论文信息 - Bearing Defect Detection Using Envelope Extraction for Dimension Reduction

Bearing Defect Detection Using Envelope Extraction for Dimension Reduction

Fault detection of the rolling element bearing (REB) has been the subject of extensive research because of its detrimental influence on the reliability of machines. Vibration-based condition monitoring is one of the commonly used methods. In most cases, vibration signals are attenuated and contaminated resulting from background noise and complex structure. Independent component analysis (ICA) has been proved to be an effective method to separate bearing defect related feature from background noise. However, it is a prerequisite that the number of observations has to be larger than that of sources. The requirement cannot be satisfied in helicopter main gearbox (MGB) bearing condition monitoring because it is not possible to install more sensors than vibration sources considering the complexity of the MGB. Hence, this paper investigates the feasibility of using envelope extraction to reduce signal dimension. The experiment was conducted on a MGB operating under different load level and input speed. The results show that bearing defect related feature was observed by combing envelope extraction and the ICA method.

[1] Fang Duan,et al. Using independent component analysis scheme for helicopter main gearbox bearing defect identification , 2017, 2017 IEEE International Conference on Prognostics and Health Management (ICPHM).

[2] Peter W. Tse,et al. Faulty bearing signal recovery from large noise using a hybrid method based on spectral kurtosis and ensemble empirical mode decomposition , 2012 .

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

[4] Ming Liang,et al. An adaptive SK technique and its application for fault detection of rolling element bearings , 2011 .

[5] J. Antoni. Fast computation of the kurtogram for the detection of transient faults , 2007 .

[6] S StalinS.. Fault Diagnosis and Automatic Classification of Roller Bearings Using Time-Domain Features and Artificial Neural Network , 2014 .

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

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

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