Towards a Hybrid Digital Twin: Physics-Informed Neural Networks as Surrogate Model of a Reinforced Concrete Beam

TL;DR

This paper explores physics-informed neural networks as surrogate models for a reinforced concrete beam, demonstrating their ability to predict strains and identify natural frequencies, thus advancing hybrid digital twin development in civil engineering.

Contribution

It introduces two physics-informed neural network surrogate models for civil structures, integrating experimental data with physics laws, and compares their effectiveness with purely data-driven approaches.

Findings

Physics-informed models accurately predict strain distributions.

Incorporating physics improves extrapolation with limited data.

The models successfully identify the beam's natural frequency.

Abstract

In this study, we investigate the potential of fast-to-evaluate surrogate modeling techniques for developing a hybrid digital twin of a steel-reinforced concrete beam, serving as a representative example of a civil engineering structure. As surrogates, two distinct models are developed utilizing physics-informed neural networks, which integrate experimental data with given governing laws of physics. The experimental data (sensor data) is obtained from a previously conducted four-point bending test. The first surrogate model predicts strains at fixed locations along the center line of the beam for various time instances. This time-dependent surrogate model is inspired by the motion of a harmonic oscillator. For this study, we further compare the physics-based approach with a purely data-driven method, revealing the significance of physical laws for the extrapolation capabilities of models in scenarios with limited access to experimental data. Furthermore, we identify the natural frequency of the system by utilizing the physics-based model as an inverse solver. For the second surrogate model, we then focus on a fixed instance in time and combine the sensor data with the equations of linear elasticity to predict the strain distribution within the beam. This example reveals the importance of balancing different loss components through the selection of suitable loss weights.