Incipient fault detection of wind turbine large-size slewing bearing based on circular domain

Abstract

Incipient fault detection of wind turbine large-size slewing bearings is crucial to their high availability and profitable operation. Many studies have been conducted using time-domain, frequency-domain analysis for fault feature extraction. However, they suffer from inherent disadvantages, such as spectrum leakage analysis under variable speed, which make them unsuitable for incipient fault detection. To overcome these shortcomings, a novel incipient weak fault feature extraction method is proposed based on circular domain analysis and piecewise aggregate approximation. A systematic methodology based on circular domain resampling approach is proposed to map the time series signals into angle domain, and eliminate the time attribute. Piecewise aggregate approximation with neighborhood correlation is utilized to reduce the amount of circular-domain signals, and detect the frequency variation of vibration signals when an incipient fault occurs. The application and superiority of the proposed methodology are validated using a wind turbine large-size bearing life-cycle test dataset. Meanwhile, a comparison is conducted between traditional fault features and various circular domain models. Results show that the proposed method has a better performance in detecting incipient faults for wind turbine large-size bearing.