of this embodiment, the rules for establishing the mapping relationship model include: obtaining the stress state, deformation data and corresponding mining stress of the historical support structure as a second training set; establishing an initial relationship model using a long short-term memory neural network, and training the initial relationship model using the second training set to obtain the mapping relationship model.

[0030] S130: Based on the coal seam prediction results and mining stress prediction results of the target area, monitor the support status of the support structure in the target area, and adjust the support scheme of the support structure when abnormalities are detected.

[0031] Specifically, this method constructs a coal seam geological feature dataset as training samples, employs a support vector machine algorithm to establish a correlation model between coal seam geological features and coal seam distribution and variation trends, and trains and optimizes the correlation model to improve prediction accuracy and generalization ability. Monitoring equipment (e.g., sensors) is deployed at the nearby coal seam mining face to collect real-time data on the stress state and deformation of the support structure, enabling predictive analysis of the support structure's safety status. Based on the predicted results of coal seam distribution and variation trends in the target area and the predicted mining-induced stress, the support at the nearby coal seam mining face is monitored. By comprehensively analyzing the prediction results (i.e., coal seam prediction results and mining-induced stress prediction results) and monitoring data (i.e., real-time monitoring data stream), the support effect of the support structure is effectively evaluated during mining, identifying weak points and potential risk points, providing a basis for decision-making in support optimization design and safety management, adjusting support schemes, and ensuring the support safety and stability of the nearby coal seam mining face.

[0032] In some embodiments of this example, the support status of the support structure in the target area is monitored, including: judging the risk level of the mining stress in the target area based on the mining stress prediction results of the target area; and using the fuzzy comprehensive evaluation method to perform a fusion analysis on the coal seam prediction results of the target area, the real-time monitoring data stream of the support structure, and the judged risk level of the mining stress in the target area, so as to assess the safety status of the support structure.

[0033] Specifically, the predicted results of coal seam distribution and change trends in the target area, real-time monitoring data streams, and hazard levels are integrated, and a fuzzy comprehensive evaluation method is used to comprehensively assess the safety status of the working face support, and the support density and strength are adjusted according to the safety status.

[0034] Furthermore, the early warning mechanism automatically adjusts the support structure parameters based on the comprehensive assessment results, such as adjusting the support density from 5m / support to 1m / support and the support strength from 2MPa to 3MPa. After adjustment, iterative optimization is performed every 30 minutes. Through this continuous cycle of "monitoring-prediction-adjustment," the working face support system can adaptively adjust support parameters according to the dynamic changes in the coal seam environment, ensuring the safety and efficiency of coal seam mining operations.

[0035] In some embodiments of this example, the risk level of mining stress in the target area is determined based on the predicted mining stress of the target area, including: when the predicted mining stress of the target area is within a first preset range, the risk level of mining stress in the target area is determined to be a Level 1 warning; when the predicted mining stress of the target area exceeds the first preset range, the risk level of mining stress in the target area is determined to be a Level 2 warning.

[0036] Specifically, when the predicted mining-induced stress exceeds the safety threshold of 35 MPa, an early warning signal is triggered. The warning information is displayed in real-time on the monitoring interface using line charts and bar charts via the Echarts visualization library. Simultaneously, the warning information is pushed to the mobile terminals of on-site personnel via SMS. On-site personnel determine the hazard level of the mining-induced stress based on the warning information: a level one warning is issued when the mining-induced stress is between 35 and 40 MPa; a level two warning is issued when the mining-induced stress exceeds 40 MPa. After the mining-induced stress recovers to a safe range below 30 MPa, the stress state and deformation data of the support structure continue to be monitored in real-time, and the above process is repeated to form a closed-loop control for safety monitoring of the coal seam mining face. By regularly updating training data and optimizing the support vector machine model parameters, the accuracy of mining-induced stress prediction is continuously improved, achieving intelligent management of safe production at the coal seam mining face.

[0037] Figure 3 This is a block diagram of an intelligent close-range coal seam mining face support monitoring system provided by one embodiment of the present invention. Figure 3 As shown, this invention provides an intelligent near-field coal seam mining face support monitoring system, comprising: The coal seam prediction module is used to input the geological feature data of coal seams in the target area into the correlation model used to predict the distribution and change trend of coal seams, so as to obtain the coal seam prediction results in the target area. The mining-induced stress prediction module is used to perform initial support scheme matching of the support structure based on the obtained coal seam prediction results. After the support structure is supported according to the matched initial support scheme, the module obtains the real-time monitoring data stream of the support structure and inputs the real-time monitoring data stream into the mapping relationship model for predicting the mining-induced stress of the target area to obtain the mining-induced stress prediction results of the target area. The support status monitoring module is used to monitor the support status of the support structure in the target area based on the coal seam prediction results and mining stress prediction results, and to adjust the support scheme of the support structure when abnormalities are detected.

[0038] Specifically, the system constructs a coal seam geological feature dataset as training samples, employs a support vector machine algorithm to establish a correlation model between coal seam geological features and coal seam distribution and variation trends, and trains and optimizes the correlation model to improve prediction accuracy and generalization ability. Monitoring equipment (e.g., sensors) is deployed at the nearby coal seam mining face to collect real-time data on the stress state and deformation of the support structure, predicting and analyzing the safety status of the support structure. Based on the predicted results of coal seam distribution and variation trends in the target area and the predicted mining-induced stress, the support of the nearby coal seam mining face is monitored. By comprehensively analyzing the prediction results (i.e., coal seam prediction results and mining-induced stress prediction results) and monitoring data (i.e., real-time monitoring data stream), the support effect of the support structure is effectively evaluated during mining, weak links and potential risk points are identified, providing a basis for decision-making in support optimization design and safety management, adjusting support schemes, and ensuring the support safety and stability of the nearby coal seam mining face.

[0039] The present invention also provides a machine-readable storage medium storing instructions that, when executed by a processor 100, configure the processor 100 to perform the above-described intelligent close-range coal seam mining face support monitoring method.

[0040] Machine-readable storage media include both permanent and non-permanent, removable and non-removable media, which can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0041] The present invention also provides an electronic device 10, which includes a memory 101, a processor 100, and a computer program 102 stored in the memory 101 and executable on the processor 100. When the processor 100 executes the computer program 102, it implements the above-mentioned intelligent close-range coal seam mining face support monitoring method.

[0042] like Figure 4The diagram shown is a schematic representation of an electronic device according to an embodiment of the present invention. Figure 4 As shown, the electronic device 10 of this embodiment includes a processor 100, a memory 101, and a computer program 102 stored in the memory 101 and executable on the processor 100. When the processor 100 executes the computer program 102, it implements the steps in the method embodiment described above. Alternatively, when the processor 100 executes the computer program 102, it implements the functions of each module / unit in the device embodiment described above.

[0043] For example, computer program 102 can be divided into one or more modules / units, one or more of which are stored in memory 101 and executed by processor 100 to complete the present invention. One or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of computer program 102 in electronic device 10. For example, computer program 102 can be divided into a coal seam prediction module, a mining stress prediction module, and a support condition monitoring module.

[0044] Electronic device 10 can be a desktop computer, laptop, handheld computer, cloud server, or other computing device. Electronic device 10 may include, but is not limited to, processor 100 and memory 101. Those skilled in the art will understand that... Figure 4 This is merely an example of electronic device 10 and does not constitute a limitation on electronic device 10. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device may also include input / output devices, network access devices, buses, etc.

[0045] The processor 100 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0046] The memory 101 can be an internal storage unit of the electronic device 10, such as a hard disk or RAM of the electronic device 10. The memory 101 can also be an external storage device of the electronic device 10, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, FlashCard, etc., equipped on the electronic device 10. Furthermore, the memory 101 can include both internal and external storage units of the electronic device 10. The memory 101 is used to store computer programs and other programs and data required by the electronic device 10. The memory 101 can also be used to temporarily store data that has been output or will be output.

[0047] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0048] Those skilled in the art will understand that embodiments of this application can be provided as a method, system, or computer program 102 product. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program 102 product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0049] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program 102 products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program 102 instructions. These computer program 102 instructions can be provided to a processor 100 of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor 100 of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0050] These computer program 102 instructions may also be stored in a computer-readable storage medium 101 that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium 101 produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0051] These computer program 102 instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0052] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0053] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. An intelligent method for monitoring and supporting coal seam mining faces at close range, characterized in that, include: The geological characteristics of coal seams in the target area are input into an association model used to predict the distribution and changing trends of coal seams, so as to obtain the prediction results of coal seams in the target area. Based on the obtained coal seam prediction results, the initial support scheme matching of the support structure is performed. After the support structure is supported according to the matched initial support scheme, the real-time monitoring data stream of the support structure is obtained. The real-time monitoring data stream is input into the mapping relationship model for predicting the mining stress of the target area to obtain the mining stress prediction result of the target area. Based on the coal seam prediction results and mining stress prediction results of the target area, the support status of the support structure in the target area is monitored, and the support scheme of the support structure is adjusted when abnormalities are detected.

2. The intelligent close-range coal seam mining face support monitoring method according to claim 1, characterized in that, The rules for establishing the association model include: Historical coal seam geological feature data are acquired, and the historical coal seam geological feature data are cleaned and normalized one by one; wherein the historical coal seam geological feature data includes at least one or more of the following: coal seam geological structure, coal seam thickness, coal seam dip angle, coal seam depth, and coal content. An initial correlation model is established using a support vector machine. The processed historical coal seam geological feature data and the corresponding coal seam distribution and change trend data are used as the first training set. The initial correlation model is trained and iteratively optimized using the first training set until the prediction deviation RMSE is less than or equal to a preset threshold, thus obtaining the correlation model.

3. The intelligent close-range coal seam mining face support monitoring method according to claim 1, characterized in that, The rules for acquiring the real-time monitoring data stream of the support structure include: The system acquires real-time stress and deformation data of the support structure from sensors deployed at the coal seam mining face in the target area; wherein the sensor deployment scheme is determined based on the stress points and deformation areas of the support structure determined by the matched initial support scheme. The stress state data and deformation data of the support structure are acquired and transmitted to the ground monitoring center to form a real-time monitoring data stream of the support structure.

4. The intelligent close-range coal seam mining face support monitoring method according to claim 1, characterized in that, Before inputting the real-time monitoring data stream into the mapping relationship model, the method further includes: After preprocessing the real-time monitoring data stream using a time series analysis algorithm, outliers exceeding the preset normal range in the preprocessed real-time monitoring data stream are removed using the 3σ principle, and noise reduction is performed using wavelet transform.

5. The intelligent close-range coal seam mining face support monitoring method according to claim 1, characterized in that, The rules for establishing the mapping relationship model include: The stress state, deformation data, and corresponding mining stress of the historical support structure are obtained as the second training set. An initial relational model is established using a long short-term memory neural network, and the initial relational model is trained using the second training set to obtain a mapping relational model.

6. The intelligent close-range coal seam mining face support monitoring method according to claim 1, characterized in that, The monitoring of the support status of the support structure in the target area includes: Based on the predicted mining stress in the target area, determine the hazard level of the mining stress in the target area; The fuzzy comprehensive evaluation method is used to integrate the coal seam prediction results of the target area, the real-time monitoring data stream of the support structure, and the hazard level of the mining-induced stress in the target area to assess the safety status of the support structure.

7. The intelligent close-range coal seam mining face support monitoring method according to claim 6, characterized in that, The determination of the risk level of mining stress in the target area based on the predicted mining stress in the target area includes: When the predicted stress of mining in the target area is within the first preset range, the risk level of the stress of mining in the target area is determined to be a Level 1 warning. When the predicted stress of mining in the target area exceeds the first preset range, the risk level of mining stress in the target area is determined to be a Level II warning.

8. An intelligent close-range coal seam mining face support monitoring system, characterized in that, include: The coal seam prediction module is used to input the geological feature data of coal seams in the target area into the correlation model used to predict the distribution and change trend of coal seams, so as to obtain the coal seam prediction results in the target area. The mining-induced stress prediction module is used to perform initial support scheme matching of the support structure based on the obtained coal seam prediction results, and after the support structure is supported according to the matched initial support scheme, it obtains the real-time monitoring data stream of the support structure and inputs the real-time monitoring data stream into the mapping relationship model for predicting the mining-induced stress of the target area to obtain the mining-induced stress prediction result of the target area. The support status monitoring module is used to monitor the support status of the support structure in the target area based on the coal seam prediction results and mining stress prediction results, and to adjust the support scheme of the support structure when abnormalities are detected.

9. A machine-readable storage medium storing instructions thereon, characterized in that, When executed by the processor, the instruction causes the processor to be configured to perform the intelligent close-range coal seam mining face support monitoring method as described in any one of claims 1 to 7.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the intelligent close-range coal seam mining face support and monitoring method according to any one of claims 1 to 7.

Images