Deflection prediction analysis of corrugated steel web composite box- girder bridge based on MEC-BP neural network

Corrugated steel web continuous rigid frame bridge has the advantages of low resource consumption and low environmental impact. It will become an important part of low-carbon construction of civil engineering. This paper presents an effective method for predicting the deflection of continuous rigid frame bridges with corrugated steel webs. The method includes three analysis stages: (1) obtain the data set to establish the prediction model (2) establish the optimized neural network model combined with mind evolutionary computation (MEC) algorithm and back propagation (BP) algorithm. (3) The optimized mec-bp model is used to predict the deflection of CSWS PC bridge construction. The feasibility of this method is verified by an actual CSWS PC bridge. The results show that compared with the traditional BP model, this method has better prediction performance, can accurately predict the deflection of CSWS PC Bridge in the construction process, and provide effective help for construction control.