Application of Physics-Informed Neural Networks for Forward and Inverse Analysis of Pile-Soil Interaction

TL;DR

This paper demonstrates how Physics-Informed Neural Networks (PINNs) can effectively analyze and invert pile-soil interaction problems, especially handling material discontinuities and using localized data for soil parameter identification.

Contribution

It introduces a domain-decomposition multi-network PINN model to address discontinuities in pile-soil analysis and applies it to both forward and inverse problems in layered formations.

Findings

PINNs successfully model abrupt material property changes.

Localized data enables effective soil parameter inversion.

Model performs well under various boundary conditions.

Abstract

The application of the Physics-Informed Neural Networks (PINNs) to forward and inverse analysis of pile-soil interaction problems is presented. The main challenge encountered in the Artificial Neural Network (ANN) modelling of pile-soil interaction is the presence of abrupt changes in material properties, which results in large discontinuities in the gradient of the displacement solution. Therefore, a domain-decomposition multi-network model is proposed to deal with the discontinuities in the strain fields at common boundaries of pile-soil regions and soil layers. The application of the model to the analysis and parametric study of single piles embedded in both homogeneous and layered formations is demonstrated under axisymmetric and plane strain conditions. The performance of the model in parameter identification (inverse analysis) of pile-soil interaction is particularly investigated. It is shown that by using PINNs, the localized data acquired along the pile length - possibly obtained via fiber optic strain sensing - can be successfully used for the inversion of soil parameters in layered formations.