Genetic Programming-Based Prediction Model for Microseismic Data

Abstract

Microseismic monitoring is a rock breakdown monitoring technology, and it has become a major technical tool for underground disaster warning and prevention. However, the massive amount of data involved in multipoint monitoring raises the difficulty for microseismic research when the research object involves underground large-scale complex engineering on time and space scales. The risk predictions of rockburst based on microseismic parameters rely only on the experience of researchers and subjective factors by the human factor. The dependent variable cannot be related to the acoustic and energy signals in the form of a functional equation. Therefore, we collected a large amount of microseismic data obtained from the working faces of Shoushan Mine of Pingdingshan Coal Group in China and filtered the data, then we constructed a prediction model of microseismic data based on underground spatial three-dimensional coordinates using genetic programming (GP), which can realize real-time monitoring and disaster warning of microseismic signals. We established the magnitude and energy prediction formulas by GP and obtained the real-time evolution of each parameter of the optimal individual. The results showed that the actual seismic and energy data of the working faces exhibited good agreement with those predicted by the prediction formulas. The high energy and seismic distribution were caused by the mining stress at the edge of working faces due to the excavation and unloading effect of the surface, and the energy and seismic evolution predicted by GP could also show this phenomenon well.