一种用于沿空留巷的液压支架时空压力监测预警系统及方法

By combining wireless sensors and positioning tags with adaptive sampling frequency and dynamic graph neural networks, the problems of cable damage and early warning lag in the hydraulic support pressure monitoring system along the goaf were solved. This enabled spatiotemporal pressure monitoring and intelligent early warning of the hydraulic support, improving prediction accuracy and system stability, and reducing safety risks.

CN121993259BActive Publication Date: 2026-07-17TAIYUAN XIANGMING INTELLIGENT CONTROL TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202610431318.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2026-04-02
Publication Date
2026-07-17
Estimated Expiration
2046-04-02

AI Technical Summary

Technical Problem

Existing hydraulic support pressure monitoring systems suffer from issues such as easily damaged cables, difficult maintenance, and high power consumption of wireless sensors in goaf-side roadway environments. Furthermore, they lack accurate perception of the spatial position of hydraulic supports and in-depth understanding of complex mine pressure patterns, resulting in low early warning accuracy and high false alarm rate, making them unsuitable for monitoring the dynamic movement of supports.

Method used

Wireless sensors and positioning tags are used to acquire the pressure and spatial position of the lower chamber of the hydraulic support column. Combined with adaptive sampling frequency control, multi-source data preprocessing, dynamic graph neural network model and reinforcement learning algorithm, spatiotemporal pressure monitoring and intelligent early warning are realized. Through spatiotemporal feature matrix construction, real-time positioning calibration, physical constraints and self-learning mechanism, the support relocation strategy is optimized.

Benefits of technology

It enables comprehensive monitoring and accurate early warning of spatial and temporal pressure changes in hydraulic supports, improves prediction accuracy and robustness, reduces safety risks, enhances operational efficiency and system stability, and adapts to pressure change characteristics under different working conditions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121993259B_ABST
    Figure CN121993259B_ABST
Patent Text Reader

Abstract

本申请提供了一种用于沿空留巷的液压支架时空压力监测预警系统及方法,属于矿山压力监测领域;解决了现有沿空留巷压力监测维度单一、预警滞后、无法适应动态环境的问题;该方法包括以下步骤:多源数据采集与预处理;时空特征矩阵构建;基于实时定位的时空矩阵动态校准;时空关联特征提取;基于物理约束的动态图神经网络模型的来压预测,将提取的时空关联特征作为输入特征矩阵输入至动态图神经网络模型中进行来压预测,同时在动态图神经网络模型的损失函数中引入物理不可满足性惩罚使得动态图神经网络模型预测的来压符合支架工作阻力与顶板下沉量之间的物理约束;基于时空注意力权重的风险辨识与动态预警;本申请应用于巷道来压预警。
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Hydraulic support control system and method for coal mine gob-side entry retaining

    CN115573756A

  • Roof pressure grading method

    CN118154046A