An Improved Feature Selection Method Based on Random Forest Algorithm for Wind Turbine Condition Monitoring

• Published in: Sensors (Basel, Switzerland) Vol. 21; no. 16; p. 5654
• Main Authors: Li, Guo, Wang, Chensheng, Zhang, Di, Yang, Guang
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 22.08.2021; MDPI
• Subjects: Accuracy; Algorithms; blade breakages; condition monitoring; Decision trees; Deep learning; Fault diagnosis; Feature selection; FS_RF algorithm; gated recurrent unit; Machine learning; Methods; Neural networks; Principal components analysis; Supervisory control and data acquisition; Turbines; Wavelet transforms; wind turbines
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s21165654

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.