Abstract
Wind turbine fault diagnosis and early warning are important to reduce wind farm operation and maintenance costs and improve power generation efficiency. In this paper, we take the Supervisory Control and Data Acquisition (SCADA) data as the research object and research wind turbine health data purification, fault diagnosis model building, and unit operation status monitoring from a completely data-driven perspective. Firstly, for the problem that Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm cannot identify high-density anomalous data. An anomaly data processing scheme combining a density clustering algorithm and normal power interval estimation is proposed. The accuracy of extracting health data from wind turbines is improved. Secondly, to address the problem that the eXtreme Gradient Boosting (XGBoost) algorithm has more hyperparameters, we propose an optimization scheme based on the Bayesian Optimization Algorithm (BOA) and tree model for feature weight measurement, which improves the efficiency and accuracy of intuitive mapping from SCADA system monitoring data to fault features. Finally, a wind turbine condition monitoring scheme based on the information fusion of multi-characteristic monitoring parameters is designed. The wind turbine condition monitoring scheme proposed in this paper can warn generator system failure 3.67 hours, gearbox system failure 5.17 hours in advance, and hydraulic system failure 2.33 hours in advance.
Highlights
In recent years, with the continuous deterioration of the global ecological environment and the gradual depletion of fossil fuels, wind power generation has gradually become a new power generation mode replacing the traditional power generation mode in the world [1], [2]
Because most wind turbines are installed in remote areas rich in wind energy, such as mountains, wilderness, islands, or even the sea, they are subject to extreme temperature differences and strong wind gusts throughout the year, resulting in a much higher failure rate than other electromechanical equipment [3], [4]
The traditional wind farm unit maintenance strategy is highly dependent on regular maintenance and post-maintenance and can only deal with the monitoring and early warning of part of the wind farm unit [5], [6]
Summary
With the continuous deterioration of the global ecological environment and the gradual depletion of fossil fuels, wind power generation has gradually become a new power generation mode replacing the traditional power generation mode in the world [1], [2]. To solve the problem that a single monitoring parameter has a low information content and is difficult to fully reflect the abnormal state of the system, the method of integrating characteristic parameters from different sources and different scales into operation state indicators is studied according to the typical weight. In order to reduce the repetitive fault data mining work and avoid too much reliance on relevant prior knowledge, this paper uses the health data of wind turbines to establish a normal model. In this way, the high-quality health data samples screened from the original SCADA data set are the basis for subsequent studies.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
