Home > Research > Publications & Outputs > Condition monitoring of wind turbine using nove...

Links

Text available via DOI:

View graph of relations

Condition monitoring of wind turbine using novel deep learning method and dynamic kernel principal components Mahalanobis distance

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published
Article number106757
<mark>Journal publication date</mark>31/10/2023
<mark>Journal</mark>Engineering Applications of Artificial Intelligence
Volume125
Publication StatusPublished
Early online date17/07/23
<mark>Original language</mark>English

Abstract

Condition monitoring (CM) of wind turbine (WT) has been increasingly adopted for its fault diagnosis and maintenance decision-making. However, the data collected in CM is typically noisy, multidimensional, and highly nonlinear, which causes significant challenges in achieving the effective CM of WT. This paper proposes a novel CM method using a deep learning model with temporal pattern attention (TPA) and a dynamic kernel principal components Mahalanobis distance (DKPMD). The method can evaluate the WT performance accurately for detecting faults. First, outliers are recognized and removed using isolation forest improved by sparse autoencoder and fuzzy c-means clustering (FSIF) from raw wind turbine data of health state for enhancing the quality and reliability of data in modeling. Then, a gated recurrent unit (GRU) is developed for data reconstruction of the objective variables using LassoNet and TPA, which can capture the short- and long-term temporal relationships under different time steps based on selected variables. Meanwhile, kernel RMSE (KRMSE) is applied as a loss function, which avoids the negative effects of large reconstructed errors in parameter optimization. A condition index (CI) is constructed using DKPMD based on the reconstructed errors to consider the dynamic correlation between the variables. Finally, a delay perception-based IF(DPIF) is utilized to determine the threshold. Experiments with data from real WT demonstrate the effectiveness of the developed approach in detecting early abnormal conditions, which outperforms other state-of-the-art methods.