Fault diagnosis of a wind turbine rolling bearing using adaptive local iterative filtering and singular value decomposition. (November 2017)

• Record Type: Journal Article
• Authors: An, Xueli; Zeng, Hongtao; Yang, Weiwei; An, Xuemin
• Is Part Of: Transactions of the Institute of Measurement and Control. Volume 39:Number 11(2017)
• Page Start: 1643
• Page End: 1648
• Publication Date: 2017-11
• Subjects: Adaptive local iterative filtering -- fault diagnosis -- singular value decomposition -- spherical roller bearing -- wind turbine; Automatic control -- Periodicals; Measuring instruments -- Periodicals; Commande automatique -- Périodiques; Mesure -- Instruments -- Périodiques; 681.2
• DOI: 10.1177/0142331216644041
• Languages: English
• ISSNs: 0142-3312

Abstract

Adaptive local iterative filtering (ALIF) is a new signal decomposition method that uses the iterative filters strategy together with an adaptive and data-driven filter length selection to achieve the decomposition. The complexity of wind power generation systems means that the randomness and kinetic mutation behaviour of their vibration signals are demonstrated at different scales. Thus it is necessary to analyse the vibration signal across multiple scales. A method based on ALIF and singular value decomposition (SVD) was used for the fault diagnosis of a wind turbine roller bearing. The ALIF method is used to decompose the bearing vibration signal into several stable components. The components, which contain major fault information, are selected to build an initial feature vector matrix. The singular value of the matrix is computed as the feature vectors of each bearing fault. The feature vectors embody the characteristics of the vibration signal. The nearest neighbour algorithm is used as a classifier to identify faults in a roller bearing. Experimental data show that the proposed method can be used to identify roller bearing faults of a wind turbine.