•  
  •  
 

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.

Download
COinS