BP-GRNN Model for Deformation Prediction of Diaphragm Wall Based on Multi-Source Data

During the foundation pit excavation, the deformation monitoring of supporting structure is directly related to the safety of construction. In this paper, the deformation monitoring and prediction of diaphragm wall are analyzed according to the construction conditions, the surrounding environment, security level and other buildings around. The single network model has the phenomenon of premature convergence and premature convergence. And the GRNN neural network has advantages in the fitting ability and computing speed. So the multi-source data BP-GRNN combined prediction model is established based on the analysis of the PSO-BP and GA-BP neural network prediction model, the model is demonstrated by examples. The prediction results show that the BP-GRNN combined prediction model has higher prediction accuracy and reliability. It will have a good application prospect in the deformation prediction of deep foundation pit and diaphragm wall.