Optimizing laser powder bed fusion of Ti-5Al-5V-5Mo-3Cr by artificial intelligence

被引：33

作者：

Shin, Da Seul ^{[1
,2
,3
]}

Lee, Chi Hun ^{[1
]}

Kuehn, Uta ^{[3
]}

Lee, Seung Chul ^{[1
]}

Park, Seong Jin ^{[1
]}

Schwab, Holger ^{[3
]}

Scudino, Sergio ^{[3
]}

Kosiba, Konrad ^{[3
]}

机构：

[1] Pohang Univ Sci & Technol POSTECH, Dept Mech Engn, 77 Cheongam Ro, Pohang 37673, Kyeongbuk, South Korea

[2] Korea Inst Mat Sci, Mat Deformat Dept, 797 Changwon Daero, Chang Won 51508, Kyeongnam, South Korea

[3] Leibniz IFW Dresden, Inst Complex Mat, Helmholtzstr 20, D-01069 Dresden, Germany

来源：

JOURNAL OF ALLOYS AND COMPOUNDS | 2021年 / 862卷

关键词：

Additive manufacturing; Laser powder bed fusion; Ti-based alloy; Artificial intelligence; Artificial neural networks; Deep learning; DEEP NEURAL-NETWORKS; MELT POOL; PREDICTION; MICROSTRUCTURE; OPTIMIZATION; PERFORMANCE; CHALLENGES; FRAMEWORK; POROSITY; DENSITY;

D O I：

10.1016/j.jallcom.2020.158018

中图分类号：

O64 [物理化学（理论化学）、化学物理学];

学科分类号：

070304 ; 081704 ;

摘要：

The prerequisite for exploiting the full potential of additive manufacturing (AM) is the rapid and cost-effective fabrication of defect-free components. However, each newly processed material usually requires the identification of the optimal parameter set, a cost and time-consuming process, mostly conducted by trial and error. Here, an optimization strategy based on artificial intelligence (AI) is developed for predicting the density of additively manufactured Ti-5Al-5V-5Mo-3Cr components from experimental data. The present approach opens the way to a faster identification of the optimum set of processing parameters via AI. (C) 2020 Elsevier B.V. All rights reserved.

引用

页数：9

共 62 条

[1]

AlMangour B., 2019, ADDITIVE MANUFACTURI

[2] Opportunities and challenges using artificial intelligence in ADME/Tox [J].