A Residual-Attention Physics-Informed Neural Network for Irregular Interfaces and Multi-Peak Transport Fields
Nanophotonics and Biophotonics Key Laboratory of Jilin Province, School of Physics, Changchun University of Science and Technology(吉林省纳米光子学与生物光子学重点实验室,长春理工大学物理学院);School of Chemistry and Environmental Engineering, Changchun University of Science and Technology(长春理工大学化学与环境工程学院)
In complex engineering systems such as electro-thermal-fluid coupling, rapid and accurate prediction of multi-physics fields is essential for advanced applications like digital twins and real-time condition monitoring. Traditional numerical methods often suffer from high computational latency, whereas standard Physics-Informed Neural Networks (PINNs) frequently fail to capture critical local features, such as irregular interfaces, localized high-gradient regions, and multi-peak transport structures. To address these limitations and provide high-fidelity intelligent predictions for engineering decision-making, this paper proposes a Residual-Attention Physics-Informed Neural Network (RA-PINN) as a powerful surrogate modeling engine. The proposed method incorporates residual learning and attention enhancement into the network backbone to improve the representation of oblique transition structures, narrow charge layers, and distributed hotspots while strictly preserving global field consistency. To evaluate its effectiveness as an intelligent prediction framework, three representative benchmark cases are constructed, including an oblique asymmetric interface, a bipolar high-gradient charge layer, and a multi-peak Gaussian charge migration field. Under unified training settings, the proposed RA-PINN is systematically compared with a standard pure PINN and an LSTM-PINN in terms of average error, local maximum error, structural similarity, and convergence behavior. The results show that RA-PINN consistently achieves the best overall performance across all benchmark cases, demonstrating its tremendous potential as a highly reliable core inference engine for the condition monitoring and digital twin modeling of complex multi-physics engineering systems.
Verified residual-specific explicit derivative kernels for physics-informed learning and discretized PDE adjoints
Institute of AI for Industries, Chinese Academy of Sciences(中国科学院工业人工智能研究所);School of Aeronautics, Northwestern Polytechnical University(西北工业大学航空学院);International Joint Institute of Artificial Intelligence on Fluid Mechanics, Northwestern Polytechnical University(西北工业大学流体力学人工智能联合研究院);National Key Laboratory of Aircraft Configuration Design(飞机气动设计国家重点实验室)
Residual Attention Physics-Informed Neural Networks for Robust Multiphysics Simulation of Steady-State Electrothermal Energy Systems
Nanophotonics and Biophotonics Key Laboratory of Jilin Province, School of Physics, Changchun University of Science and Technology(吉林省纳米光子与生物光子重点实验室,物理学院,长春理工大学)
Beyond Residuals: Energy based solutions of partial differential equations using scientific machine learning
Bauhaus University Weimar(魏玛包豪斯大学);Institute of Structural Mechanics, Bauhaus University Weimar(魏玛包豪斯大学结构力学研究所);Fudan University(复旦大学);Institute of Computational Mechanics and Artificial Intelligence, Fudan University(复旦大学计算力学与人工智能研究所);Tsinghua University(清华大学);Department of Engineering Mechanics, Tsinghua University(清华大学工程力学系)
Potential failures of physics-informed machine learning in traffic flow modeling: theoretical and experimental analysis
University of Maryland, College Park, MD 20742, United States(马里兰大学学院公园分校);Florida Atlantic University, Boca Raton, FL 33431, United States(佛罗里达 Atlantic 大学)
RAMS: Residual-based adversarial-gradient moving sample method for scientific machine learning in solving partial differential equations
Department of Civil and Environmental Engineering, Hong Kong Polytechnic University(香港理工大学土木与环境工程系);Department of Statistics and Data Science, Yale University(耶鲁大学统计与数据科学系)