Stator Short-Circuit Diagnosis in Induction Motors Using Mutual Information and Intelligent Systems

被引：56

作者：

Bazan, Gustavo Henrique ^{[1
,2
]}

Scalassara, Paulo Rogerio ^{[3
]}

Endo, Wagner ^{[3
]}

Goedtel, Alessandro ^{[3
]}

Cunha Palacios, Rodrigo Henrique ^{[3
]}

Godoy, Wagner Fontes ^{[3
]}

机构：

[1] Fed Inst Parana, Dept Control & Ind Proc, BR- 8640000 Jacarezinho, Brazil

[2] Univ Tecnol Fed Parana, Dept Elect Engn, BR-86300000 Cornelio Procopio, Brazil

[3] Univ Tecnol Fed Parana, Dept Elect & Comp Engn, BR-86300000 Cornelio Procopio, Brazil

来源：

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS | 2019年 / 66卷 / 04期

关键词：

Artificial neural networks (ANNs); decision trees (DTs); induction motors; mutual information (MI); stator winding fault detection; FAULT-DETECTION; WINDING FAULTS; TURN-FAULT; MACHINES; SIGNATURES;

D O I：

10.1109/TIE.2018.2840983

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper proposes a novel approach for detection of stator short-circuit faults in three-phase induction motors. The method is based on two stages: feature extraction and classification by intelligent systems. First, mutual information is estimated from delayed stator current signals, which are used as inputs of C4.5 decision trees and multilayer perceptron neural networks in the second step. Several offline and online experimental tests are presented considering voltage unbalance, load torque variations, and 1% to 10% short-circuit levels. The obtained results corroborate the effectiveness of this new diagnostic approach.

引用

页码：3237 / 3246

页数：10

共 40 条

[1] Evaluation of respiratory muscles activity by means of cross mutual information function at different levels of ventilatory effort [J].

Alonso, Joan Francesc ;

Mananas, Miguel A. ;

Hoyer, Dirk ;

Topor, Zbigniew L. ;

Bruce, Eugene N. .

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2007, 54 (09) :1573-1582

[2]

[Anonymous], 2009, ACM SIGKDD explorations newsletter, DOI 10.1145/1656274.1656278

[3] Fault Diagnosis of the Asynchronous Machines Through Magnetic Signature Analysis Using Finite-Element Method and Neural Networks [J].

Barzegaran, Mohammadreza ;

Mazloomzadeh, Ali ;

Mohammed, Osama A. .

IEEE TRANSACTIONS ON ENERGY CONVERSION, 2013, 28 (04) :1064-1071

[4] An Empirical Demodulation for Electrical Fault Detection in Induction Motors [J].

Batista, Fabiano Bianchini ;

Monteiro Lamim Filho, Paulo Cezar ;

Pederiva, Robson ;

Diniz Silva, Vinicius Augusto .

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2016, 65 (03) :559-569

[5] Advances in Diagnostic Techniques for Induction Machines [J].

Bellini, Alberto ;

Filippetti, Fiorenzo ;

Tassoni, Carta ;

Capolino, Gerard-Andre .

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2008, 55 (12) :4109-4126

[6] Induction Motor Bearing Fault Analysis Using a Root-MUSIC Method [J].

Boudinar, Ahmed Hamida ;

Benouzza, Noureddine ;

Bendiabdellah, Azeddine ;

Khodja, Mohammed-El-Amine .

IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS, 2016, 52 (05) :3851-3860

[7] New Expressions of Symmetrical Components of the Induction Motor Under Stator Faults [J].

Bouzid, Monia Ben Khader ;

Champenois, Gerard .

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2013, 60 (09) :4093-4102

[8]

Cover Thomas M, 2006, Elements of information theory

[9] A novel multi-agent approach to identify faults in line connected three-phase induction motors [J].

Cunha Palacios, Rodrigo H. ;

da Silva, Ivan N. ;

Goedtel, Alessandro ;

Godoy, Wagner F. .

APPLIED SOFT COMPUTING, 2016, 45 :1-10

[10] A comprehensive evaluation of intelligent classifiers for fault identification in three-phase induction motors [J].

Cunha Palacios, Rodrigo H. ;

da Silva, Ivan Nunes ;

Goedtel, Alessandro ;

Godoy, Wagner F. .

ELECTRIC POWER SYSTEMS RESEARCH, 2015, 127 :249-258

← 1 2 3 4 →