期刊
ENVIRONMENTAL EARTH SCIENCES
卷 76, 期 5, 页码 -出版社
SPRINGER
DOI: 10.1007/s12665-017-6523-y
关键词
Liquefaction; Genetic algorithm; Particle swarm optimization; Backpropagation
资金
- CAS Pioneer Hundred Talents Program
This study presents two optimization techniques: genetic algorithm (GA) and particle swarm optimization (PSO), to improve the efficiency of backpropagation (BP) neural network model for predicting liquefaction susceptibility of soil. A detailed parametric study is designed and performed to find the optimal parameters of GA and PSO, respectively. The database used in this study includes 166 CPT-based field observations from more than eight major earthquakes between 1964 and 1983. Six factors including cone resistance, total vertical stress, effective vertical stress, depth of penetration, normalized peak horizontal acceleration at ground surface and earthquake magnitude are selected as the evaluating indices. The predictions from the PSO-BP model were compared with those from two models: BP and GA-BP. The study concluded that the proposed PSO-BP model improves the classification accuracy and is a feasible method in predicting soil liquefaction.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据