Overpressure Distribution Prediction of Mine Gas Explosion Based on BP Neural Networks

摘要：

Gas disaster is one of important problems which concerning the safety of mine. The shock wave and harmful-air after explosive are the main damage for human. Moreover, the prevention measures to avoid gas explosion expanded are depended on the measurements and forecasts of blast overpressure. Due to various factors, gas explosion overpressure depends on the experiment to determine or establish equation calculated based on the experimental results longterm, however, the calculated results and experimental results are not in accordance. Therefore, the paper uses ANN s nonlinear advantage and according to previous experimental analysis to predict the relationship between overpressure and measuring point. First extract the relevant data as learning samples, then use BP neural network training them after normalized. The results show that application of ANN prediction can significantly reduce the forecast error, and it is suitable for mining enterprises to operate.

关键词： gas explosion overpressure ANN prediction

作者: WANG Yajun YANG Yingdi LI Jiangtao

作者单位: Department of Safety Engineering, Heilongjiang Institute of Science and Technology, Harbin 150027, H College of Energy & Safety, Anhui University of Science and Technology, Huainan 232001, Anhui, China Shenyang Branch of China Coal Research Institute, Shenyang 110016, Liaoning, China

会议类型: 国际会议

会议名称: The 2010 International Symposium on Safety Science and Technology(2010 安全科学与技术国际会议)

会议地点: 杭州

会议语种:英文

页码: 1184-1188

在线出版日期: 2010-10-26（万方平台首次上网日期，不代表论文的发表时间）