Physics-Informed Machine Learning Regulated by Finite Element Analysis for Simulation Acceleration of Melt Pool Dynamics in Laser Powder Bed Fusion
arXiv:2506.20537v3 Announce Type: replace Abstract: Efficient simulation of Laser Powder Bed Fusion (LPBF) is crucial for process prediction due to the lasting issue of high computational cost associated with traditional numerical methods such as finite element analysis (FEA). While a Physics-Informed Neural Network (PINN) can predict solution fields with small training data and enables the generalization of new process parameters via transfer learning, it suffers from accuracy degradation in time-dependent problems due to the accumulation of residual and the difficulty in capturing the steep
The increasing complexity of advanced manufacturing processes like Laser Powder Bed Fusion (LPBF) and the limitations of traditional simulation methods are driving the need for more efficient computational approaches.
Improving the accuracy and efficiency of simulating additive manufacturing processes can unlock new capabilities in material science and engineering, accelerating innovation in critical sectors.
The integration of physics-informed machine learning with finite element analysis offers a path to overcome the computational bottlenecks of complex manufacturing simulations, leading to faster design cycles and higher fidelity outcomes.
- · Additive Manufacturing Industry
- · Material Science
- · High-Performance Computing (HPC)
- · AI/ML Software Developers
- · Traditional Simulation Software Vendors (slow to adapt)
- · Manufacturing processes reliant solely on empirical testing
More efficient and accurate simulation of complex manufacturing processes like LPBF becomes feasible.
Accelerated development of new materials and designs for aerospace, medical, and defense applications.
Reduced costs and increased accessibility for advanced manufacturing, fostering greater industrial competitiveness for nations with strong AI and manufacturing integration.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG