A combined machine learning/search algorithm-based method for the identification of constitutive parameters from laboratory tests and in-situ tests

Accurate numerical analysis in geotechnical engineering heavily relies on the constitutive model and its parameters. The advanced constitutive model can describe the complex mechanical behaviors of soil that may involve a number of parameters. However, determining the values of constitutive parameters always relies on manual trial-and-error, which can be a time-consuming process and not conducive to widespread application. This paper presents an identification method that combines machine learning with search algorithm based on the laboratory and in-situ testing. Initially, the sensitivity of constitutive parameters was analyzed by investigating the effects of variations in soil overconsolidation and structural parameters on the results of triaxial and pressuremeter tests. Subsequently, the initial state parameter values and material control parameter ranges of the soil can be identified from the triaxial tests, this is achieved by using the neural network model. In order to accurately determine the parameters value, the numerical model was established based on in-situ pressuremeter test, and traversal algorithm was implemented to search for the optimal fit values within the range of material control parameters. Finally, the proposed identification method was applied to layers 3–5 of Shanghai clay, and the inverted parameters exhibited a good fit with the outcomes of triaxial tests and pressuremeter tests. The combination of laboratory and in-situ testing can enhance the reliability of obtaining constitutive parameters, and this method provides an insight into the parameters identification for advanced constitutive models.