Fault Detection for Wind Turbine System Using Fractional Extended Dispersion Entropy and Cumulative Sum Control Chart
Kaixuan Shao, Yigang He, Xiaoyan Liu, Zhikai Xing, Bolun Du
Abstract
Reliable and quick fault detection is crucial for the wind turbine system (WTS) to detect any potential abnormalities and early faults in time. However, constructing sensitive indicators to reflect the operation state of WTS is still a challenging work. In view of the conceptions of fractional calculus and dispersion entropy, this paper proposes a novel indicator called fractional extended dispersion entropy (FrEDE) to cope with the challenge. Specifically, a connection block with an information factor is first applied to enhance the utilization of information in the raw signals. Moreover, fractional calculus is integrated into entropy calculation to support a constructive interplay in the fault detection of complex WTS. The experiments on simulated data investigate the effect of parameters on FrEDE and verify its ability to detect the dynamic changes of complex system. Finally, FrEDE is further applied to two real-world datasets. Comparative experimental results show that FrEDE is able to accurately differentiate normal between faulty states, and a detection scheme fusing FrEDE and cumulative sum control chart (CUSUM) is accessible to detect abnormal stats and provide early failure alarm effectively.