Research on the method of rbf network predicting attenuation of earthquake peak ground acceleration.

Abstract: Seismic peak ground acceleration(PGA) is one of the important factors for reflecting the potential earthquake risk. PGA attenuation model commonly used assumed mathematical model, the use of regression analysis to establish the relevant parameters, but the model itself invariance restrictions on the range and accuracy. This paper proposes the application of RBF neural network model predicted PGA attenuation, the steps of RBF network structure elements and parameters are analyzed. With example the research verify that the predictive value base on the RBF neural network model is more consistent with the actual value. The analytic method and process discussed in this paper can also be applied to calculate and draw up the seismic ground motion parameter zonation in different region. [Copyright &y& Elsevier]