Authors: Wenqing Zhao; Min Cui
Addresses: School of Control and Computer Engineering, North China Electric Power University, Baoding 071003, China ' School of Control and Computer Engineering, North China Electric Power University, Baoding 071003, China
Abstract: The health status evaluation of electric power equipment is an important issue with extensive concerns in power system community around the globe. In consideration of the uncertain characteristics of the monitoring data of wind turbines, a real-time health status evaluation method for wind turbines is presented employing the advantages of the cloud model in dealing with uncertain information. In the presented method, real-time data are analysed based on the well-established unsupervised clustering to partition the operational space. The health evaluation model is then trained based on the cloud model and cloud transformation, combining with SCADA historical state data and fully considering the uncertain information of wind turbines. The proposed model is applied to evaluate the health conditions of a 1.5 MW wind turbine located in northern China, and it is demonstrated that this model can detect the changing trend, and hence promote reliability of wind turbines, and reduce maintenance costs.
Keywords: electric power equipment; cloud model; cloud transformation; health evaluation; unsupervised clustering.
International Journal of Simulation and Process Modelling, 2020 Vol.15 No.1/2, pp.134 - 144
Received: 12 Sep 2018
Accepted: 27 Apr 2019
Published online: 22 Apr 2020 *