A worldwide SPT-based soil liquefaction triggering analysis utilizing gene expression programming and Bayesian probabilistic method  

作　　者：Maral Goharzay Ali Noorzad Ahmadreza Mahboubi Ardakani Mostafa Jalal 

机构地区：[1]Faculty of Civil,Water and Environmental Engineering,Shahid Beheshti University [2]Zachry Department of Civil Engineering,Texas A & M University,College Station

出　　处：《Journal of Rock Mechanics and Geotechnical Engineering》2017年第4期683-693,共11页岩石力学与岩土工程学报（英文版）

摘　　要：In this context,two different approaches of soil liquefaction evaluation using a soft computing technique based on the worldwide standard penetration test(SPT) databases have been studied.Gene expression programming(GEP) as a gray-box modeling approach is used to develop different deterministic models in order to evaluate the occurrence of soil liquefaction in terms of liquefaction field performance indicator(LI) and factor of safety(FS) in logistic regression and classification concepts.The comparative plots illustrate that the classification concept-based models show a better performance than those based on logistic regression.In the probabilistic approach,a calibrated mapping function is developed in the context of Bayes’ theorem in order to capture the failure probabilities(PL) in the absence of the knowledge of parameter uncertainty.Consistent results obtained from the proposed probabilistic models,compared to the most well-known models,indicate the robustness of the methodology used in this study.The probability models provide a simple,but also efficient decision-making tool in engineering design to quantitatively assess the liquefaction triggering thresholds.In this context,two different approaches of soil liquefaction evaluation using a soft computing technique based on the worldwide standard penetration test(SPT) databases have been studied.Gene expression programming(GEP) as a gray-box modeling approach is used to develop different deterministic models in order to evaluate the occurrence of soil liquefaction in terms of liquefaction field performance indicator(LI) and factor of safety(F_S) in logistic regression and classification concepts.The comparative plots illustrate that the classification concept-based models show a better performance than those based on logistic regression.In the probabilistic approach,a calibrated mapping function is developed in the context of Bayes' theorem in order to capture the failure probabilities(P_L) in the absence of the knowledge of parameter uncertainty.Consistent results obtained from the proposed probabilistic models,compared to the most well-known models,indicate the robustness of the methodology used in this study.The probability models provide a simple,but also efficient decision-making tool in engineering design to quantitatively assess the liquefaction triggering thresholds.

关 键 词：LIQUEFACTION Soft computing technique Gene expression programming(GEP) Deterministic model Bayes' theorem 

分 类 号：TU472[建筑科学—结构工程]