A predicting model for properties of steel using the industrial big data based on machine learning

被引:90
作者
Guo, Shun [1 ]
Yu, Jinxin [1 ,2 ,3 ]
Liu, Xingjun [4 ,5 ]
Wang, Cuiping [2 ,3 ]
Jiang, Qingshan [1 ]
机构
[1] Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen 518000, Guangdong, Peoples R China
[2] Xiamen Univ, Coll Mat, Xiamen 361000, Fujian, Peoples R China
[3] Xiamen Univ, Fujian Prov Key Lab Mat Genome, Xiamen 361000, Fujian, Peoples R China
[4] Harbin Inst Technol, State Key Lab Adv Welding & Joining, Harbin 150001, Heilongjiang, Peoples R China
[5] Harbin Inst Technol Shenzhen, Inst Mat Genome & Big Data, Shenzhen 518000, Guangdong, Peoples R China
基金
中国博士后科学基金; 国家重点研发计划;
关键词
Big data; Machine learning; Regression; Steel properties; Nonlinear programming; ALLOYING ELEMENTS; ALGORITHM; OPTIMIZATION; BEHAVIOR; SEARCH;
D O I
10.1016/j.commatsci.2018.12.056
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Extracting the valuable information about the connections between the overall properties and the related factors from the industrial big data of materials is of significant interest to the materials engineering. At present, most data-driven approaches focus on building a relation model for a single property of the materials, where it may ignore the restrictive boundaries of other properties. In this paper, we propose a machine-learning-based method using nonlinear programming for multiple properties of the materials, and solve the problem by using the Interior Point Algorithm. The key idea is to take the mapping functions corresponding to the properties of the materials as the constraints of the nonlinear programming problem, thus it is capable of processing the restrictions of these properties. Moreover, with our method, the possible boundaries of these properties under certain conditions can be calculated. Experiments results on steel production data demonstrate the rationality and reliability of the proposed method.
引用
收藏
页码:95 / 104
页数:10
相关论文
共 49 条
[1]   Exploration of data science techniques to predict fatigue strength of steel from composition and processing parameters [J].
Agrawal A. ;
Deshpande P.D. ;
Cecen A. ;
Basavarsu G.P. ;
Choudhary A.N. ;
Kalidindi S.R. .
Integrating Materials and Manufacturing Innovation, 2014, 3 (01) :90-108
[2]  
An L.C., 2015, FOUNDRY TECHNOL, P847
[3]  
[Anonymous], MATH GAZETTE, DOI DOI 10.1017/S0025557200105583
[4]  
Axelsson O., 1990, PRECONDITIONED CONJU
[5]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32
[6]   Support Vector Machines for classification and regression [J].
Brereton, Richard G. ;
Lloyd, Gavin R. .
ANALYST, 2010, 135 (02) :230-267
[7]  
Browne WNL, 2004, STUD FUZZ SOFT COMP, V150, P223
[8]   A trust region method based on interior point techniques for nonlinear programming [J].
Byrd, RH ;
Gilbert, JC ;
Nocedal, J .
MATHEMATICAL PROGRAMMING, 2000, 89 (01) :149-185
[9]   An interior point algorithm for large-scale nonlinear programming [J].
Byrd, RH ;
Hribar, ME ;
Nocedal, J .
SIAM JOURNAL ON OPTIMIZATION, 1999, 9 (04) :877-900
[10]  
Callister Jr W.D, 2000, ANTICORROS METHODS M