A Transfer Learning-Based Multi-Fidelity Point-Cloud Neural Network Approach for Melt Pool Modeling in Additive Manufacturing
ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B: Mechanical Engineering · 01.03.2022 · 8 (1)
DOI: 10.1115/1.4051749 ↗Kurz gefasst
Fachartikel in der Zeitschrift ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B: Mechanical Engineering, online erschienen am 04.08.2021. Verfasst von Xufeng Huang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 58 Literaturangaben. Gefördert von: Directorate for Engineering.
Abstract (Originalsprache)
Melt pool modeling is critical for model-based uncertainty quantification (UQ) and quality control in metallic additive manufacturing (AM). Finite element (FE) simulation for thermal modeling in metal AM, however, is tedious and time-consuming. This paper presents a multifidelity point-cloud neural network method (MF-PointNN) for surrogate modeling of melt pool based on FE simulation data. It merges the feature representations of the low-fidelity (LF) analytical model and high-fidelity (HF) FE simulation data through the theory of transfer learning (TL). A basic PointNN is first trained using LF data to construct a correlation between the inputs and thermal field of analytical models. Then, the basic PointNN is updated and fine-tuned using the small size of HF data to build the MF-PointNN. The trained MF-PointNN allows for efficient mapping from input variables and spatial positions to thermal histories, and thereby efficiently predicts the three-dimensional melt pool. Results of melt pool modeling of electron beam additive manufacturing (EBAM) of Ti-6Al-4V under uncertainty demonstrate the efficacy of the proposed approach.
Förderung
- Directorate for Engineering
Zitieren
APA
Huang, X., Xie, T., Wang, Z., Chen, L., Zhou, Q., & Hu, Z. (2022). A Transfer Learning-Based Multi-Fidelity Point-Cloud Neural Network Approach for Melt Pool Modeling in Additive Manufacturing. ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B: Mechanical Engineering, 8(1). https://doi.org/10.1115/1.4051749
Vancouver
Huang X, Xie T, Wang Z, Chen L, Zhou Q, Hu Z. A Transfer Learning-Based Multi-Fidelity Point-Cloud Neural Network Approach for Melt Pool Modeling in Additive Manufacturing. ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B: Mechanical Engineering. 2022;8(1). doi:10.1115/1.4051749
BibTeX
@article{Huang2022,
author = {Huang, Xufeng and Xie, Tingli and Wang, Zhuo and Chen, Lei and Zhou, Qi and Hu, Zhen},
title = {A Transfer Learning-Based Multi-Fidelity Point-Cloud Neural Network Approach for Melt Pool Modeling in Additive Manufacturing},
journal = {ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B: Mechanical Engineering},
year = {2022},
volume = {8},
number = {1},
doi = {10.1115/1.4051749}
}
EUVIMED