Radial basis function neural network based comparison of dimensionality reduction techniques for effective bearing diagnostics

Abstract

This article uses the cluster dependent weighted fuzzy C-means based radial basis function neural network for comparing the different dimensionality reduction techniques for the fault diagnosis in the rolling element bearing. The vibration signals from normal bearing, bearing with defect on the inner race, and bearing with defect on the outer race were acquired under one radial load and two shaft speeds. These signals were subjected to the wavelet transform based denoising from which several time and frequency domain features were extracted. Dimensionality reduction techniques, namely, principal component analysis, Fisher’s criterion, and separation index, have been used to select the sensitive features. The selected features were used to train and test the radial basis function neural network, where the centers of the radial basis function units have been optimized by the cluster dependent weighted fuzzy C-means and the widths of the radial basis function units have been fixed by trial and error. Finally, a comparison of the dimensionality reduction techniques based on the radial basis function neural network performance is presented.

Keywords

Rolling element bearing vibration signal analysis wavelet denoising radial basis function fuzzy C-means principal component analysis Fisher’s criterion

Get full access to this article

View all access options for this article.

References

Tandon

Choudhury

. A review of vibration and acoustic measurement methods for the detection of defects in rolling element bearings. Tribol Int 1999; 32: 469–480.

Patil

Mathew

Rajendrakumar

. Bearing signature analysis as a medium for fault detection: a review. J Tribol 2008; 130: 014001-1–014001-7.

Hong H and Liang M. De-noising mechanical signals by hybrid thresholding. In: Proceedings of the IEEE international workshop on robotic and sensors environments (ROSE 2005), Ottawa, ON, Canada. 30 September–1 October 2005, pp.65--70, Piscataway, NJ: IEEE.

Yang

Ren

. Wavelet denoising using principal component analysis. Expert Syst Appl 2011; 38: 1073–1076.

Abbasion

Rafsanjani

Farshidianfar

. Rolling element bearings multi-fault classification based on the wavelet denoising and support vector machine. Mech Syst Sig Process 2007; 21: 2933–2945.

. Customized wavelet denoising using intra- and inter-scale dependency for bearing fault detection. J Sound Vib 2008; 313: 342–359.

Wang

. Enhancement of signal denoising and multiple fault signatures detecting in rotating machinery using dual-tree complex wavelet transform. Mech Syst Sig Process 2010; 24: 119–137.

Wang

. Multiwavelet denoising with improved neighbouring coefficients for application on rolling bearing fault diagnosis. Mech Syst Sig Process 2011; 25: 285–304.

Feng

Jiang

. Rolling element bearing fault detection based on optimal antisymmetric real Laplace wavelet. Measurement 2011; 44: 1582–1591.

10.

Jiang

Tang

Qin

. Feature extraction method of wind turbine based on adaptive Morlet wavelet and SVD. Renewable Energy 2011; 36: 2146–2153.

11.

Donoho

. De-noising by soft-thresholding. IEEE Trans Inf Theory 1995; 41(3): 613–627.

12.

Michel M, Yves M, Georges O, et al. Wavelet toolbox™ 4 user’s guide. Version 4. Natick, MA: The MathWorks Inc., 2010, pp.4-101–4-115.

13.

Donoho

Johnstone

. Ideal spatial adaptation by wavelet shrinkage. Biometrika 1994; 81(3): 425–455.

14.

Peng YH. De-noising by modified soft-thresholding. In: Proceedings of the IEEE Asia-Pacific conference on circuits and systems, IEEE APCCAS 2000, Crystal Palace Hotel, Tianjin, China, 4–6 December 2000, pp.760--762. Piscataway, NJ: IEEE.

15.

Lin Y and Cai J. A new threshold function for signal denoising based on wavelet transform. In: Proceedings of the 2010 international conference on measuring technology and mechatronics automation, Changsha City, China, 13–14 March 2010, pp.200--203. Piscataway, NJ: IEEE.

16.

Fang H-T and Huang D-S. Wavelet de-noising by means of trimmed thresholding. In: Proceedings of the 5th world congress on intelligent control and automation, Hangzhou, China, 15–19 June 2004, pp.1621--1624. Piscataway, NJ: IEEE.

17.

Jack

Nandi

. Fault detection using support vector machines and artificial neural networks, augmented by genetic algorithms. Mech Syst Sig Process 2002; 16(2–3): 373–390.

18.

Peng

Chu

. Application of the wavelet transform in machine condition monitoring and fault diagnostics: a review with bibliography. Mech Syst Sig Process 2004; 18: 199–221.

19.

Randall

Antoni

. Rolling element bearing diagnostics—a tutorial. Mech Syst Sig Process 2011; 25: 485–520.

20.

Samanta

Al-Balushi

Al-Araimi

. Bearing fault detection using artificial neural networks and genetic algorithm. EURASIP J Appl Sig Process 2004; 3: 366–377.

21.

Samanta

Al-Balushi

Al-Araimi

. Artificial neural networks and genetic algorithm for bearing fault detection. Soft Comput 2006; 10: 264–271.

22.

Alguindigue

Loskiewicz-Buczak

Uhrig

. Monitoring and diagnosis of rolling element bearings using artificial neural networks. IEEE Trans Ind Electron 1993; 40(2): 209–217.

23.

Chow

Tipsuwan

. Neural-network-based motor rolling bearing fault diagnosis. IEEE Trans Ind Electron 2000; 47(5): 1060–1069.

24.

Samanta

Al-Balushi

. Artificial neural network based fault diagnostics of rolling element bearings using time-domain features. Mech Syst Sig Process 2003; 17(2): 317–328.

25.

Al-Raheem

Roy

Ramachandran

. Application of the Laplace-wavelet combined with ANN for rolling bearing fault diagnosis. J Vib Acoust 2008; 130(5): 051007-1–051007-9.

26.

Castejon

Lara

Garcia-Prada

. Automated diagnosis of rolling bearings using MRA and neural networks. Mech Syst Sig Process 2010; 24: 289–299.

27.

Wang

Kang

Shen

. Applications of fault diagnosis in rotating machinery by using time series analysis with neural network. Expert Syst Appl 2010; 37: 1696–1702.

28.

Kankar

Satish Sharma

Harsha

. Fault diagnosis of ball bearings using machine learning methods. Expert Syst Appl 2011; 38: 1876–1886.

29.

Zarei

. Induction motors bearing fault detection using pattern recognition techniques. Expert Syst Appl 2012; 39: 68–73.

30.

Izzet

Dalci

Senol

. Detection of bearing defects in three-phase induction motors using Park’s transform and radial basis function neural networks. Sadhana 2006; 31(3): 235–244.

31.

Lei

Zhengji

Yanyang

. Application of an intelligent classification method to mechanical fault diagnosis. Expert Syst Appl 2009; 36: 9941–9948.

32.

Vijay GS, Srinivasa Pai P, Sriram NS, et al. Bearing diagnostics – a radial basis function neural network approach. In: Proceedings of the international conference on COMADEM2011, Stavanger, Norway, 30 May–1 June 2011, pp.843–854.

33.

Haykin

. Neural networks – a comprehensive foundation, Delhi: Prentice Hall, 1999.

34.

Srinivasa Pai

Nagabhushana

Ramakrishna Rao

. Radial basis function neural networks for tool wear monitoring: a critical evaluation. Int J COMADEM 2002; 5(3): 21–30.

35.

Nagabhushana

Srinivasa Pai

Rao Raj

BKN

. Neural network based tool wear monitoring techniques: a critical performance evaluation. Int J COMADEM 2004; 7(1): 29–38.

36.

Samanta

Al-Balushi

Al-Araimi

. Artificial neural networks and support vector machines with genetic algorithm for bearing fault detection. Eng Appl Artif Intell 2003; 16: 657–665.

37.

Saxena

Saad

. Evolving an artificial neural network classifier for condition monitoring of rotating mechanical systems. Appl Soft Comput 2007; 7: 441–454.

38.

Sreejith B, Vermaand AK and Srividya A. Fault diagnosis of rolling element bearing using time-domain features and neural networks. In: Proceedings of the IEEE region 10 colloquium and the third ICIIS, Kharagpur, India, 8–10 December 2008, vol. 409, pp.1--6. Piscataway, NJ: IEEE.

39.

Smith LI. A tutorial on principal components analysis. Technical Report, University of Otago, 2002, http://www.sccg.sk/∼haladova/principal_components.pdf (2002, accessed 20 May 2012).

40.

Xia M, Kong F and Hu F. An approach for bearing fault diagnosis based on PCA and multiple classifier fusion. In: Proceedings of the 6th IEEE joint international information technology and artificial intelligence conference (ITAIC), Chongqing, China, 20–22 August 2011, pp.321--325. Piscataway, NJ: IEEE.

41.

Yin S, Steven XD, Naik A, et al. On PCA-based fault diagnosis techniques. In: Proceedings of the conference on control and fault tolerant systems, Nice, France, 6–8 October 2010, pp.179--184. Piscataway, NJ: IEEE.

42.

Li P, Kong F and Dang L. A new fault diagnosis system for train bearings based on PCA and ACO. In: Proceedings of the 2010 IEEE international conference on logistics, systems and intelligent management, Harbin Heilongjiang, China, 9–10 January 2010, pp.526--530. Piscataway, NJ: IEEE.

43.

Yen

Lin

K-C

. Wavelet packet feature extraction for vibration monitoring. IEEE Trans Ind Electron 2000; 47(3): 650–667.

44.

Fuente MJ, Garcia-Alvarez D, Sainz-Palmero GI, et al. Fault detection and identification method based on multivariate statistical techniques. In: Proceedings of the IEEE conference on emerging technologies and factory automation (EFTA 2009), Mallorca, Spain, 22–25 September 2009, pp.1--6. Piscataway, NJ: IEEE.

45.

Tang X-C and Li Y. Monitoring and fault diagnosis using fisher discrimnant analysis. In: Proceedings of the 6th international conference on machine learning and cybernetics, Hong Kong, 19–22 August 2007, pp.1100--1105, Piscataway, NJ: IEEE.

46.

Kim EY, Andy Tan CC, Yang B-S, et al. Experimental study on condition monitoring of low speed bearings in time domain. In: F Albermani (ed.) Proceedings of the 5th Australian congress on applied mechanics, Brisbane, Australia, 10–12 December 2007. Brisbane, Australia: Queensland University of Technology.

47.

Lei

Zhengji

Yanyang

. A new approach to intelligent fault diagnosis of rotating machinery. Expert Syst Appl 2008; 35: 1593–1600.

48.

Senguler

Karatoprak

Serker

. A new MLP approach for the detection of the incipient bearing damage. Adv Electr Comput Eng 2010; 10(3): 34–39.

49.

Hadjahmadi AH, Homayounpour MM and Ahadi SM. Robust weighted fuzzy C-means clustering. In: Proceedings of the IEEE international conference on fuzzy systems (FUZZ2008), Hong Kong, China, 1--6 June 2008, pp.305--311. Piscataway, NJ: IEEE.

50.

Chen J-L and Wang J-H. A new robust clustering algorithm-density-weighted fuzzy C-means. In: Proceedings of the IEEE international conference on systems, man, and cybernatics IEEE SMC ‘99, Tokyo, Japan, 12–15 October 1999, vol. III, pp.90--94, Piscataway, NJ: IEEE.