Omslagsbillede

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

Guardado en:
Udgivet i:Communications Engineering vol. 4, no. 1 (Dec 2025), p. 168
Hovedforfatter: Tian, Mingxuan
Andre forfattere: Mu, Haochen, Liu, Tao, Li, Mengjiao, Ding, Donghong, Zhao, Jianping
Udgivet:
Springer Nature B.V.
Fag:
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
Online adgang:Citation/Abstract
Full Text
Full Text - PDF
Tags: Tilføj Tag
Ingen Tags, Vær først til at tagge denne postø!
Resumen: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
Fuente:Science Database