Prediction of slope safety factor based on WOA-SVM model
Because the threat of slope instability to people's life and property is increasingly prominent,the evaluation of slope stability is of great significance for slope disaster prevention and control.When the traditional support vector machine model is used to estimate the slope safety factor,its accuracy is low,its convergence is poor,and the error of slope safety factor estimation is relatively large.Therefore,aiming at such problems,the whale optimization algorithm was adopted to optimize the support vector machine(SVM)model.WOA was used to find the optimal penalty coefficient c and kernel function parameter g of SVM,and the WOA-SVM model is established.The optimized WOA-SVM model was used to predict the slope safety factor,so as to achieve the purpose of improving the accuracy of slope safety factor estimation.The results showed that the mean absolute error(MAE),root mean square error(RMSE)and mean absolute percentage error(MAPE)of the WOA-SVM model were better than those of other models,indicating that the accuracy of slope safety factor estimation was higher than that of other models.Therefore,this model has certain reference value for slope stability analysis.
NETL
NSTL
万方数据
