An adaptive Bayesian Physics-Informed neural network model for predicting the fatigue life of high-strength steel under non-uniform corrosion
Authors:
- XuanRui YuXYXuanRui Yu
- QianLing WangQWQianLing Wang
- Nima KhodadadiNima Khodadadi
- Antonio NanniANAntonio Nanni
- Khalid M. MosalamKMKhalid M. Mosalam
Open Access
- 7 June 2026
- journal article
- Published by Elsevier in Computer-Aided Civil and Infrastructure Engineering
- Vol. 50
Abstract
No abstract availableFunding Information
- Chongqing Jiaotong University (SKLBT-2409)
- Chongqing University of Science and Technology (CKRC20240616)
- University of California Berkeley
- Natural Science Foundation of Chongqing Municipality (CSTB2025NSCQ-GPX0946)
This publication has 37 references indexed in Scilit:
- Bayesian physics-informed neural networks with iterative ensemble Kalman inversion for RUL prediction and uncertainty quantificationAdvanced Engineering Informatics, 2025
- Multifactorial prediction of corrosion fatigue crack growth in aluminum alloys using physics-informed neural networksEngineering Failure Analysis, 2025
- A data-driven model for predicting fatigue performance of high-strength steel wires based on optimized XGBOOSTEngineering Failure Analysis, 2024
- Bayesian Physics-informed Neural Networks for system identification of inverter-dominated power systemsElectric Power Systems Research, 2024
- A Bayesian defect-based physics-guided neural network model for probabilistic fatigue endurance limit evaluationComputer Methods in Applied Mechanics and Engineering, 2023
- Data-driven prediction of the fatigue performance of corroded high-strength steel wiresEngineering Failure Analysis, 2023
- Bayesian Physics Informed Neural Networks for real-world nonlinear dynamical systemsComputer Methods in Applied Mechanics and Engineering, 2022
- Stress–strain model of lower corroded steel plates of normal strength for fitness-for-purpose analysesConstruction and Building Materials, 2022
- Weibull modeling of the fatigue life for steel rebar considering corrosion effectsInternational Journal of Fatigue, 2018
- Kernel density maximum entropy method with generalized moments for evaluating probability distributions, including tails, from a small sample of dataInternational Journal for Numerical Methods in Engineering, 2017