본문 바로가기

기계 학습 및 실험적 검증을 활용한 La 함량 별 알루미늄 합금 설계

Aluminum Alloy Design by La Amount through Machine Learning and Experimental Verification

문서 유형
연구출판물 · 학술지 논문
등재
KCISCIEScopus
저널 순위
JCR Q3Scopus Q3KCI Q1
저널
Korean Journal of Metals and Materials62(7) · pp.524 · 2024
피인용
Web of Science 4Scopus 4KCI 0
FWCI (Scopus)
0.46
JCR IF
JCR 2023 1.1
ISSN
1738-8228

저자

  1. 김경훈제1저자Pohang Inst Mat Ind Advancement, DX Technol Team, Pohang 37666, South Korea
  2. 박종구Pohang Inst Mat Ind Advancement, DX Technol Team, Pohang 37666, South Korea
  3. 양해웅Pohang Inst Mat Ind Advancement, DX Technol Team, Pohang 37666, South Korea
  4. 허우로Pohang Inst Mat Ind Advancement, DX Technol Team, Pohang 37666, South Korea
  5. 강남현교신저자Pusan Natl Univ, Dept Mat Sci & Engn, Pusan 46241, South Korea

초록

The development and design of metal materials have been carried out through experimentalmethod and simulation based on theoretic. Recently, with the widespread application of artificial intelligence(AI) in various fields, many studies have been actively incorporating artificial intelligence into the field ofmetal material design. Especially, many studies have been reported on adding rare-earth elements toaluminum alloys to improve corrosion resistance and mechanical properties using AI. However, theperformance evaluation of artificial intelligence through experimental verification has not yet been reportedrelated to metal material. In this study, we investigated the artificial intelligence algorithm capable ofpredicting the hardness based on the composition ratio of aluminum alloy with added Lanthanum (La) usingexperimental data and conducted a comparative analysis of the predicted hardness values. The machinelearning models employed Adaptive Boosting Regressor (ADA), Gradient Boosting Regressor (GBR), RandomForest Regressor (RF), and Extra Trees Regressor (ET). The dataset comprised 1,210 encompassing 9composition elements constituting the alloy. In the result, the findings revealed that the ET modeldemonstrated the most effective performance in predicting hardness. In addition, the microstructure becamefine and showed the highest hardness at 0.5 wt.% La and hardness tended to decrease as the amount of Laincreased. The ET model showed excellent performance in predicting this tendency through experimentalverification.

키워드

Machine learningExperimental VerificationAluminum alloyRare-earth elementHardnessMECHANICAL-PROPERTIESHEAT-TREATMENTMICROSTRUCTUREPREDICTIONLANTHANUMHARDNESSSTEELSMODEL

식별자

Scopus EID
2-s2.0-85197589599
WoS UID
001265097300001
KCI
ART003090507