Seismic Design Value Evaluation Based on Checking Records and Site Geological Conditions Using Artificial Neural Networks

Abstract

This study proposes an improved computational neural network model that uses three seismic parameters (i.e., local magnitude, epicentral distance, and epicenter depth) and two geological conditions (i.e., shear wave velocity and standard penetration test value) as the inputs for predicting peak ground acceleration—the key element for evaluating earthquake response. Initial comparison results show that a neural network model with three neurons in the hidden layer can achieve relatively better performance based on the evaluation index of correlation coefficient or mean square error. This study further develops a new weight-based neural network model for estimating peak ground acceleration at unchecked sites. Four locations identified to have higher estimated peak ground accelerations than that of the seismic design value in the 24 subdivision zones are investigated in Taiwan. Finally, this study develops a new equation for the relationship of horizontal peak ground acceleration and focal distance by the curve fitting method. This equation represents seismic characteristics in Taiwan region more reliably and reasonably. The results of this study provide an insight into this type of nonlinear problem, and the proposed method may be applicable to other areas of interest around the world.

Computational Intelligence Application in Modeling Seismic Record and Soil Test Data at a Specified Area

“…However, this directly predicted result seems too conservative, a modified result by using square root of the sum of the square [25], for checking stations within each of the subdivision zones, are calculated and included in the plot. It can be seen that there are 3 subdivision zones (A7, A8, and A9) exhibit a higher horizontal PGA than the design value, and the tendency is also similar to previous research [26] Therefore, this modified result is believed to have a more reliability for the case studied herein, and the identified potential hazardous subdivision zones should pay more precautious in relevant engineering applications. For the seismic zone B, as the PGAs obtained from both NN+GA and NN models are lower than that of the design value (0.23g), so all of prediction results comply with design standard in building code.…”

Incorporating global search capability of a genetic algorithm into neural computing to model seismic records and soil test data

“…Three subdivision zones (i.e. A7, A8, and A9) exhibited a higher horizontal PGA than the design value, and the tendency was similar to that reported in previous studies [20,46]. Therefore, this modified result is believed to have a more favourable reliability for the case in this study, and the identified potential hazardous subdivision zones should be examined with precaution in relevant engineering applications.…”