A novel approach based on pattern recognition techniques to evaluate magnetic properties of a non-grain oriented electrical steel in the secondary recrystallization process

被引:7
作者
Duarte, Larissa Moreira [1 ]
de Alencar Santos, Jose Daniel [1 ]
Costa Freitas, Francisco Nelio [1 ]
Reboucas Filho, Pedro Pedrosa [2 ]
Gomes de Abreu, Hamilton Ferreira [3 ]
机构
[1] Fed Inst Educ Sci & Technol Ceara IFCE, Dept Ind, Maracanau, Ceara, Brazil
[2] Fed Inst Educ Sci & Technol Ceara IFCE, Dept Ind, Fortaleza, Ceara, Brazil
[3] Fed Univ Ceara UFC, Dept Met & Mat Engn, Fortaleza, Ceara, Brazil
关键词
Machine learning; Non-grain oriented steel; Magnetic losses; Hysteresis loop; Secondary recrystallization; Classifiers; EXTREME LEARNING-MACHINE; TEXTURE; MICROSTRUCTURE; CLASSIFICATION; REGRESSION; EVOLUTION; ENERGY; MODEL; SVM; PREDICTION;
D O I
10.1016/j.measurement.2020.108135
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
This paper proposes a new automatic approach based on machine learning strategies to associate the microstructural conditions of Non-Grain Oriented (NGO) steels, during secondary recrystallization, with their magnetic losses, which were determined from hysteresis loops. These hysteresis curves and the states of the secondary recrystallization enabled us to establish the feature extraction and the labels for the classification problem. We also applied a specific methodology to create synthetic samples to overcome the available database, which was too small, and its imbalance among the classes. As far as the authors know, this is the first time that a study has treated this issue in this manner. Normally, magnetic losses of NGO steels are analyzed through expensive and laborious tests. We evaluated our proposal through computer experiments with several state-of-the-art classifiers. The Least Squares Support Vector Machine (LSSVM) achieved the best results with 88.9% accuracy using real samples. (C) 2020 Elsevier Ltd. All rights reserved.
引用
收藏
页数:13
相关论文
共 96 条
  • [1] CWV-BANN-SVM ensemble learning classifier for an accurate diagnosis of breast cancer
    Abdar, Moloud
    Makarenkov, Vladimir
    [J]. MEASUREMENT, 2019, 146 : 557 - 570
  • [2] Aguirre L.A., 1999, INTRO IDENTIFICACAO
  • [3] [Anonymous], 1998, Tech. rep.
  • [4] [Anonymous], 2013, NONL SYST ID NARM
  • [5] [Anonymous], 1998, ICML
  • [6] [Anonymous], THESIS
  • [7] [Anonymous], 2002, LEAST SQUARES SUPPOR
  • [8] Hyperspectral image nonlinear unmixing and reconstruction by ELM regression ensemble
    Ayerdi, Borja
    Grana, Manuel
    [J]. NEUROCOMPUTING, 2016, 174 : 299 - 309
  • [9] Bencheikh A., 2018, INT C ADV INT SYST S, P287
  • [10] Bhatia N., 2010, ARXIV10070085