Analysis of Prediction Model of Failure Depth of Mine Floor Based on Fuzzy Neural Network

Abstract

To obtain the law of failure depth of mine floor and its influencing factors during coal mining process, a large amount of field measured data of floor failure depth was collected, and five influencing factors were summarized based on the analysis of data and years of field experience. The five main influencing factors were the length of working face, mining depth, mining height, dip angle and floor anti-sabotage ability. Based on fuzzy math membership and membership function, the five factors were preliminarily processed, then the sensitivity ranking was obtained according to the weight of influencing factors, and the prediction model of failure depth of mine floor was established based on the fuzzy neural network. It was shown that the order of the weight of the five factors was the length of working face > dip angle > floor anti-sabotage ability > mining depth > mining height. The maximum weight of the length of working face was 0.3678. The accuracy of the model was high and the prediction results were in good agreement with the engineering practice according to verification results. To ensure the maximum economic benefit of mine, some measures and methods through human intervention to reduce the failure depth of floor and ensure mine safety were suggested.