CPT-BASED LIQUEFACTION ASSESSMENT BY USING FUZZY-NEURAL NETWORK

Authors

Shuh-Gi Chern, Department of Habor and River Engineering, National Taiwan Ocean University, Keelung, Taiwan, R.O.C.Follow
Ching-Yinn Lee, Department of Habor and River Engineering, National Taiwan Ocean University, Keelung, Taiwan, R.O.C.
Chin-Chen Wang, Department of Habor and River Engineering, National Taiwan Ocean University, Keelung, Taiwan, R.O.C.

Abstract

Because of the increasing popularity worldwide of the cone penetration test (CPT) for site characterization, significant progress on the simplified CPT-based methods has been made for evaluation of earthquake induced liquefaction potential of soils. In this study, a fuzzy-neural network combined with 466 CPT field observations is developed to evaluate liquefaction potential of soils. The proposed model combines fuzzy theory with subtractive clustering algorithm to establish a fuzzy-neural system. The study indicates that fuzzy-neural network can successfully describe the complex relationship between seismic parameters, soil parameters, and the liquefaction potential. The fuzzy-neural network model is found to have very good predictive ability and is expected to be very reliable for evaluation of liquefaction potential.

Recommended Citation

Chern, Shuh-Gi; Lee, Ching-Yinn; and Wang, Chin-Chen (2008) "CPT-BASED LIQUEFACTION ASSESSMENT BY USING FUZZY-NEURAL NETWORK," Journal of Marine Science and Technology: Vol. 16: Iss. 2, Article 6.
DOI: 10.51400/2709-6998.2024
Available at: https://jmstt.ntou.edu.tw/journal/vol16/iss2/6