A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Identification of chloride diffusion coefficient in concrete using physics-informed neural networks
Abstract The corrosion of steel caused by chloride is one of the important causes of the deterioration of reinforced concrete structures. In order to describe the transport behavior of chlorides in concrete and to make quantitative durability designs based on it, it is necessary to determine the chloride diffusion coefficient correctly. However, the commonly used analytical method is not suitable for the free chloride diffusion coefficient considering the nonlinear chloride binding capacity of concrete. In this study, by comparing the results of solving forward problems involving chloride transport equations using finite element method (FEM) and solving corresponding inverse problems using physics-informed neural networks (PINNs), it is verified that PINNs can be applied to identify the chloride diffusion coefficient in non-steady-state immersion tests and accelerated chloride migration tests considering no chloride binding, Langmuir binding, or Freundlich binding. The robustness of PINNs is verified by training with 5% and 10% noise data as observed data. The results of interpolation and extrapolation using PINNs trained successfully show its excellent generalization performance.
Highlights The applicability of PINNs to identify chloride diffusion coefficient is verified. Adjusting the weight of residuals can avoid the noise-induced overfitting problem. PINNs show good robustness at the 5% and 10% noise corruption level of data. PINNs have excellent generalization performance for chloride transport equations.
Identification of chloride diffusion coefficient in concrete using physics-informed neural networks
Abstract The corrosion of steel caused by chloride is one of the important causes of the deterioration of reinforced concrete structures. In order to describe the transport behavior of chlorides in concrete and to make quantitative durability designs based on it, it is necessary to determine the chloride diffusion coefficient correctly. However, the commonly used analytical method is not suitable for the free chloride diffusion coefficient considering the nonlinear chloride binding capacity of concrete. In this study, by comparing the results of solving forward problems involving chloride transport equations using finite element method (FEM) and solving corresponding inverse problems using physics-informed neural networks (PINNs), it is verified that PINNs can be applied to identify the chloride diffusion coefficient in non-steady-state immersion tests and accelerated chloride migration tests considering no chloride binding, Langmuir binding, or Freundlich binding. The robustness of PINNs is verified by training with 5% and 10% noise data as observed data. The results of interpolation and extrapolation using PINNs trained successfully show its excellent generalization performance.
Highlights The applicability of PINNs to identify chloride diffusion coefficient is verified. Adjusting the weight of residuals can avoid the noise-induced overfitting problem. PINNs show good robustness at the 5% and 10% noise corruption level of data. PINNs have excellent generalization performance for chloride transport equations.
Identification of chloride diffusion coefficient in concrete using physics-informed neural networks
Wan, Yutong (author) / Zheng, Wenzhong (author) / Wang, Ying (author)
2023-06-01
Article (Journal)
Electronic Resource
English
Determination of diffusion coefficient of chloride in concrete using Warburg diffusion coefficient
| British Library Online Contents | 2009
Physics-informed neural networks for identification of material properties using standing waves
| British Library Conference Proceedings | 2022
Structural Digital Twin of Concrete Infrastructure Powered with Physics-Informed Neural Networks
| Springer Verlag | 2024