A comprehensive review on identification of the geomaterial constitutive model using the computational intelligence method

Abstract

It is crucial to determine geomaterial constitutive models to analyze the mechanical behavior of geomaterials and geotechnical engineering stability. Thus, identification of a geomaterial constitutive model is a very important aspect of back analysis. Because the real mechanical behavior of geomaterials are very complicated, it is difficult to identify a suitable geomaterial constitutive model based on traditional methods. Therefore, some computational intelligence methods have been used to solve this problem, and many related studies have been performed. In this study, previous research is reviewed according to the following four aspects: constitutive model approach via an artificial neural network, constitutive model description via an artificial neural network, constitutive model selection via an evolutionary computation, and constitutive model construction via an evolutionary computation. Moreover, the state-of-the-art research advancement of the four research aspects is summarized. The merits and demerits of these research aspects have been comprehensively analyzed and discussed. Finally, possible research directions to identify a geomaterial constitutive model based on computational intelligence are also provided.