CN-121997407-A - Intelligent short-distance coal seam mining operation face support monitoring method and system

CN121997407ACN 121997407 ACN121997407 ACN 121997407ACN-121997407-A

Abstract

The invention provides an intelligent short-distance coal seam mining operation surface support monitoring method and system, and belongs to the technical field of coal seam mining. The method comprises the steps of inputting coal seam geological feature data of a target area into a correlation model to obtain a coal seam prediction result of the target area, executing initial supporting scheme matching of a supporting structure based on the coal seam prediction result, acquiring real-time monitoring data flow of the supporting structure after supporting the supporting structure according to the initial supporting scheme, inputting the real-time monitoring data flow into a mapping relation model to obtain a mining stress prediction result of the target area, monitoring the supporting condition of the supporting structure according to the coal seam prediction result and the mining stress prediction result of the target area, and adjusting the supporting scheme of the supporting structure when the monitoring condition is abnormal. Therefore, in the exploitation 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 the working face of the close-range coal seam exploitation are ensured.

Inventors

FENG TAO
WANG CHENG
JING JUDONG
YU YONGJIANG
LIU YICAI

Assignees

国家能源集团宁夏煤业有限责任公司
辽宁工程技术大学

Dates

Publication Date: 20260508
Application Date: 20251211

Claims (10)

1. An intelligent close-range coal seam mining operation face support monitoring method is characterized by comprising the following steps of: Inputting the coal seam geological feature data of the target area into a correlation model for predicting the distribution and change trend of the coal seam so as to obtain a coal seam prediction result of the target area; performing initial supporting scheme matching of the supporting structure based on the obtained coal seam prediction result, acquiring real-time monitoring data flow of the supporting structure after supporting the supporting structure according to the matched initial supporting scheme, and inputting the real-time monitoring data flow into a mapping relation model for predicting mining stress of a target area so as to obtain the mining stress prediction result of the target area; And monitoring the supporting condition of the supporting structure of the target area according to the coal seam prediction result and the mining stress prediction result of the target area, and adjusting the supporting scheme of the supporting structure when the abnormal supporting condition is monitored.
2. The intelligent short-distance coal mining face support monitoring method according to claim 1, wherein the establishment rules of the association model comprise: Acquiring historical coal seam geological feature data, and carrying out data cleaning and normalization processing on the historical coal seam geological feature data one by one, wherein the historical coal seam geological feature data at least comprises one or more of a coal seam geological structure, a coal seam thickness, a coal seam dip angle, a coal seam depth and a coal content; And establishing an initial association model by using a support vector machine, taking the processed historical coal seam geological feature data and the corresponding coal seam distribution and change trend data as a first training set, and training and iterative optimization of the initial association model by using the first training set until the prediction deviation RMSE is smaller than or equal to a preset threshold value to obtain the association model.
3. The intelligent short-distance coal mining face support monitoring method according to claim 1, wherein the acquisition rule of the real-time monitoring data flow of the support structure comprises: The method comprises the steps of acquiring stress state data and deformation data of a supporting structure, which are acquired in real time by sensors arranged on a coal seam mining working face of a target area, wherein the arrangement scheme of the sensors is determined based on stress points and deformation areas of the supporting structure determined by a matched initial supporting scheme; And transmitting the obtained stress state data and deformation data of the support structure to a ground monitoring center to form a real-time monitoring data stream of the support structure.
4. An intelligent close-range coal mining face support monitoring method according to claim 1, wherein prior to inputting the real-time monitoring data stream into a mapping relationship model, the method further comprises: And after preprocessing the real-time monitoring data stream by adopting a time sequence analysis algorithm, removing abnormal values exceeding a preset normal range in the preprocessed real-time monitoring data stream by using a3 sigma principle, and carrying out noise reduction processing by adopting wavelet transformation.
5. The intelligent short-distance coal mining operation face support monitoring method according to claim 1, wherein the establishment rule of the mapping relation model comprises: acquiring stress state, deformation data and corresponding mining stress of the historical support structure as a second training set; And establishing an initial relation model by using the long-short-period memory neural network, and training the initial relation model by using the second training set to obtain a mapping relation model.
6. The method for monitoring the support of the intelligent close-range coal seam mining operation face according to claim 1, wherein the monitoring the support condition of the support structure of the target area comprises: executing dangerous grade judgment of mining stress of the target area based on the mining stress prediction result of the target area; And carrying out fusion analysis on the coal seam prediction result of the target area, the real-time monitoring data flow of the supporting structure and the judged dangerous grade of the mining stress of the target area by adopting a fuzzy comprehensive evaluation method so as to evaluate the safety state of the supporting structure.
7. The intelligent short-distance coal mining face support monitoring method according to claim 6, wherein the dangerous level judgment of the mining stress of the target area is performed based on the mining stress prediction result of the target area, and the method comprises the following steps: judging the dangerous grade of the mining stress of the target area as a first-level early warning when the mining stress prediction result of the target area is in a first preset range; And when the mining stress prediction result of the target area exceeds the first preset range, judging that the dangerous level of the mining stress of the target area is a secondary early warning.
8. An intelligent close range coal mining face support monitored control system, which characterized in that includes: The coal seam prediction module is used for inputting the coal seam geological feature data of the target area into the association model for predicting the distribution and change trend of the coal seam so as to obtain a coal seam prediction result of the target area; the mining stress prediction module is used for executing initial supporting scheme matching of the supporting structure based on the obtained coal seam prediction result, acquiring real-time monitoring data flow of the supporting structure after supporting the supporting structure according to the matched initial supporting scheme, and inputting the real-time monitoring data flow into a mapping relation model for predicting mining stress of a target area so as to obtain a mining stress prediction result of the target area; the support condition monitoring module is used for monitoring the support condition of the support structure of the target area according to the coal seam prediction result and the mining stress prediction result of the target area, and adjusting the support scheme of the support structure when the support condition is monitored to be abnormal.
9. A machine-readable storage medium having instructions stored thereon, which when executed by a processor, cause the processor to be configured to perform the intelligent close proximity coal seam mining face support monitoring method of any 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, wherein the processor, when executing the computer program, implements the intelligent close range coal mining face support monitoring method of any one of claims 1 to 7.

Description

Intelligent short-distance coal seam mining operation face support monitoring method and system Technical Field The invention relates to the technical field of coal seam mining, in particular to an intelligent close range coal seam mining operation surface support monitoring method, an intelligent close range coal seam mining operation surface support monitoring system, a machine-readable storage medium and electronic equipment. Background The parameters such as the geological structure of the coal bed, the thickness of the coal bed, the inclination angle and the like are comprehensively analyzed and predicted through a machine learning algorithm, so that important reference data is provided for supporting and monitoring the working face of the close-range coal bed exploitation, however, certain deviation exists between the variation of the coal bed and a predicted result in the actual exploitation process, and the stress state and the deformation condition of the supporting structure need to be monitored in real time to ensure the safety. How to effectively evaluate the supporting effect of the supporting structure in the exploitation process, identify weak links and potential risk points, and adjust supporting parameters so as to ensure the supporting safety and stability of the working face of the close-range coal seam exploitation are the problems to be solved at present. Disclosure of Invention The invention aims to provide an intelligent monitoring method and system for supporting a close-range coal seam mining operation surface, which at least solve the problems of effectively evaluating the supporting effect of a supporting structure, identifying weak links and potential risk points, and adjusting supporting parameters to ensure the supporting safety and stability of the close-range coal seam mining operation surface in the mining process. In order to achieve the above object, a first aspect of the present invention provides an intelligent monitoring method for a near-distance coal mining face support, including: Inputting the coal seam geological feature data of the target area into a correlation model for predicting the distribution and change trend of the coal seam so as to obtain a coal seam prediction result of the target area; Performing initial supporting scheme matching of the supporting structure based on the obtained coal seam prediction result, acquiring real-time monitoring data flow of the supporting structure after supporting the supporting structure according to the matched initial supporting scheme, and inputting the real-time monitoring data flow into a mapping relation model for predicting mining stress of a target area so as to obtain a mining stress prediction result of the target area; And monitoring the supporting condition of the supporting structure of the target area according to the coal seam prediction result and the mining stress prediction result of the target area, and adjusting the supporting scheme of the supporting structure when the abnormal supporting condition is monitored. Optionally, the rule for establishing the association model includes: Acquiring historical coal seam geological feature data, and carrying out data cleaning and normalization processing on the historical coal seam geological feature data one by one, wherein the historical coal seam geological feature data at least comprises one or more of a coal seam geological structure, a coal seam thickness, a coal seam inclination angle, a coal seam depth and a coal content; And establishing an initial association model by using a support vector machine, taking the processed historical coal seam geological feature data and the corresponding coal seam distribution and change trend data as a first training set, and training and iterative optimization of the initial association model by using the first training set until the prediction deviation RMSE is smaller than or equal to a preset threshold value to obtain the association model. Optionally, the acquiring rule of the real-time monitoring data flow of the supporting structure includes: The method comprises the steps of acquiring stress state data and deformation data of a supporting structure, which are acquired in real time by sensors arranged on a coal seam mining working face of a target area, wherein the arrangement scheme of the sensors is determined based on stress points and deformation areas of the supporting structure determined by a matched initial supporting scheme; And transmitting the obtained stress state data and deformation data of the support structure to a ground monitoring center to form a real-time monitoring data stream of the support structure. Optionally, before inputting the real-time monitoring data stream into the mapping relation model, the method further comprises: After preprocessing the real-time monitoring data stream by adopting a time sequence analysis algorithm, removing abnormal values exceeding a preset normal range in t