Metaheuristic Optimization of Powder Size Distribution in Powder Forming Process Using Multi-Particle Finite Element Method Coupled with Artificial Neural Network and Genetic Algorithm
-
- Kahhal Parviz
- School of Mechanical Engineering, Pusan National University School of Engineering, The University of Waikato
-
- Ghorbani-Menghari Hossein
- School of Mechanical Engineering, Pusan National University
-
- Kim Hwi-Jun
- Korea Institute of Industrial Technology
-
- Choi Hyunjoo
- School of Advanced Materials Engineering, Kookmin University
-
- Cha Pil-Ryung
- School of Advanced Materials Engineering, Kookmin University
-
- Kim Ji Hoon
- School of Mechanical Engineering, Pusan National University
この論文をさがす
抄録
<p>A neural network-based approach is proposed to minimize the maximum axial stress in the powder forming process. The finite element analysis was conducted using a MATLAB code and an ABAQUS python script to generate observations for the neural network training procedure. Powders of three different particle size distributions were mixed, and the mixture fractions were considered as control parameters. The artificial neural network determined the relationship between parameters and objective function. The effect of mixture fractions on maximum axial stress was analyzed. The results showed that the genetic algorithm could effectively determine the optima and the proposed method had strong prediction capability and accuracy.</p>
収録刊行物
-
- MATERIALS TRANSACTIONS
-
MATERIALS TRANSACTIONS 64 (11), 2648-2655, 2023-11-01
公益社団法人 日本金属学会
- Tweet
キーワード
詳細情報 詳細情報について
-
- CRID
- 1390016427484698240
-
- NII書誌ID
- AA1151294X
-
- ISSN
- 13475320
- 13459678
-
- NDL書誌ID
- 033147833
-
- 本文言語コード
- en
-
- データソース種別
-
- JaLC
- NDL
- Crossref
-
- 抄録ライセンスフラグ
- 使用不可
