Dynamical Forecasting Technology for Coalmine Safety

摘要：

Safety forecasting model are also founded by the MATLAB software. Three types of NN models and training functions are comparably studied to prove that the TRAINDM learning rules continues for too long, the TRAINBR can minimizes the error than TRAINLM and not continues for so long as TRAINDM. Therefore, TRAINBR maybe is the most adaptive learning rule of coalmine safety forecasting. And if the forecasting model is so simple that it can not meet with the precise requirements.

关键词： coalmine safety forecasting artificial neural network network structure training functions

作者: XU Man-gui GAO Jian-ying

作者单位: Energy College of Xian University of Science and Technology, 710054 P.R.C Department of Foreign Language of Xian University of Science and Technology, 710054 P.R.C

会议类型: 国际会议

会议名称: The 2007 International Symposium on Safety Science and Technology(2007采矿科学与安全技术国际学术会议)

会议地点: 河南焦作

会议语种:英文

页码: 2231-2235

在线出版日期: 2007-04-17（万方平台首次上网日期，不代表论文的发表时间）