Reliable multiple combined fault diagnosis of bearings using heterogeneous feature models and multiclass support vector Machines

被引:128
作者
Islam, M. M. Manjurul [1 ]
Kim, Jong-Myon [1 ]
机构
[1] Univ Ulsan, Dept Elect Elect & Comp Engn, Bldg 7,Room 7-304-1,93 Daehak Ro, Ulsan 44610, South Korea
基金
新加坡国家研究基金会;
关键词
Bearings (mechanical); Envelope signal processing; Feature extraction; Support vector machines; Nearest neighborhood search; Fault detection and diagnosis; Data-driven diagnostic; Reliability;
D O I
10.1016/j.ress.2018.02.012
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
This paper proposes a reliable multiple combined fault diagnosis scheme for bearings using heterogeneous feature models and an improved one-against-all multiclass support vector machines (OAA-MCSVM) classifier. Distinct feature extraction methods are simultaneously applied to an acoustic emission (AE) signal to extract unique fault features for diagnosing bearing defects. These fault features are composed of time domain, frequency domain statistical parameters, and complex envelope spectrum analysis. Generally, a high-dimensional feature vector is used to train the standard OAA-MCSVM classifier for diagnosis and identification of bearing defects. However, this classification method ignores individual classifier competence when results from multiple classes are agglomerated for the final decision, and therefore, yields undecided and overlapped feature spaces where classification accuracy is severely degraded. To solve this unreliability problem, this paper introduces a dynamic reliability measure (DReM) technique for individual support vector machines (SVMs) in the one-against-all (OAA) framework. This DReM accounts for the spatial variation of the classifier's performance by finding the local neighborhood of a test sample in the training samples space and defining a new decision function for the OAA-MCSVM. The efficacy of the proposed OAA-MCSVM classifier with DReM is tested for identifying single and multiple combined faults in low-speed bearings. The experimental results demonstrate that the proposed classifier technique is superior to three state-of-the-art algorithms, yielding 6.19-16.59% improvement in the average classification performance. (C) 2018 Elsevier Ltd. All rights reserved.
引用
收藏
页码:55 / 66
页数:12
相关论文
共 32 条
[1]   Fuzzy support vector machines for multilabel classification [J].
Abe, Shigeo .
PATTERN RECOGNITION, 2015, 48 (06) :2110-2117
[2]  
[Anonymous], 2017, J AMBIENT INTELL HUM
[3]   A multi-objective artificial immune algorithm for parameter optimization in support vector machine [J].
Aydin, Ilhan ;
Karakose, Mehmet ;
Akin, Erhan .
APPLIED SOFT COMPUTING, 2011, 11 (01) :120-129
[4]   A review on data-driven fault severity assessment in rolling bearings [J].
Cerrada, Mariela ;
Sanchez, Rene-Vinicio ;
Li, Chuan ;
Pacheco, Fannia ;
Cabrera, Diego ;
de Oliveira, Jose Valente ;
Vasquez, Rafael E. .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2018, 99 :169-196
[5]   Local Classifier Weighting by Quadratic Programming [J].
Cevikalp, Hakan ;
Polikar, Robi .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2008, 19 (10) :1832-+
[6]   Fault diagnosis based on dependent feature vector and probability neural network for rolling element bearings [J].
Chen, Xiaoyue ;
Zhou, Jianzhong ;
Xiao, Jian ;
Zhang, Xinxin ;
Xiao, Han ;
Zhu, Wenlong ;
Fu, Wenlong .
APPLIED MATHEMATICS AND COMPUTATION, 2014, 247 :835-847
[7]  
CORTES C, 1995, MACH LEARN, V20, P273, DOI 10.1023/A:1022627411411
[8]   From Model, Signal to Knowledge: A Data-Driven Perspective of Fault Detection and Diagnosis [J].
Dai, Xuewu ;
Gao, Zhiwei .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2013, 9 (04) :2226-2238
[9]   Bearing Fault Detection by a Novel Condition-Monitoring Scheme Based on Statistical-Time Features and Neural Networks [J].
Delgado Prieto, Miguel ;
Cirrincione, Giansalvo ;
Garcia Espinosa, Antonio ;
Antonio Ortega, Juan ;
Henao, Humberto .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2013, 60 (08) :3398-3407
[10]   Automatic condition monitoring system for crack detection in rotating machinery [J].
Gomez, M. J. ;
Castejon, C. ;
Garcia-Prada, J. C. .
RELIABILITY ENGINEERING & SYSTEM SAFETY, 2016, 152 :239-247