Multi-fault diagnosis method for wind power generation system based on recurrent neural network. (August 2019)

• Record Type: Journal Article
• Authors: Wang, Junnian; Dou, Yao; Wang, Zhenheng; Jiang, Dan
• Other Names: Childs Peter guest-editor.; Kurt Erol guest-editor.; Liu Zhongwei guest-editor.
• Is Part Of: Proceedings of the Institution of Mechanical Engineers. Volume 233:Number 5(2019)
• Page Start: 604
• Page End: 615
• Publication Date: 2019-08
• Subjects: Wind turbine -- fault diagnosis -- data driven -- deep learning -- classification prediction; Mechanical engineering -- Periodicals; Power (Mechanics) -- Periodicals; Production engineering -- Periodicals; 621
• DOI: 10.1177/0957650919844065
• Languages: English
• ISSNs: 0957-6509

Abstract

With the continuous expansion of the scale of wind turbine system, wind power production, operation and equipment control of wind turbine have become more and more significant. To improve the reliability of wind turbine systems fault diagnosis, combining with data-driven technology, this paper proposes a multi-fault diagnosis method for wind power system based on recurrent neural network. According to the actual wind speed data, the normal operation and fault data of the wind turbine system are obtained by system modeling, and the classification and prediction model based on the recurrent neural network algorithm is established, which takes 30 characteristic parameters such as wind speed, rotor speed, generator speed and power generation as input, and 10 different types faults labels of the wind turbine as output. Specific rules formed inside the sample data of the wind turbine system are learned intelligently by the model which is continuously trained, optimized and tested to verify the feasibility of the algorithm. The results of evaluation standards such as accuracy rate, missed detection rate and F1-measure that compared with other related algorithms such as deep belief network show that the proposed algorithm can solve the problem of multi-classification fault diagnosis for wind power generation system efficiently.