节理岩体地层沉陷的进化神经网络预测方法研究  

Prediction Method for Evolutionary Neural Net of Strata Subsidence of Rock Mass

作　　者：姚大勇[1] 邵军[1] 

机构地区：[1]辽宁工程技术大学,辽宁阜新123000

出　　处：《矿业安全与环保》2002年第3期11-12,共2页Mining Safety & Environmental Protection

摘　　要：根据神经网络的特点,特别是岩层高度非线性特点,在网络结构的确定和模拟过程中采用了遗传算法,进行全局优化,达到了比较好的效果。Strata subsidence is one of com-mon geo logic disasters in mines.The high nonlinearity and com-plex of rock strata often make this disaster to be difficultly pre-dicted accurate ly by the existing prediction method.The paper,based on the feature of neural net and the high nonlinearity char-acteristic of rock strata,gives an overall optimization of the neural net with genetic method in the process of the determination and simulation of net structure,and good results were achieved.

关 键 词：岩体 神经网络 地层沉陷 遗传算法 拓扑结构 

分 类 号：TD325[矿业工程—矿井建设]