Prospective on applying machine learning in computational fluid dynamics (CFD) simulation of metallurgical reactors DOI
Yuhong Liu, Jiangshan Zhang, Shufeng Yang

et al.

Ironmaking & Steelmaking Processes Products and Applications, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 10, 2024

Metallurgical reactors, especially in ironmaking/steelmaking process, characterise with high-temperature turbulence, multiphase flow, mass/heat transfer and reactions. Computational fluid dynamics (CFD) simulation-based design optimisation are of significance for efficient metallurgical performance. However, the difficulty cost to numerically solve nonlinear controlling equations combined data pre/post-processing make whole CFD simulation process time-consuming, which makes it challenging provide in-time feedback industrial practices. The popularisation prosperous development machine learning bring new opportunities promoting Discussion has been made on current research progress applying workflow including pre-processing, solving, post-processing. Among them, time consumed by manual pre-processing exceeds 50% tasks general. or parametric modelling methods can reduce three orders estimate. solving step is expected be accelerated 5 1000 times using learning. A brief review coupled provided, as a prospective its development. presented main functions, challenges, typical techniques future directions purpose making faster, more accurate, better visualised based

Language: Английский

Improving out-of-distribution generalization for online weld expulsion inspection using physics-informed neural networks使用物理信息神经网络改进在线焊缝飞溅检测的分布外泛化 DOI
Yu-Jun Xia, Qiang Song, B Yi

et al.

Welding in the World, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 9, 2025

Language: Английский

Citations

0
Physics-Informed Machine Learning of Thermal Stress Evolution in Laser Metal Deposition DOI
Rahul Swarup Sharma,

Y. B. Guo

˜The œminerals, metals & materials series, Journal Year: 2025, Volume and Issue: unknown, P. 550 - 559

Published: Jan. 1, 2025

Language: Английский

Citations

0
Influence of Nozzle Diameter and Gas Flow on Spatter Removal in Laser Powder Bed Fusion: A CFD Approach DOI Creative Commons
Awad B.S. Alquaity

Results in Engineering, Journal Year: 2024, Volume and Issue: unknown, P. 103759 - 103759

Published: Dec. 1, 2024

Language: Английский

Citations

2
Review of Recent Additive Manufacturing and Welding Research with Application of Physics-Informed Neural Networks DOI Open Access
Taehwan Ko,

H. Kim,

Yeoungcheol Shin

et al.

Journal of Welding and Joining, Journal Year: 2024, Volume and Issue: 42(4), P. 357 - 365

Published: Aug. 29, 2024

This review introduces recent research on applying physics-informed neural networks (PINNs) to additive manufacturing and welding. PINNs, which are artificial intelligence models, integrate governing equations containing physical information with networks, enabling the modeling of complex phenomena at a lower computational cost than traditional numerical models. Although PINNs have been employed in limited number studies welding processes, they extensively used various within field manufacturing. study reviews theoretical background explore their effective application examining 12 cases two processes. The analysis included structure PINN, equations, prediction results each study. Results indicate that provide faster computation speeds higher accuracies Moreover, could perform analyses without additional training even when process parameters materials changed. Additionally, effectively applied predict mechanical properties molten zone. Consequently, anticipated be actively future property prediction.

Language: Английский

Citations

0
Prospective on applying machine learning in computational fluid dynamics (CFD) simulation of metallurgical reactors DOI
Yuhong Liu, Jiangshan Zhang, Shufeng Yang

et al.

Ironmaking & Steelmaking Processes Products and Applications, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 10, 2024

Metallurgical reactors, especially in ironmaking/steelmaking process, characterise with high-temperature turbulence, multiphase flow, mass/heat transfer and reactions. Computational fluid dynamics (CFD) simulation-based design optimisation are of significance for efficient metallurgical performance. However, the difficulty cost to numerically solve nonlinear controlling equations combined data pre/post-processing make whole CFD simulation process time-consuming, which makes it challenging provide in-time feedback industrial practices. The popularisation prosperous development machine learning bring new opportunities promoting Discussion has been made on current research progress applying workflow including pre-processing, solving, post-processing. Among them, time consumed by manual pre-processing exceeds 50% tasks general. or parametric modelling methods can reduce three orders estimate. solving step is expected be accelerated 5 1000 times using learning. A brief review coupled provided, as a prospective its development. presented main functions, challenges, typical techniques future directions purpose making faster, more accurate, better visualised based

Language: Английский

Citations

0