Using independent component analysis scheme for helicopter main gearbox bearing defect identification

Vibration signal analysis is the most common technique for helicopter health condition monitoring. It has been widely employed to detect helicopter gearbox fault and ensure the safe operation. Through the years, vibration signal analysis has a significant contribution to successfully prevent a number of accidents. However, vibration based bearing identification remains a challenge because bearing defects signatures are contaminated by strong background noise. In this paper, the independent component analysis (ICA) scheme was utilized to analyze vibration signals captured from a CS29 Category ‘A’ helicopter main gearbox, where bearing faults were seeded on the second epicyclic stage planetary gears bearing. The ICA scheme could separate the multichannel signals into the mutually independent components. The bearing defect signature can be clearly observed in one of the independent components. The analysis result showed that ICA scheme is a promising method for detecting the bearing fault signatures.

[1]  Jiangxin Yang,et al.  Vibration Sources Identification with Independent Component Analysis , 2006, 2006 6th World Congress on Intelligent Control and Automation.

[2]  Jing Lin,et al.  Gearbox fault diagnosis using independent component analysis in the frequency domain and wavelet filtering , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[3]  Feng Wu,et al.  Automatic fault feature extraction of mechanical anomaly on induction motor bearing using ensemble super-wavelet transform , 2015 .

[4]  Michael Corsar,et al.  Using empirical mode decomposition scheme for helicopter main gearbox bearing defect identification , 2016, 2016 Prognostics and System Health Management Conference (PHM-Chengdu).

[5]  Peter W. Tse,et al.  An enhanced Kurtogram method for fault diagnosis of rolling element bearings , 2013 .

[6]  Aapo Hyvärinen,et al.  Fast and robust fixed-point algorithms for independent component analysis , 1999, IEEE Trans. Neural Networks.

[7]  Fang Duan,et al.  Helicopter main gearbox bearing defect identification with acoustic emission techniques , 2016, 2016 IEEE International Conference on Prognostics and Health Management (ICPHM).

[8]  J. Cardoso.  Infomax and maximum likelihood for blind source separation , 1997, IEEE Signal Processing Letters.

[9]  Mohammed Ben‐Daya,et al.  Condition‐Based Maintenance , 2016 .

[10]  Liangsheng Qu,et al.  Machine diagnosis with independent component analysis and envelope analysis , 2002, 2002 IEEE International Conference on Industrial Technology, 2002. IEEE ICIT '02..

[11]  Jing Na,et al.  Envelope extraction based dimension reduction for independent component analysis in fault diagnosis of rolling element bearing , 2014 .

[12]  David G. Lewicki,et al.  Condition Monitoring of Helicopter Gearboxes by Embedded Sensing , 2002 .

[13]  Nam Phan,et al.  Flight Testing of Wireless Sensing Networks for Rotorcraft Structural Health and Usage Management Systems , 2011 .

[14]  Jagadeesh Pujari,et al.  Neuro-fuzzy fusion in a multimodal face recognition using PCA, ICA and SIFT , 2016 .

[15]  Eric Moulines,et al.  A blind source separation technique using second-order statistics , 1997, IEEE Trans. Signal Process..

[16]  Christopher J James,et al.  Independent component analysis for biomedical signals , 2005, Physiological measurement.

[17]  Michael J. Roan,et al.  A NEW, NON-LINEAR, ADAPTIVE, BLIND SOURCE SEPARATION APPROACH TO GEAR TOOTH FAILURE DETECTION AND ANALYSIS , 2002 .

[18]  Richard M. Everson,et al.  Independent Component Analysis: Principles and Practice , 2001 .