主元分析-神经网络岩爆等级预测模型

Prediction model of rockburst grade based on PCA-neural network

为准确可靠地预测岩爆灾害,构建结合主元分析法(PCA)的径向基神经网络(RBFNN)、概率神经网络(PNN)和广义回归神经网络(GRNN)岩爆预测模型。选取6个常用的参数构成岩爆预测指标体系,采用PCA消除各指标间的相关性并降维,得出3个线性无关的主元即岩爆综合预测指标Y1、Y2和Y3,构成RBFNN、PNN、GRNN这3种神经网络的输入向量。研究结果表明:这3种PCA-神经网络模型,其岩爆预测结果优于对应的RBFNN、PNN、GRNN模型,提高预测准确率并缩短运算时间。从局部准确率、整体准确率及运算时间这3个方面综合比较,各模型的预测能力从强到弱依次为:PCA-GRNN> PCA-PNN> PCA-RBFNN> PNN> GRNN> RBFNN。

In order to predict rockburst disaster accurately and reliably,RBFNN,PNN and GRNN prediction models based on PCA were established. Six frequently-used parameters were chosen to constitute prediction indicator system, PCA was used to eliminate correlation of indicators and reduce their dimensionality. Then, three linearly independent pivot elements were obtained, namely three comprehensive indicators Y1,Y2 and Y3,which constituted input vectors of RBFNN,PNN and GRNN neural networks. The results show that predictions of three PCA neural network models are better than original RBFNN,PNN and GRNN models as they not only improve accuracy,but also shorten operation time. Moreover,according to comparison from three aspects of local accuracy,overall accuracy and operation time,these three models ranks as PCA-GRNN > PCA-PNN > PCA-RBFNN > PNN > GRNN >RBFNN from strong to weak based on their accuracy ability.