首页|Rockburst Prediction Using Evolutionary Support Vector Machine
Rockburst Prediction Using Evolutionary Support Vector Machine
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
Rockburst is a disaster occurred frequently in hydroelectric powerhouse， mining tunnel， road and railway tunnel， and nuclear power station etc。 Because of the complexity， fuzzy， and nonlinear of rock mechanics， we don't know the mechanism of rockburst。 So， it is difficult to predict rockburst using the conventional method such as mathematics and elastic mechanics。 Based on the analysis of main cause of rockbust， we propose a novel method， termed evolutionary support vector machine(SVM) which combined support vector machine and genetic algorithm ， to predict rockburst。 Support vector machine is a new generation learning system based on statistical learning theory， can find global optimal solutions for problem with small training samples， high dimension， non-linearity。 The relationship between rockbust and it's influence factor is presented by support vector machine。 This model is learned from case histories and predict the rockburst of similar conditions。 Three support vector machine models have been build for VCR stope， carbon leader stope and tunnel in deep gold mines， respectively。 The results show this method is feasible and appropriate and has significant potenetial。
NETL
