Comparative Investigation of BP and RBF Neural Network on Seismic Damage Prediction of Multistory Brick Buildings

Seismic damage prediction of multistory brick buildings is a multi-factor nonlinear complex problem, this paper analyzed the deficiencies of the traditional methods for predicting the seismic damage and the discrepancies of BP and RBF neural network prediction model, and then the simulation and prediction were carried out. The results show that RBF network more suitable for seismic damage prediction of multistory brick buildings with the noise and distortion of the input dates, and RBF network structure elements and parameters are studied and obtained. Analytical method and process discussed in this paper can also be applied to seismic damage prediction of brick buildings of urban earthquake disaster prevention planning.