A machine-learning-based alloy design platform that enables both forward and inverse predictions for thermo-mechanically controlled processed (TMCP) steel alloys

被引:38
作者
Lee, Jin-Woong [1 ]
Park, Chaewon [1 ]
Do Lee, Byung [1 ]
Park, Joonseo [1 ]
Goo, Nam Hoon [2 ]
Sohn, Kee-Sun [1 ]
机构
[1] Sejong Univ, Nanotechnol & Adv Mat Engn, 209 Neungdong Ro, Seoul 143747, South Korea
[2] Hyundai Steel DangJin Works, Adv Res Team, Dangjin 31719, Chungnam, South Korea
基金
新加坡国家研究基金会;
关键词
HOLOGRAPHIC RESEARCH STRATEGY; NONDOMINATED SORTING APPROACH; ARTIFICIAL NEURAL-NETWORKS; HIGH ENTROPY ALLOYS; DISORDERED COMPOUND; VARIABLE SELECTION; GENETIC ALGORITHM; LOW-SYMMETRY; BAND-GAP; OPTIMIZATION;
D O I
10.1038/s41598-021-90237-z
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Predicting mechanical properties such as yield strength (YS) and ultimate tensile strength (UTS) is an intricate undertaking in practice, notwithstanding a plethora of well-established theoretical and empirical models. A data-driven approach should be a fundamental exercise when making YS/UTS predictions. For this study, we collected 16 descriptors (attributes) that implicate the compositional and processing information and the corresponding YS/UTS values for 5473 thermo-mechanically controlled processed (TMCP) steel alloys. We set up an integrated machine-learning (ML) platform consisting of 16 ML algorithms to predict the YS/UTS based on the descriptors. The integrated ML platform involved regularization-based linear regression algorithms, ensemble ML algorithms, and some non-linear ML algorithms. Despite the dirty nature of most real-world industry data, we obtained acceptable holdout dataset test results such as R-2>0.6 and MSE<0.01 for seven non-linear ML algorithms. The seven fully trained non-linear ML models were used for the ensuing 'inverse design (prediction)' based on an elitist-reinforced, non-dominated sorting genetic algorithm (NSGA-II). The NSGA-II enabled us to predict solutions that exhibit desirable YS/UTS values for each ML algorithm. In addition, the NSGA-II-driven solutions in the 16-dimensional input feature space were visualized using holographic research strategy (HRS) in order to systematically compare and analyze the inverse-predicted solutions for each ML algorithm.
引用
收藏
页数:18
相关论文
共 75 条
[21]   Modelling the correlation between processing parameters and properties of maraging steels using artificial neural network [J].
Guo, Z ;
Sha, W .
COMPUTATIONAL MATERIALS SCIENCE, 2004, 29 (01) :12-28
[22]   Determination of possible configurations for Li0.5CoO2 delithiated Li-ion battery cathodes via DFT calculations coupled with a multi-objective non-dominated sorting genetic algorithm (NSGA-III) [J].
Han, Woo Gyu ;
Park, Woon Bae ;
Singh, Satendra Pal ;
Pyo, Myoungho ;
Sohn, Kee-Sun .
PHYSICAL CHEMISTRY CHEMICAL PHYSICS, 2018, 20 (41) :26405-26413
[23]  
Henseler J, 2009, ADV INT MARKETING, V20, P277, DOI 10.1108/S1474-7979(2009)0000020014
[24]  
Hinton GE, 2002, ADV NEURAL INFORM PR, V15, P833
[25]  
Ho TK, 1998, IEEE T PATTERN ANAL, V20, P832, DOI 10.1109/34.709601
[26]   Density functional theory calculations for the band gap and formation energy of Pr4-xCaxSi12O3+xN18-x; a highly disordered compound with low symmetry and a large cell size [J].
Hong, Sung Un ;
Singh, Satendra Pal ;
Pyo, Myoungho ;
Park, Woon Bae ;
Sohn, Kee-Sun .
PHYSICAL CHEMISTRY CHEMICAL PHYSICS, 2017, 19 (25) :16702-16712
[27]  
Hoskuldsson A., 1988, J Chemom, V2, P211, DOI [DOI 10.1002/CEM.1180020306, 10.1002/CEM.1180020306]
[28]   Analysis of a complex of statistical variables into principal components [J].
Hotelling, H .
JOURNAL OF EDUCATIONAL PSYCHOLOGY, 1933, 24 :417-441
[29]   Two-way design of alloys for advanced ultra supercritical plants based on machine learning [J].
Hu, Xiaobing ;
Wang, Jincheng ;
Wang, Yanyan ;
Li, Junjie ;
Wang, Zhijun ;
Dang, Yingying ;
Gu, Yuefeng .
COMPUTATIONAL MATERIALS SCIENCE, 2018, 155 :331-339
[30]   An Evolutionary Many-Objective Optimization Algorithm Using Reference-Point Based Nondominated Sorting Approach, Part II: Handling Constraints and Extending to an Adaptive Approach [J].
Jain, Himanshu ;
Deb, Kalyanmoy .
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2014, 18 (04) :602-622