Simulation of Silty Clay Compressibility Parameters Based on Improved BP Neural Network Using Bayesian Regularization

作者：CAI Run,PENG Tao,WANG Qian,HE Fanmin,ZHAO Duoying

摘要：Soil compressibility parameters are important indicators in the geotechnical field and are affected by various factors such as natural conditions and human interference.When the sample size is too large,conventional methods require massive human and financial resources.In order to reasonably simulate the compressibility parameters of the sample,this paper firstly adopts the correlation analysis to select seven influencing factors.Each of the factors has a high correlation with compressibility parameters.Meanwhile,the proportion of the weights of the seven factors in the Bayesian neural network is analyzed based on Garson theory.Secondly,an output model of the compressibility parameters of BR-BP silty clay is established based on Bayesian regularized BP neural network.Finally,the model is used to simulate the measured compressibility parameters.The output results are compared with the measured values and the output results of the traditional LM-BP neural network.The results show that the model is more stable and has stronger nonlinear fitting ability.The output of the model is basically consistent with the actual value.Compared with the traditional LMBP neural network model,its data sensitivity is enhanced,and the accuracy of the output result is significantly improved,the average value of the relative error of the compression coefficient is reduced from 15.54%to 6.15%,and the average value of the relative error of the compression modulus is reduced from 6.07%to 4.62%.The results provide a new technical method for obtaining the compressibility parameters of silty clay in this area,showing good theoretical significance and practical value.

发文机构：Chengdu Surveying Geotechnical Research Institute Key Laboratory of Loess Earthquake Engineering Lanzhou Institute of Seismology

关键词：SiltyclayCOMPRESSIBILITYCorrelationanalysisBayesianregularizationNeuralnetworks

分类号： TP1[自动化与计算机技术—控制理论与控制工程]