Gas extraction coupling anomaly monitoring and grading method and system fused with AI time sequence analysis

By integrating AI time-series analysis, dynamically adjusting the sampling frequency and performing multi-dimensional time-series hazard index analysis, and combining adaptive compression factor particle swarm optimization algorithm to identify gas extraction coupling anomalies, the problem of insufficient real-time performance, accuracy and stability of existing monitoring and early warning technologies is solved, and efficient monitoring of gas extraction anomalies is achieved.

CN122286604APending Publication Date: 2026-06-26GUIZHOU UNIV +1
4 Cites 0 Cited by

Patent Information

Application Number
CN202610775786.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-06-01
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Existing gas extraction anomaly monitoring technologies suffer from problems such as coarse time-series signal processing, reliance on manually fixed thresholds for identifying abrupt change trends, and the lack of dynamic iteration mechanisms for monitoring data and analysis models, resulting in insufficient real-time performance, accuracy, and stability of monitoring and early warning.

Method used

By employing a fusion AI time series analysis approach, coupled parameter time series data are collected through multiple types of monitoring sensors. The sampling frequency is dynamically adjusted, and step-wise time series processing and multi-dimensional time series hazard index analysis are performed. The good point set improved adaptive compression factor particle swarm optimization algorithm is used to identify coupled mutation trends and construct a dynamic hazard index to achieve bidirectional dynamic feedback calibration and output the risk level of the target monitoring area.

Benefits of technology

It achieves efficient capture of coupled abrupt changes such as instantaneous surges in gas outflow and reverse stress recovery, improves the accuracy and timeliness of abrupt change identification, ensures self-iterative improvement of early warning accuracy, and has good scenario expansion capabilities and engineering practicality.

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

Abstract

The invention discloses a gas extraction coupling anomaly monitoring and grading method and system fused with AI time sequence analysis, and relates to the technical field of coal mine safety monitoring, and the method comprises the steps: collecting coupling parameter time sequence data, and generating a multi-time-resolution original time sequence data set; performing stepped time sequence processing on the original time sequence data set to generate regular time sequence data; constructing a multi-dimensional time sequence risk index sequence, and mapping the regular time sequence data to the sequence; the coupling mutation trend is adaptively recognized through a good point set improved adaptive compression factor particle swarm optimization algorithm, and a mutation recognition result is output; performing weighted fusion on the multi-dimensional time sequence dangerousness indexes to generate dynamic dangerousness indexes, and dynamically adjusting the updating frequency of the dynamic dangerousness indexes according to the mutation recognition result; and comparing the latest dynamic risk index with a preset grading threshold value, and outputting the current risk grade of the target monitoring area. Therefore, the real-time performance, the accuracy and the stability of gas extraction abnormity monitoring are improved.
Need to check novelty before this filing date? Find Prior Art