A dual-physics-informed neural network (DPINN) that integrates Walker and Forman crack growth models into a deep residual network that achieves superior performance after fine-tuning, significantly outperforming both a single Walker-PINN and gradient boosting regressors.
Abstract
Aluminum alloys used in aircraft structures are susceptible to corrosion fatigue cracking under combined aggressive environments and cyclic loading, threatening structural integrity. Pure data-driven models often fail under distribution shifts, while single-physics-informed neural networks (PINNs) lack flexibility in complex conditions. This paper proposes a dual-physics-informed neural network (DPINN) that integrates Walker and Forman crack growth models into a deep residual network. The model adaptively fuses both physical formulas via a trainable weight α and predicts material constants. A hybrid loss function with α regularization ensures physically consistent predictions. Using comprehensive corrosion fatigue data covering eight aluminum alloys, we evaluate the model on an internal test set and, more importantly, on an independent external test set simulating real-world distribution shifts. We further investigate an incremental learning scenario where the model is sequentially fine-tuned with increasing fractions of the external set. Results demonstrate that DPINN rapidly rectifies initial distribution mismatch, crossing the engineering reliability threshold (R2 > 0.90) at an early incremental stage, and achieves superior performance after fine-tuning, significantly outperforming both a single Walker-PINN and gradient boosting regressors. SHAP feature importance analysis identifies ΔK and stress ratio as dominant drivers, confirming mechanistic consistency. The proposed architecture offers a data-efficient and interpretable tool for corrosion fatigue crack growth prediction in aluminum alloy structures.
Accurate prediction of creep degradation across multiple high-temperature alloy grades remains a significant challenge in structural integrity assessment. Classical empirical and mechanistic models are typically restricted to estimating total creep rupture life and are often material-specific, limiting their generaliza...
H. Bhardwaj, Mukul Shukla· Journal of the Brazilian Soc...· 0 citations
The mechanical properties of reinforcing steel are fundamental to the durability of concrete structures. In service environments, corrosion of reinforcing bars is pervasive, and corrosion–fatigue failure constitutes a major driver of structural degradation, particularly in bridge infrastructure. Conventional data‐d...
Guo-Wen Yao, Yong-Yi Jian, Qian-Ling Wang et al.· Fatigue & Fracture of En...· 0 citations
This paper offers a physics-informed neural network (PINN) and ensemble learning framework that integrates physical and data-driven modeling using Bayesian model averaging (BMA) with a probabilistic neural network (PNN).
De-Biao Meng, Muhammad Umar Khan, Hua-Xi Wu et al.· Surface review and letters· 0 citations
Accurate prediction of concrete compressive strength is critical for mix design optimization, quality control, and reliable decision-making in modern construction. While data-driven machine learning models have demonstrated strong predictive capability, most existing approaches treat concrete behavior as a purely stati...
Anik Mazumder, M. Bappy, B. Sarker· Innovative Infrastructure So...· 0 citations
Bond strength degradation of corroded reinforced concrete (RC) structures involves complex mechanical interactions that are difficult to capture through experimental or purely data-driven methods alone. This study proposes a physics-informed neural network (PINN) framework that embeds a thin-walled cylinder rust expans...
Nan Jiang, Xiao-Kai Qiu, Wei-Wen Quan et al.· Buildings· 0 citations
Numerical results indicate that the presence of an upper sheet modifies heat generation and stress distribution, promoting more uniform material flow and improved bushing geometry under the investigated condition.
S. El-Bahloul· Journal of the Brazilian Soc...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.