中国矿山工程

This study proposes a mining slope monitoring network optimization method that integrates numerical simulation and clustering analysis algorithms to address the problems of sparse monitoring networks and insufficient spatial representativeness caused by equipment costs and terrain limitations in mining slope monitoring. This method first explores the stability evolution law of slopes under normal and rainfall conditions based on the strength reduction method, and divides the slope risk areas; On this basis, particle swarm optimization algorithm is introduced to determine the clustering centers of each partition, and redundant monitoring points are eliminated by combining spatial correlation coefficient, ultimately achieving the optimization of the mining slope monitoring network. This article takes the Chongqing Huaxin limestone dolomite mine as a case study to verify the effectiveness of the monitoring network optimization method. The results showed that after optimization, the number of monitoring points decreased from 35 to 18, and the overlapping information entropy decreased by 293%. While ensuring monitoring coverage, the monitoring cost was significantly reduced, providing a theoretical basis for the economic monitoring of mine slopes.