Intelligent analysis and monitoring method of mine pressure based on machine learning

The machine learning-based method for analyzing mine pressure data from liquid pressure sensors addresses the inaccuracy in existing monitoring systems by extracting key features and calculating anomaly indicators, resulting in improved detection and safety in coal mines.

CN119474758BActive Publication Date: 2025-03-25JINAN FUSHEN HINGGAN TECH CO LTD
2 Cites 0 Cited by

Patent Information

Application Number
CN202510045959.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-01-13
Publication Date
2025-03-25
Estimated Expiration
2045-01-13

AI Technical Summary

Technical Problem

Existing methods for monitoring mine pressure (mining pressure) using liquid pressure sensors in coal mines are inadequate due to the complexity of geological conditions and varying coal extraction rates, leading to inaccurate identification of pressure anomalies and delayed warnings.

Method used

A machine learning-based method that processes pressure data from liquid pressure sensors by extracting key features such as extreme value sequences, calculating pressure deviation, and using sliding window analysis to generate anomaly indicators for real-time monitoring.

Benefits of technology

This approach enhances the accuracy of mine pressure anomaly detection, providing timely warnings and improving safety by analyzing pressure data trends and deviations, thus reducing the risk of accidents.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present invention relates to the technical field of data processing, and in particular to a method for intelligent analysis and monitoring of mine pressure based on machine learning. The method collects pressure data of any hydraulic support to obtain a pressure data sequence; obtains multiple pressure subsequences according to maximum value data and minimum value data in the pressure data sequence; screens target pressure subsequences, obtains the pressure deviation degree of each target pressure subsequence, and forms a pressure deviation degree sequence; performs STL decomposition on the pressure deviation degree sequence to obtain a corresponding trend item sequence, and obtains a pressure anomaly index according to the trend item sequence; obtains the pressure anomaly index of all hydraulic supports, performs mine pressure anomaly monitoring and early warning according to the pressure anomaly index of all hydraulic supports, uses the pressure data between the maximum value data and the minimum value data as periodic pressure data, and performs mine pressure anomaly monitoring according to the difference in the pressure data change amplitude of multiple periodic pressure data, thereby improving the accuracy of anomaly monitoring.
Need to check novelty before this filing date? Find Prior Art