A new integrated analytics approach for wind turbine fault detection using wavelet, RLS filter and random forest

ABSTRACT

Nowadays wind energy production is growing fast, and the cost of operation and maintenance is growing fast also. Most wind turbines (WTs) are equipped with supervisory control and data acquisition (SCADA) system for system control and logging data. Huge amounts of data acquired for SCADA systems can be used for condition monitoring and fault detection (CMDF) by applying data mining methods. However, the collected data are not used effectively. Few researches are about input and output data optimization and proper feature selection.

In this paper, the proposed method regards SCADA data as data points. Wavelet analysis is applied to the input signal to make noise reduction and uses recursive least square (RLS) filter to reduce false alarm rate. On the basis of the general model-based CMDF approach, the random forest algorithm is used to find the best input features. With these methods applied, a more precise output is obtained as well and greatly reduces the false alarm rate as well. Experiments are given with real SCADA data to show the effectiveness of the proposed method.

KEYWORDS:

• SCADA data
• wind turbines
• fault detection
• wavelet denoising
• recursive least square
• adaptive filter

Acknowledgments

This paper is supported by NSFC (Grant No. 41572347) and Renewable Energy Research Center of China Electric Power Research Institute of STATE GRID’s science and technology project: Research on Key Technologies of condition monitoring and intelligent early detection of wind turbine based on big data.

Additional information

Funding

This work was supported by the NSFC [41572347].

Notes on contributors

Shiyao Qin

Shiyao Qin male, 40, deputy director of New Energy Institute of China Electric Power Research Institute, a professor-level senior engineer. Engaged in wind power generation network and test technology research, undertaken a number of major national science and technology projects.

Mengzhou Zhang female, 27, a postgraduate student of China University of Geosciences (Beijing). Her theoretical research interests are Data Mining and Signal Processing.

Xiaojing Ma female, 33, received her master degree in Acoustics from University of Chinese Academy of Sciences in 2009. She is presently working on renewable energy power generation technology. Her research interests focus on acoustic noise, power performance and the mechanical load of wind turbines.

Mei Li Female, 48. She teaches and researches in China University of Geosciences (Beijing). Her theoretical research interests are signal processing and data mining. Her applied research interests are the application of the Internet of Things.