In view of the difficulty of tuning the traditional prediction model parameters and the lack of high prediction accuracy,this paper introduced the sand cat swarm optimization(SCSO)and the bidirectional gated recurrent unit(BIGRU)into the dam deformation analysis and constructed a dam deformation prediction model based on SCSO-BIGRU by automatically optimizing the parameters of the BIGRU model through SCSO.By taking the vertical monitoring data of a dam as an example,the SCSO-BIGRU model and the comparison model were analyzed.The results show that the SCSO-BIGRU model has higher prediction accuracy,and the root mean square error(RMSE),average absolute error(MAE),and correlation coefficient R2 obtained are 0.111 5,0.142 2,and 0.997 1,respectively.The accuracy evaluation indexes are better than those of the BIGRU model and the GRU model,which can provide a reference for the accurate prediction of dam deformation.
万方数据
维普
