Intelligent wind turbine blade icing detection using supervisory control and data acquisition data and ensemble deep learning

Abstract

Ice accretion on wind turbine blades is one of the major faults affecting the operational safety and power generation efficiency of wind turbines. Current icing detection methods are based on either meteorological observing system or extra condition monitoring system. Compared with current methods, icing detection using the intrinsic supervisory control and data acquisition (SCADA) data of wind turbines has plenty of potential advantages, such as low cost, high stability, and early icing detection ability. However, there have not been deep investigations in this field at present. In this paper, a novel intelligent wind turbine blade icing detection method based on the wind turbine SCADA data is proposed. This method consists of three processes: SCADA data preprocessing, automatic feature extraction, and ensemble icing detection model construction. Specifically, deep autoencoders network is employed to learn multilevel fault features from the complex SCADA data adaptively. And the ensemble technique is utilized to make full use of all the extracted features from different hidden layers of the deep autoencoders network to build the ensemble icing detection model. The effectiveness of the proposed method is validated using the data collected from actual wind farms. The experimental results reveal that the proposed method is able to not only adaptively extract valuable fault features from the complex SCADA data, but also obtains higher detection accuracy and generalization capability compared with conventional machine learning models and individual deep learning model.

Wind Fleet Generator Fault Detection via SCADA Alarms and Autoencoders

“…Successively, they also utilized denoising autoencoders, enriched with temporal information to assess turbine conditions in a laboratory and online scenario [17]. Finally, autoencoders have been successfully used for ice-detection on turbines' blades by Liu et al [18].…”

An Ensemble Learning Solution for Predictive Maintenance of Wind Turbines Main Bearing

“…A meta-learner trained on a subset of base predictors has been used to improve wind power production in [ 38 , 39 ]. Liu et al proposed a solution to detect wind turbine blades icing combining features extracted by Deep-Autoencoders into an ensemble model where decision is taken by majority vote [ 40 ]. Ensembles can be used to merge information from different data sources, as Turnbull et al demonstrated using a OCSVM to combine NBMs of a temperature SCADA and vibration data for gearbox and generator bearings of wind turbines [ 41 ].…”

Temporal Attention Convolutional Neural Network for Estimation of Icing Probability on Wind Turbine Blades

“…The limitation of shallow machine learning methods is that the process for obtaining such features is usually time-consuming and can be very expensive. Deep learning-based methods attempt to model high-level representations of sensor data and identify icing conditions via a hierarchical structure [10], [16], [21], which is more competitive in terms of performance than shallow machine learning methods are.…”

“…However, to the best of our knowledge, their use in detecting icing on wind turbine blades has not yet been extensively studied [10], [12], [21]. There are even fewer studies of deep learning-based methods for icing detection [10].…”