Powder Bed Fusion via Machine Learning-Enabled Approaches

Powder Bed Fusion via Machine Learning-Enabled Approaches

Powder bed fusion (PBF) applies to various metallic materials used in the metal printing process of building a wide range of complex parts compared to other AM technologies. PBF process has several variants such as DMLS (direct metal laser sintering), EBM (electron beam melting), SHS (selective heat...

Full description

Saved in:
Bibliographic Details
Published in:Complexity (New York, N.Y.) Vol. 2023; pp. 1 - 25
Main Authors: Chadha, Utkarsh, Selvaraj, Senthil Kumaran, Abraham, Abel Saji, Khanna, Mayank, Mishra, Anirudh, Sachdeva, Isha, Kashyap, Swati, Dev, S. Jithin, Swatish, R. Srii, Joshi, Ayushma, Anand, Simar Kaur, Adefris, Addisalem, Lokesh Kumar, R., Kaliappan, Jayakumar, Dhanalakshmi, S.
Format: Journal Article
Language:English
Published: Hoboken Hindawi 2023
Hindawi Limited
Hindawi-Wiley
Subjects:
Additive manufacturing
Algorithms
Artificial neural networks
Defects
Efficiency
Electron beam melting
Heat
Laser beam melting
Laser sintering
Machine learning
Mechanical properties
Powder beds
Process parameters
Productivity
Real time
Residual stress
Sintering (powder metallurgy)
Yield stress
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Powder bed fusion (PBF) applies to various metallic materials used in the metal printing process of building a wide range of complex parts compared to other AM technologies. PBF process has several variants such as DMLS (direct metal laser sintering), EBM (electron beam melting), SHS (selective heat sintering), SLM (selective laser melting), and SLS (selective laser sintering). For PBF to reach its maximum potential, machine learning (ML) algorithms are used with suitable materials to achieve goals cost-effectively. Various applications of neural networks, including ANNs, CNNs, RNNs, and other popular techniques such as KNN, SVM, and GP were reviewed, and future challenges were discussed. Some special-purpose algorithms were listed as follows: GAN, SeDANN, SCNN, K-means, PCA, etc. This review presents the evolution, current status, challenges, and prospects of these technologies in terms of material, features, process parameters, applications, advantages, disadvantages, etc., to explain their significance and provide an in-depth understanding of the same.
ISSN:1076-2787
1099-0526
DOI:10.1155/2023/9481790