Three-Dimensional Modeling and Analysis of Directed Energy Deposition Melt Pools Based on Physical Information Neural Networks
Open Access
- 27 August 2025
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 15 (17) , 9401
Abstract
In Directed Energy Deposition (DED), modeling the molten pool temperature field is crucial for precise temperature control, process optimization, and quality improvement. However, conventional numerical methods suffer from limitations such as high computational costs and poor transferability. This study proposes a physics-informed neural network with dynamic learning rate (DLR-PINN) model, which integrates transfer learning to enable rapid prediction of 3D temperature fields and dimensions of molten pools across process parameters. Its validity is verified by a finite element method (FEM) calibrated via single-track DED experiments. Results show that DLR-PINN exhibits superior convergence and stability compared to traditional PINN. Combined with transfer learning, training efficiency is significantly enhanced, with a single prediction taking only 10 s. Using the FEM as the benchmark, it achieves a mean absolute percentage error (MAPE) of 0.53% for temperature prediction, and MAPE of 3.69%, 2.48%, and 6.96% for molten pool dimension predictions, respectively. Sensitivity analysis of process parameters reveals that scanning speed has a significantly greater regulatory effect on molten pool characteristics than laser power. Additionally, the temperature field of the flat-top heat source is more uniform than that of the Gaussian heat source, which is more conducive to improving printing quality and efficiency.Keywords
Funding Information
- National Key R&D Program of China (2022YFB4601601, GKAB23026101, 202500081, 2023GXNSFBA026287)
- Key R&D Program of Guangxi Province (2022YFB4601601, GKAB23026101, 202500081, 2023GXNSFBA026287)
- Internet Information Innovation Talent of Guangxi Province (2022YFB4601601, GKAB23026101, 202500081, 2023GXNSFBA026287)
- Guangxi Natural Science Foundation (2022YFB4601601, GKAB23026101, 202500081, 2023GXNSFBA026287)
This publication has 49 references indexed in Scilit:
- When physics meets machine learning: a survey of physics-informed machine learningMachine Learning for Computational Science and Engineering, 2025
- Simulation of melt pool dynamics including vaporization using the particle finite element methodComputational Mechanics, 2024
- Laser additive manufacturing of titanium alloys: process, materials and post‐processingRare Metals, 2024
- Role of Machine Learning in Additive Manufacturing of Titanium Alloys—A ReviewArchives of Computational Methods in Engineering, 2023
- Hybrid thermal modeling of additive manufacturing processes using physics-informed neural networks for temperature prediction and parameter identificationComputational Mechanics, 2023
- 3D temperature field prediction in direct energy deposition of metals using physics informed neural networkThe International Journal of Advanced Manufacturing Technology, 2022
- Physics-informed neural networks (PINNs) for fluid mechanics: a reviewActa Mechanica Sinica, 2021
- Prediction of residual stress and deformation based on the temperature distribution in 3D-printed partsThe International Journal of Advanced Manufacturing Technology, 2021
- Machine learning for metal additive manufacturing: predicting temperature and melt pool fluid dynamics using physics-informed neural networksComputational Mechanics, 2021
- A framework to link localized cooling and properties of directed energy deposition (DED)-processed Ti-6Al-4VActa Materialia, 2017