Physics-informed machine learning-based real-time long-horizon temperature fields prediction in metallic additive manufacturing

Guardat en:

Dades bibliogràfiques
Publicat a:	Communications Engineering vol. 4, no. 1 (Dec 2025), p. 168
Autor principal:	Tian, Mingxuan
Altres autors:	Mu, Haochen, Liu, Tao, Li, Mengjiao, Ding, Donghong, Zhao, Jianping
Publicat:	Springer Nature B.V.
Matèries:	Temperature distribution Finite element method Finite volume method Accuracy Fluid dynamics Parameter identification Quality assurance Boundary conditions Data processing Manufacturing Machine learning Low carbon steel Additive manufacturing Efficiency Simulation Physics Partial differential equations Residual stress Temperature Neural networks Process controls Recurrent neural networks Data collection Finite element analysis Errors Real time
Accés en línia:	Citation/Abstract Full Text Full Text - PDF
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!

Descripció
Resum:	Real-time long-horizon temperature prediction in wire arc additive manufacturing is critical for process control and quality assurance. However, finite element methods are computationally expensive, and the existing data-driven models suffer from error accumulation and poor adaptability. Here we propose a physics-informed geometric recurrent neural network that integrates geometric characteristics and physical constraints, captures spatiotemporal characteristics via convolutional long short-term memory cells, and enforces physical consistency through hard-encoding initial/boundary conditions and physics-informed loss function. The model can predict the temperature field for future 1.25 s based on current 1.25 s data, and has also been evaluated for more long-horizon predictions. Transfer learning was used to enhance the model’s efficiency in practical applications. Results demonstrate that the proposed model achieves 4.5−13.9% maximum prediction error in simulations and experimental data. Including geometric characteristics and physical information reduces maximum error by about 1%, while the integrated model lowers it by 4%. Furthermore, transfer learning reduces the training time by approximately 50% while achieving the same loss level.Real-time long-horizon temperature prediction in metal additive manufacturing is critical for process control and quality assurance. Mingxuan Tian and colleagues propose a physics-informed machine learning model to predict temperature field for future 1.25 s.
ISSN:	2731-3395
DOI:	10.1038/s44172-025-00501-7
Font:	Science Database