A new framework for intelligent simultaneous-fault diagnosis of rotating machinery using pairwise-coupled sparse Bayesian extreme learning committee machine
Restricted accessResearch articleFirst published online March, 2017
A new framework for intelligent simultaneous-fault diagnosis of rotating machinery using pairwise-coupled sparse Bayesian extreme learning committee machine
This paper proposes a new diagnostic framework, namely, probabilistic committee machine, to diagnose simultaneous-fault in the rotating machinery. The new framework combines a feature extraction method with ensemble empirical mode decomposition and singular value decomposition, multiple pairwise-coupled sparse Bayesian extreme learning machines (PCSBELM), and a parameter optimization algorithm to create an intelligent diagnostic framework. The feature extraction method is employed to find the features of single faults in a simultaneous-fault pattern. Multiple PCSBELM networks are built as different signal committee members, and each member is trained using vibration or sound signals respectively. The individual diagnostic result from each fault detection member is then combined by a new probabilistic ensemble method, which can improve the overall diagnostic accuracy and increase the number of detectable fault as compared to individual classifier acting alone. The effectiveness of the proposed framework is verified by a case study on a gearbox fault detection. Experimental results show the proposed framework is superior to the existing single probabilistic classifier. Moreover, the proposed system can diagnose both single- and simultaneous-faults for the rotating machinery while the framework is trained by single-fault patterns only.
JalanAKMohantyAR. Model based fault diagnosis of a rotor–bearing system for misalignment and unbalance under steady-state condition. J Sound Vib2009; 327: 604–622.
2.
BittencourtACSaarinenKSander-TavallaeyS. A data-driven approach to diagnostics of repetitive processes in the distribution domain – Applications to gearbox diagnostics in industrial robots and rotating machines. Mechatronics2014; 24: 1032–1041.
3.
LoutasTHSotiriadesGKalaitzoglouI. Condition monitoring of a single-stage gearbox with artificially induced gear cracks utilizing on-line vibration and acoustic emission measurements. Appl Acoust2009; 70: 1148–1159.
4.
HuQHeZZhangZ. Fault diagnosis of rotating machinery based on improved wavelet package transform and SVMs ensemble. Mech Syst Signal Process2007; 21: 688–705.
5.
SanzJPereraRHuertaC. Fault diagnosis of rotating machinery based on auto-associative neural networks and wavelet transforms. J Sound Vib2007; 302: 981–999.
6.
WidodoAYangBS. Application of nonlinear feature extraction and support vector machines for fault diagnosis of induction motors. Expert Syst Appl2007; 33: 241–250.
7.
WongPKYangZVongCM. Real-time fault diagnosis for gas turbine generator systems using extreme learning machine. Neurocomputing2014; 128: 249–257.
8.
YangDLiuYLiS. Gear fault diagnosis based on support vector machine optimized by artificial bee colony algorithm. Mech Mach Theory2015; 90: 219–229.
9.
WuJDLiuCH. Investigation of engine fault diagnosis using discrete wavelet transform and neural network. Expert Syst Appl2008; 35: 1200–1213.
10.
YangYYuDChengJ. A fault diagnosis approach for roller bearing based on IMF envelope spectrum and SVM. Measurement2007; 40: 943–950.
11.
JingJMengG. A novel method for multi-fault diagnosis of rotor system. Mech Mach Theory2009; 44: 697–709.
12.
ChenXXiaoLZhangX. A heterogeneous fault diagnosis method for bearings in gearbox. Proc IMechE, Part C: J Mechanical Engineering Science2014; 229: 1491–1499.
13.
VongCMWongPKIpWF. A new framework of simultaneous-fault diagnosis using pairwise probabilistic multi-label classification for time-dependent patterns. IEEE Trans Ind Electron2013; 60: 3372–3385.
14.
YangZWongPKVongCM. Simultaneous-fault diagnosis of gas turbine generator systems using a pairwise-coupled probabilistic classifier. Math Prob Eng2013; 2013: 14–14.
15.
YélamosIEscuderoGGraellsMSimultaneous fault diagnosis in chemical plants using support vector machines. In: ValentinPPaul ŞerbanA (eds). Computer aided chemical engineering, New York: Elsevier, 2007, pp. 1253–1258.
16.
HongLDhupiaJS. A time domain approach to diagnose gearbox fault based on measured vibration signals. J Sound Vib2014; 333: 2164–2180.
17.
LeiYHeZZiY. A new approach to intelligent fault diagnosis of rotating machinery. Expert Syst Appl2008; 35: 1593–1600.
18.
BanerjeeTDasSRoychoudhuryJImplementation of a new hybrid methodology for fault signal classification using short-time Fourier transform and support vector machines. In: CorchadoENovaisPAnalideCSedanoJ (eds). Proceedings of 5th international workshop in soft computing models in industrial and environmental applications, Berlin Heidelberg: Springer, 2010, pp. 219–225.
19.
YanRGaoRXChenX. Wavelets for fault diagnosis of rotary machines: A review with applications. Signal Process2014; 96: 1–15.
20.
LiuBRiemenschneiderSXuY. Gearbox fault diagnosis using empirical mode decomposition and Hilbert spectrum. Mech Syst Signal Process2006; 20: 718–734.
21.
CaiJ. Fault diagnosis of rolling bearing based on empirical mode decomposition and higher order statistics. Proc IMechE, Part C: J Mechanical Engineering Science2014; 229: 1630–1638.
22.
WuZHuangNE. Ensemble empirical mode decomposition: A noise-assisted data analysis method. Adv Adapt Data Anal2009; 1: 1–41.
23.
Van der VeenAJDeprettereEFSwindlehurstAL. Subspace-based signal analysis using singular value decomposition. Proc IEEE1993; 81: 1277–1308.
24.
ChengJYuDTangJ. Application of SVM and SVD technique based on EMD to the fault diagnosis of the rotating machinery. Shock Vib2009; 16.
25.
LiuHWangXLuC. Rolling bearing fault diagnosis under variable conditions using Hilbert-Huang transform and singular value decomposition. Math Prob Eng2014; 2014: Article ID 765621–Article ID 765621.
26.
JiangHChenJDongG. Study on Hankel matrix-based SVD and its application in rolling element bearing fault diagnosis. Mech Syst Signal Process2015; 52–53: 338–359.
27.
DouDYangJLiuJ. A rule-based intelligent method for fault diagnosis of rotating machinery. Knowledge-Based Syst2012; 36: 1–8.
28.
TrespV. A Bayesian committee machine. Neural Comput2000; 12: 2719–2741.
WangCZhouJQinH. Fault diagnosis based on pulse coupled neural network and probability neural network. Expert Syst Appl2011; 38: 14307–14313.
31.
WangGYangYXieQ. Force based tool wear monitoring system for milling process based on relevance vector machine. Adv Eng Softw2014; 71: 46–51.
32.
LuoJVongCMWongPK. Sparse Bayesian extreme learning machine for multi-classification. IEEE Trans Neural Networks Learn Syst2014; 25: 836–843.
33.
WuTFLinCJWengRC. Probability estimates for multi-class classification by pairwise coupling. J Mach Learn Res2004; 5: 975–1005.
34.
RobinsonJRahmat-SamiiY. Particle swarm optimization in electromagnetics. IEEE Trans Antennas Propag2004; 52: 397–407.
35.
TreleaIC. The particle swarm optimization algorithm: Convergence analysis and parameter selection. Inform Process Lett2003; 85: 317–325.
36.
FengZLiangMZhangY. Fault diagnosis for wind turbine planetary gearboxes via demodulation analysis based on ensemble empirical mode decomposition and energy separation. Renew Energy2012; 47: 112–126.
37.
LeiYHeZZiY. Application of the EEMD method to rotor fault diagnosis of rotating machinery. Mech Syst Signal Process2009; 23: 1327–1338.
38.
HuangNEShenZLongSR. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc Roy Soc Lond A: Math Phys Eng Sci1998; 454: 903–995.
39.
BinGGaoJLiX. Early fault diagnosis of rotating machinery based on wavelet packets—Empirical mode decomposition feature extraction and neural network. Mech Syst Signal Process2012; 27: 696–711.
40.
HuangGBDingXZhouH. Optimization method based extreme learning machine for classification. Neurocomputing2010; 74: 155–163.
41.
HuangGBZhouHDingX. Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybernet B: Cybernet2012; 42: 513–529.
42.
BishopCM. Pattern recognition and machine learning, New York: Springer, 2006.
43.
MacKayDJBayesian methods for backpropagation networks. In: DomanyEHemmenJLVSchultenK (eds). Models of neural networks III, New York: Springer, 1996, pp. 211–254.
44.
HastieTTibshiraniR. Classification by pairwise coupling. Ann Stat1998; 26: 451–471.
45.
HripcsakGRothschildAS. Agreement, the f-measure, and reliability in information retrieval. J Am Med Inform Assoc2005; 12: 296–298.
46.
QuYHeDYoonJ. Gearbox tooth cut fault diagnostics using acoustic emission and vibration sensors—A comparative study. Sensors2014; 14: 1372–1393.
47.
WongPKTamLMLiK. Engine idle-speed system modelling and control optimization using artificial intelligence. Proc IMechE, Part D: J Automobile Engineering2010; 224: 55–72.
