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:
Accés en línia:Citation/Abstract
Full Text
Full Text - PDF
Etiquetes: Afegir etiqueta
Sense etiquetes, Sigues el primer a etiquetar aquest registre!

MARC

LEADER 00000nab a2200000uu 4500
001 3255943831
003 UK-CbPIL
022 |a 2731-3395 
024 7 |a 10.1038/s44172-025-00501-7  |2 doi 
035 |a 3255943831 
045 2 |b d20251201  |b d20251231 
100 1 |a Tian, Mingxuan  |u Nanjing Tech University, School of Mechanical and Power Engineering, Nanjing, China (GRID:grid.412022.7) (ISNI:0000 0000 9389 5210) 
245 1 |a Physics-informed machine learning-based real-time long-horizon temperature fields prediction in metallic additive manufacturing 
260 |b Springer Nature B.V.  |c Dec 2025 
513 |a Journal Article 
520 3 |a 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. 
653 |a Temperature distribution 
653 |a Finite element method 
653 |a Finite volume method 
653 |a Accuracy 
653 |a Fluid dynamics 
653 |a Parameter identification 
653 |a Quality assurance 
653 |a Boundary conditions 
653 |a Data processing 
653 |a Manufacturing 
653 |a Machine learning 
653 |a Low carbon steel 
653 |a Additive manufacturing 
653 |a Efficiency 
653 |a Simulation 
653 |a Physics 
653 |a Partial differential equations 
653 |a Residual stress 
653 |a Temperature 
653 |a Neural networks 
653 |a Process controls 
653 |a Recurrent neural networks 
653 |a Data collection 
653 |a Finite element analysis 
653 |a Errors 
653 |a Real time 
700 1 |a Mu, Haochen  |u Nanjing Tech University, School of Mechanical and Power Engineering, Nanjing, China (GRID:grid.412022.7) (ISNI:0000 0000 9389 5210); Nanjing Tech University, Institute of Reliability centered Manufacturing, Nanjing, China (GRID:grid.412022.7) (ISNI:0000 0000 9389 5210); Nanjing Tech University, Jiangsu Provincial Key Laboratory of Energy Power Manufacturing Equipment and Reliability Technology, Nanjing, China (GRID:grid.412022.7) (ISNI:0000 0000 9389 5210) 
700 1 |a Liu, Tao  |u Nanjing Tech University, School of Mechanical and Power Engineering, Nanjing, China (GRID:grid.412022.7) (ISNI:0000 0000 9389 5210) 
700 1 |a Li, Mengjiao  |u Nanjing Tech University, School of Mechanical and Power Engineering, Nanjing, China (GRID:grid.412022.7) (ISNI:0000 0000 9389 5210) 
700 1 |a Ding, Donghong  |u Nanjing Tech University, School of Mechanical and Power Engineering, Nanjing, China (GRID:grid.412022.7) (ISNI:0000 0000 9389 5210); Nanjing Tech University, Institute of Reliability centered Manufacturing, Nanjing, China (GRID:grid.412022.7) (ISNI:0000 0000 9389 5210); Nanjing Tech University, Jiangsu Provincial Key Laboratory of Energy Power Manufacturing Equipment and Reliability Technology, Nanjing, China (GRID:grid.412022.7) (ISNI:0000 0000 9389 5210) 
700 1 |a Zhao, Jianping  |u Nanjing Tech University, School of Mechanical and Power Engineering, Nanjing, China (GRID:grid.412022.7) (ISNI:0000 0000 9389 5210); Nanjing Tech University, Jiangsu Provincial Key Laboratory of Energy Power Manufacturing Equipment and Reliability Technology, Nanjing, China (GRID:grid.412022.7) (ISNI:0000 0000 9389 5210) 
773 0 |t Communications Engineering  |g vol. 4, no. 1 (Dec 2025), p. 168 
786 0 |d ProQuest  |t Science Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3255943831/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full Text  |u https://www.proquest.com/docview/3255943831/fulltext/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3255943831/fulltextPDF/embedded/6A8EOT78XXH2IG52?source=fedsrch