Evaluation of Seismic Design Values in the Taiwan Building Code by Using Artificial Neural Network
Tienfuan Kerh; J.S. Lai; D. Gunaratnam; and R. Saunders

doi:10.3970/cmes.2008.026.001
Source CMES: Computer Modeling in Engineering & Sciences, Vol. 26, No. 1, pp. 1-12, 2008
Download Full length paper in PDF format. Size = 546,051 bytes
Keywords building code, design value criteria, neural network, peak ground acceleration, potential hazardous locations, curve fitting model.
Abstract Taiwan frequently suffers from strong ground motion, and the current building code is essentially based on two seismic zones, A and B. The design value of horizontal acceleration for zone A is 0.33g, and the value for zone B is 0.23g. To check the suitability of these values, a series of actual earthquake records are considered for evaluating peak ground acceleration (PGA) for each of the zones by using neural network models. The input parameters are magnitude, epicenter distance, and focal depth for each of the checking stations, and the peak ground acceleration is calculated as the output with the use of spatial relationship in an averaged sense. The neural network model estimations showed that for 5 of the locations, out of the 24 locations considered, the design value recommended in the building code would be exceeded. In addition, a curve fitting model, PGA = 8.96/Df, is developed for the relationship between horizontal PGA and focal distance (Df), and reflecting the essential characteristics of strong motion in region investigated. The neural network model and the mathematical equation can provide useful information for both the relevant government agencies and practicing engineering designers.
PDF download PDF