Analysis of Prediction Mechanisms and Feature Importance of Martensite Start Temperature of Alloy Steel via Explainable Artificial Intelligence

被引:2
|
作者
Jeon, Junhyub [1 ]
Seo, Namhyuk [1 ]
Jung, Jae-Gil [1 ,2 ]
Son, Seung Bae [1 ,2 ]
Lee, Seok-Jae [1 ,2 ]
机构
[1] Jeonbuk Natl Univ, Div Adv Mat Engn, Jeonju 54896, South Korea
[2] Jeonbuk Natl Univ, Res Ctr Adv Mat Dev, Jeonju 54896, South Korea
关键词
machine learning; martensite start temperature; explainable artificial intelligence; prediction mechanism; alloy steels; AUSTENITE GRAIN-SIZE; NEURAL-NETWORK; TRANSFORMATION; ELEMENTS;
D O I
10.2320/matertrans.MT-MI2022004
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
This study proposes a machine learning model to predict the martensite start temperature (Ms) of alloy steels. We collected 219 usable data from the literature, and adjusted the hyperparameters to propose an accurate machine learning model. Artificial neural networks (ANN) exhibited the best performance compared with existing empirical equation. The prediction mechanisms and feature importance of the ANN with regards to the whole system were discussed via the Shapley additive explanation (SHAP).
引用
收藏
页码:2196 / 2201
页数:6
相关论文
共 50 条
  • [1] Predicting Meibomian Gland Dropout and Feature Importance Analysis with Explainable Artificial Intelligence
    Fineide, Fredrik A.
    Storas, Andrea M.
    Riegler, Michael A.
    Utheim, Tor Paaske
    2023 IEEE 36TH INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS, CBMS, 2023, : 366 - 373
  • [2] Application of artificial networks in the prediction of martensite start temperature
    Hou, Zhe-Zhe
    Wu, Jian-Jun
    Cailiao Rechuli Xuebao/Transactions of Materials and Heat Treatment, 2004, 25 (06): : 104 - 106
  • [3] Application of explainable artificial intelligence for prediction and feature analysis of carbon diffusivity in austenite
    Jeon, Junhyub
    Seo, Namhyuk
    Son, Seung Bae
    Jung, Jae-Gil
    Lee, Seok-Jae
    JOURNAL OF MATERIALS SCIENCE, 2022, 57 (38) : 18142 - 18153
  • [4] Application of explainable artificial intelligence for prediction and feature analysis of carbon diffusivity in austenite
    Junhyub Jeon
    Namhyuk Seo
    Seung Bae Son
    Jae-Gil Jung
    Seok-Jae Lee
    Journal of Materials Science, 2022, 57 : 18142 - 18153
  • [5] Prediction of martensite start temperature using artificial neural networks
    Vermeulen, WG
    Morris, PF
    deWeijer, AP
    vanderZwaag, S
    IRONMAKING & STEELMAKING, 1996, 23 (05) : 433 - 437
  • [6] Soil temperature prediction based on explainable artificial intelligence and LSTM
    Geng, Qingtian
    Wang, Leilei
    Li, Qingliang
    FRONTIERS IN ENVIRONMENTAL SCIENCE, 2024, 12
  • [7] Prediction of martensite start temperature by neural network analysis
    Capdevila, C
    Caballero, FG
    de Andrés, CG
    JOURNAL DE PHYSIQUE IV, 2003, 112 : 217 - 221
  • [8] Prediction of Martensite Start Temperature in Alloy Steels with Different Grain Sizes
    Lee, Seok-Jae
    Park, Kyong-Su
    METALLURGICAL AND MATERIALS TRANSACTIONS A-PHYSICAL METALLURGY AND MATERIALS SCIENCE, 2013, 44A (08): : 3423 - 3427
  • [9] Prediction of Martensite Start Temperature in Alloy Steels with Different Grain Sizes
    Seok-Jae Lee
    Kyong-Su Park
    Metallurgical and Materials Transactions A, 2013, 44 : 3423 - 3427
  • [10] Prediction of martensite formation start temperature in steels using artificial neural networks
    Arjomandi, M.
    Khorsand, H.
    Sadati, S. H.
    Abdoos, H.
    DIFFUSION IN SOLIDS AND LIQUIDS III, 2008, 273-276 : 329 - 334