Abstract
Feature selection and dimensionality reduction are important for the performance of wind turbine condition monitoring models using supervisory control and data acquisition (SCADA) data. In this paper, an improved random forest algorithm, namely Feature Simplification Random Forest (FS_RF), is proposed, which is capable of identifying features closely correlated with wind turbine working conditions. The Euclidian distances are employed to distinguish the weight of the same feature among different samples, and its importance is measured by means of the random forest algorithm. The selected features are finally verified by a two-layer gated recurrent unit (GRU) neural network facilitating condition monitoring. The experimental results demonstrate the capacity and effectiveness of the proposed method for wind turbine condition monitoring.
Highlights
Compared with traditional energy sources, wind energy is clean and renewable; wind power has spread worldwide [1,2,3]
This motivated the research into datadriven wind turbine condition monitoring methods that are capable of estimating working conditions and detecting faults
In [10], the authors presented a virtual model to predict two parameters using supervisory control and data acquisition (SCADA) data in wind turbines, and the results indicated that the accuracy of the model depended to a large extent on the selected input parameters
Summary
Compared with traditional energy sources, wind energy is clean and renewable; wind power has spread worldwide [1,2,3]. To prevent high financial losses, condition monitoring and fault prognosis for wind turbines attract a great deal of attention. Condition monitoring methods for wind turbines were mainly carried out with signals collected by sensors. This motivated the research into datadriven wind turbine condition monitoring methods that are capable of estimating working conditions and detecting faults. Sun et al [7] proposed a method to detect weak features in early faults of rolling bearings in wind turbines. They combined the multiwavelet denoising technique with the threshold of the data-driven block and separated features from noises. Zhang et al [8] successfully localized the fault planet gear in wind turbine gearboxes using the acoustic emission technique
Sign-in/Register to view highlights & summary 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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
