A novel neural network-based alloy design strategy: Gated recurrent unit machine learning modeling integrated with orthogonal experiment design and data augmentation

被引:23
作者
Yin, Jie [1 ]
Lei, Qian [1 ]
Li, Xiang [2 ]
Zhang, Xiaoyan [1 ]
Meng, Xiangpeng [2 ]
Jiang, Yanbin [2 ]
Tian, Liang [3 ]
Zhou, Shuang [1 ]
Li, Zhou [2 ]
机构
[1] Cent South Univ, State Key Lab Powder Met, Changsha 410083, Peoples R China
[2] Cent South Univ, Sch Mat Sci & Engn, Changsha 410083, Peoples R China
[3] Univ Alabama, Off Informat Technol, Tuscaloosa, AL 35487 USA
基金
中国国家自然科学基金;
关键词
Alloy design; Machine learning; Copper alloys; Gated recurrent unit; Orthogonal experiment; HIGH ELECTRICAL-CONDUCTIVITY; HIGH-STRENGTH; MECHANICAL-PROPERTIES; ULTRAHIGH STRENGTH; MICROSTRUCTURE; CR; OPTIMIZATION; PERFORMANCE;
D O I
10.1016/j.actamat.2022.118420
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Machine learning-aided alloy design has recently attracted broad interest among the materials science community. However, the prediction accuracy of general machine learning models is limited due to a limited number of model hyperparameters and their dedicated application domains. The artificial neural network (ANN) model can significantly improve the prediction accuracy. At the same time, it suffers from the well-known curse of dimensionality issue (i.e., the amount of required training data increases exponentially with input feature dimensions). In this work, a novel alloy design strategy through a Gated recurrent unit (GRU) deep learning model, orthogonal experimental design and data augmentation technique was developed. Under the case of orthogonal experimental design and data augmentation, the GRU model, compared with the regular feed-forward neural network model, reduced the amount of training data required for accurate prediction and dramatically improved model prediction accuracy. The experimental results further verified that the GRU model exhibited the best prediction accuracy in the case of data augmentation and orthogonal experimental sampling. In addition, the prediction trend of GRU model and the analysis results of orthogonal experiment indicated the main factors affecting yield strength were HD (Hot rolling deformation), CD (Cold rolling deformation), AT (Aging temperature), the main factors affecting conductivity were AT (Aging temperature), At (Aging time). Finally, a high strength and high conductivity Cu-Ni-Si alloy with a tensile strength of 923 MPa, a yield strength of 685 MPa, and electrical conductivity of 47.2% IACS was predicted by using 36 experimental data through the strategy. These findings provide a new machine learning method to predict the properties through dozens of experimental data. (c) 2022 Acta Materialia Inc. Published by Elsevier Ltd. All rights reserved.
引用
收藏
页数:15
相关论文
共 73 条
  • [1] Ahn J.H., MATER CHARACT
  • [2] [Anonymous], 2016, J MATER ENG PERFORM, V25, P1336
  • [3] Bai EW, 2014, CHIN CONTR CONF, P6, DOI 10.1109/ChiCC.2014.6896586
  • [4] SMOTE for high-dimensional class-imbalanced data
    Blagus, Rok
    Lusa, Lara
    [J]. BMC BIOINFORMATICS, 2013, 14
  • [5] Quantum chemical accuracy from density functional approximations via machine learning
    Bogojeski, Mihail
    Vogt-Maranto, Leslie
    Tuckerman, Mark E.
    Mueller, Klaus-Robert
    Burke, Kieron
    [J]. NATURE COMMUNICATIONS, 2020, 11 (01)
  • [6] Molecular ferroelectric/semiconductor interfacial memristors for artificial synapses
    Cai, Yichen
    Zhang, Jialong
    Yan, Mengge
    Jiang, Yizhou
    Jawad, Husnain
    Tian, Bobo
    Wang, Wenchong
    Zhan, Yiqiang
    Qin, Yajie
    Xiong, Shisheng
    Cong, Chunxiao
    Qiu, Zhi-Jun
    Duan, Chungang
    Liu, Ran
    Hu, Laigui
    [J]. NPJ FLEXIBLE ELECTRONICS, 2022, 6 (01)
  • [7] Microstructure and Precipitate Evolution in Cu-3.2Ni-0.75Si Alloy Processed by Twin-Roll Strip Casting
    Cao, Guangming
    Zhang, Shuang
    Chen, Jian
    Jia, Fei
    Fang, Feng
    Li, Chenggang
    [J]. JOURNAL OF MATERIALS ENGINEERING AND PERFORMANCE, 2021, 30 (02) : 1318 - 1329
  • [8] Cho K, 2014, ARXIV14061078, P1724
  • [9] Enhanced thermoelectric performance of skutterudites via orthogonal experimental design
    Deng, L.
    Qin, J. M.
    Jia, X. P.
    Guo, X.
    [J]. JOURNAL OF ALLOYS AND COMPOUNDS, 2017, 695 : 3152 - 3155
  • [10] An optimization method for multi-objective and multi-factor designing of a ceramic slurry: Combining orthogonal experimental design with artificial neural networks
    Deng, Lina
    Feng, Bo
    Zhang, Yue
    [J]. CERAMICS INTERNATIONAL, 2018, 44 (13) : 15918 - 15923