The feasibility of monitoring the health of wind turbine (WT) gearboxes based on the lubricant pressure data in the supervisory control and data acquisition system is investigated in this paper. A deep neural network (DNN)-based framework is developed to monitor conditions of WT gearboxes and identify their impending failures. Six data-mining algorithms, the k- nearest neighbors, least absolute shrinkage and selection operator, ridge regression (Ridge), support vector machines, shallow neural network, as well as DNN, are applied to model the lubricant pressure. A comparative analysis of developed data-driven models is conducted and the DNN model is the most accurate. To prevent the overfitting of the DNN model, a dropout algorithm is applied into the DNN training process. Computational results show that the prediction error will shift before the occurrences of gearbox failures. An exponentially weighted moving average control chart is deployed to derive criteria for detecting the shifts. The effectiveness of the proposed monitoring approach is demonstrated by examining real cases from wind farms in China and benchmarked against the gearbox monitoring based on the oil temperature data.

In this paper, a data-driven framework is proposed to automatically detect wind turbine blade surface cracks based on images taken by unmanned aerial vehicles (UAVs). Haar-like features are applied to depict crack regions and train a cascading classifier for detecting cracks. Two sets of Haar-like features, the original and extended Haar-like features, are utilized. Based on selected Haar-like features, an extended cascading classifier is developed to perform the crack detection through stage classifiers selected from a set of base models, the LogitBoost, Decision Tree, and Support Vector Machine. In the detection, a scalable scanning window is applied to locate crack regions based on developed cascading classifiers using the extended feature set. The effectiveness of the proposed data-driven crack detection framework is validated by both UAV-taken images collected from a commercial wind farm and artificially generated. The extended cascading classifier is compared with a cascading classifier developed by the LogitBoost only to show its advantages in the image-based crack detection. A computational study is performed to further demonstrate the success of the proposed framework in identifying the number of cracks and locating them in original images.

More recently, wind speed forecasting as an effective computing technique currently plays an important role in advancing industry informatics, while dealing with those issues of control and operation for renewable power systems. However, it is facing some increasing difficulties to handle the large-scale dataset generated in these forecasting applications, with the purpose of ensuring stable computing performance. In response to such limitation, this article proposes a more practical approach through the combination of extreme learning machine (ELM) method and deep learning model. ELM as a novel computing paradigm enables the neural network- (NN-) based learning to be achieved with fast training speed and good generalization performance. The stacked ELM (SELM) is an advanced ELM algorithm under deep learning framework, which works efficiently on memory consumption decrease. In this article, an enhanced SELM is accordingly developed via replacing the Euclidean norm of the mean square error (MSE) criterion in ELM with the generalized correntropy criterion to further improve the forecasting performance. The advantage of the enhanced SELM with generalized correntropy to achieve better forecasting performance mainly relies on the following aspect. Generalized correntropy is a stable and robust nonlinear similarity measure while employing machine learning method to forecast wind speed, where the outliers may exist in some industrially measured values. Specifically, the experimental results of short-term and ultra-short-term forecasting on real wind speed data show that the proposed approach can achieve better computing performance compared with other traditional and more recent methods.

This paper proposes a novel model-free solution algorithm, the natural cubic-spline-guided Jaya algorithm (S-Jaya), for efficiently solving the maximum power point tracking (MPPT) problem of PV systems under partial shading conditions. A photovoltaic (PV) system which controls the power generation with its operating voltage is considered. As the same as the generic Jaya algorithm, the S-Jaya is free of algorithm-specific parameters. A natural cubic-spline-based prediction model is incorporated into the iterative search process to guide the update of candidate solutions (operating voltage settings) in the S-Jaya and such extension is capable of improving the tracking performance. Simulation studies and experiments are conducted to validate the effectiveness of the proposed S-Jaya algorithm for better addressing PV MPPT problems considering a variety of partial-shading conditions. The performance of the proposed algorithm is benchmarked against the generic Jaya and the particle swarm optimization, which has been widely considered in the model-free MPPT, to demonstrate its advantages. Results of simulation studies and experiments demonstrate that the S-Jaya algorithm converges faster and provides a higher overall tracking efficiency.

A short-term forecasting of the electricity price with data-driven algorithms is studied in this research. A stacked denoising autoencoder (SDA) model, a class of deep neural networks, and its extended version are utilized to forecast the electricity price hourly. Data collected in Nebraska, Arkansas, Louisiana, Texas, and Indiana hubs in U.S. are utilized. Two types of forecasting, the online hourly forecasting and day-ahead hourly forecasting, are examined. In online forecasting, SDA models are compared with data-driven approaches including the classical neural networks, support vector machine, multivariate adaptive regression splines, and least absolute shrinkage and selection operator. In the day-ahead forecasting, the effectiveness of SDA models is further validated through comparing with industrial results and a recently reported method. Computational results demonstrate that SDA models are capable to accurately forecast electricity prices and the extended SDA model further improves the forecasting performance.

Monitoring wind turbine blade breakages based on supervisory control and data acquisition (SCADA) data is investigated in this research. A preliminary data analysis is performed to demonstrate that existing SCADA features are unable to present irregular patterns prior to occurrences of blade breakages. A deep autoencoder (DA) model is introduced to derive an indicator of impending blade breakages, the reconstruction error (RE), from SCADA data. The DA model is a neural network of multiple hidden layers organized symmetrically. In training DA models, the restricted Boltzmann machine is applied to initialize weights and biases. The back-propagation method is subsequently employed to further optimize the network structure. Through examining SCADA data, we observe that the trend of RE will shift by the blade breakage. To effectively detect RE shifts through online monitoring, the exponentially weighted moving average control chart is deployed. The effectiveness of the proposed monitoring approach is validated by blade breakage cases collected from wind farms located in China. The computational results prove the capability of the proposed monitoring approach in identifying impending blade breakages.