A physics-informed coupled residual-Fourier neural network for multi-physics field prediction in laser manufacturing
Source abstract
Abstract
In hybrid laser-MIG(Metal Inert Gas) welding, multi-physics field prediction in the melting pool is crucial for process optimization and quality control. However, the complex coupling among temperature, concentration, and velocity fields makes conventional simulations computationally expensive. This paper presents a Physics-Informed Coupled Residual-Fourier Network (PCRF-Net) method for multi-physics field prediction in the melting pool using simulation data and coupling physical residual equations. The method consists of a dual-branch architecture: the temperature and concentration fields branch uses deep residual networks, integrating energy conservation and solute transport equation residuals to predict temperature field and concentration distribution; the velocity field branch employs a Fourier-enhanced multilayer perceptron to predict velocity fields that capture long-range flow structures, while applying a temperature mask to restrict training to the molten regions. A stepwise training strategy is adopted, where the TC-Branch is trained first, and then the trained temperature field is used to guide the VF-Branch training, effectively reducing the complexity of multi-physics coupling. Compared to numerical simulation results, the method efficiently learns the temperature, concentration, and velocity fields generated by the coupling of laser and MIG heat sources, achieving second-level fast prediction. This demonstrates its great potential for real-time monitoring and parameter optimization in hybrid laser-MIG welding processes. • A novel stepwise training strategy is proposed that decouples the complex multi-physics coupling by sequentially training temperature-concentration fields and velocity fields, effectively solving the training instability problem that plagues traditional physics-informed neural networks when handling multiple coupled equations. • The method achieves approximately 5.73-fold speedup compared to traditional numerical simulations; after training, the model can predict arbitrary refined grids at second-level speed through interpolation methods without requiring re-simulation, demonstrating excellent grid resolution generalization capability.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Welding Techniques and Residual Stresses · Machine Learning in Materials Science · Model Reduction and Neural Networks
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (24)
Show source-provided references
1. A methodology for multi-object optimization of laser/mig hybrid welding process, Procedia CIRP
2. Understanding melt pool characteristics in laser powder bed fusion: an overview of single- and multi-track melt pools for process optimization
3. Simulation of melt pool behaviour during additive manufacturing: underlying physics and progress
4. Heat transfer and fluid flow during gas-metal-arc fillet welding for various joint configurations and welding positions10.1007/s11661-006-9083-4 ↗
5. Finite element modeling of welding processes10.1016/j.apm.2010.07.026 ↗
6. Modeling of transport phenomena in hybrid laser-mig keyhole welding10.1016/j.ijheatmasstransfer.2008.02.011 ↗
7. Multi-physics multi-scale simulation of the solidification process in the molten pool during laser welding of aluminum alloys10.1016/j.ijheatmasstransfer.2020.120316 ↗
8. Multi-scale modeling and simulation of additive manufacturing based on fused deposition technique10.1063/5.0141316 ↗
9. Transfer learning-enhanced physics informed neural network for accurate melt pool prediction in laser melting
10. Machine learning for metal additive manufacturing: towards a physics-informed data-driven paradigm10.1016/j.jmsy.2021.11.003 ↗
11. Data-driven and physics-informed deep learning operators for solution of heat conduction equation with parametric heat source10.1016/j.ijheatmasstransfer.2022.123809 ↗
12. A physics-informed neural network framework to predict 3D temperature field without labeled data in process of laser metal deposition10.1016/j.engappai.2023.105908 ↗
13. A dimensionally augmented and physics-informed machine learning for quality prediction of additively manufactured high-entropy alloy10.1016/j.jmatprotec.2022.117637 ↗
14. Meltpoolnet: melt pool characteristic prediction in metal additive manufacturing using machine learning
15. A review of multi-scale and multi-physics simulations of metal additive manufacturing processes with focus on modeling strategies
16. A physics-informed neural network framework for multi-physics coupling microfluidic problems10.1016/j.compfluid.2024.106421 ↗
17. Review of physics-informed neural networks: challenges in loss function design and geometric integration10.3390/math13203289 ↗
18. High-speed x-ray transmission and numerical study of melt flows inside the molten pool during laser welding of aluminum alloy
19. Softening behavior of a new Al-Zn-Mg-Cu alloy due to tig welding10.1007/s11665-016-2014-7 ↗
20. Origin of grain orientation during solidification of an aluminum alloy10.1016/j.actamat.2016.05.057 ↗
21. Numerical study of heat transfer and solute distribution in hybrid laser-mig welding10.1016/j.ijthermalsci.2019.106182 ↗
22. Modelling of hybrid laser–gma welding: review and challenges10.1179/1362171811Y.0000000022 ↗
23. Evolution of solidification texture during additive manufacturing10.1038/srep16446 ↗
24. Heat and mass transfer in laser dissimilar welding of stainless steel and nickel10.1016/j.apsusc.2012.02.143 ↗