Soil liquefaction modeling by Genetic Expression Programming and Neuro-Fuzzy

摘要: Liquefaction of soils induced by the earthquake is one major complex problems for geotechnical engineering. It generally determined from in situ tests and laboratory test which application very difficult, expensive time consuming. They also require extreme cautions labor. Hence development new models prediction liquefaction potential provides fairly significant facility to design constructions. This study presents Genetic Expression Programming (GEP) Adaptive Neuro-Fuzzy (ANFIS) computing paradigm forecast safety factor soils. To develop models, a total 569 data set collected literature were used. Five parameters such as standard penetration ((N"1)"6"0), percentage finest content (FC), effective overburden stresses (@s'), cyclic stress ratios (CSR) angle shearing resistance (@f') used input parameters. The performance was comprehensively judged using several statistical verification tools. results revealed that GEP ANFIS are promising approach soil capable representing relationship between seismic properties their potential.