Application of ANN to Prediction of Earthquake Influence

摘要

The maximum of earthquake affecting coefficient is a main parameter of earthquake response spectra, which is the key of seismic microzonation and design of earthquake resistant structures. Because the distribution of the maximum of earthquake affecting coefficient is controlled by basement rock and site condition, the relationship between the maximum of earthquake affecting coefficient and influencing factors is complicated. In order to design earthquake response spectra subtly, the calculating model is constructed on the basis of artificial neural network (ANN), which makes the parameter (the maximum of earthquake affecting coefficient) become a variable. In Tangshan City, the calamitous earthquake in 1976 deprived of 243,000 peoplepsilas lives, and more attention has been paid to seismic microzonation. As an example application, the distribution of the maximum of earthquake affecting coefficient is calculated precisely, and it is applied to the design of earthquake response spectra and seismic microzonation in Tangshan City. Finally, the calculating results are analysed and some advice is proposed for the city planning for disaster prevention.