The deployment of wind power plants in cold climate becomes ever more attractive due to the increased air density resulting from low temperatures, the high wind speeds, and the low population density. However, the cold climate conditions bring some additional challenges as itt can easily cause wind turbine blades to freeze. The frizzing ice on blades not only increases the energy required for the rotation of blades, resulting in a reduction in the power generation, but also increases the amplitude of the blades’ vibrations, which may cause the blade to break, affecting the power generation performance of the wind turbine and poses a threat to its safe operation.

Current published blade icing detection methods focus on studying the blade icing mechanism, building the model and then judging if it is iced or not. These models vary with different wind turbines and working conditions, so expertise knowledge is required. However, deep learning techniques may solve the abovementioned problem based on their excellent feature learning abilities but until now, there are only few studies on wind turbine blade icing detection based on the deep learning technology. Therefore, this paper proposes a novel blade icing detection model, named two-dimensional convolutional neural network with focal loss function (FL-2DCNN). The network takes the raw data collected by the Supervisory Control and Data Acquisition (SCADA) system as input, automatically learns the correlation between the different physical parameters in the dataset, and captures the abnormal information, in order to accurately output the detection results.

However, the amount of normal data collected by SCADA systems is usually much larger than the one of blade icing fault data, leading to a serious data imbalance problem. This problem makes it difficult for the network to obtain enough features related to the blade icing fault. Therefore the focal loss function is introduced to the FL-2DCNN to solve the aforementioned data imbalanced problem. The focal loss function can effectively balance the importance of normal samples and icing fault samples, so that the network can obtain more icing-related feature information from the icing fault samples, and thus the detection ability of the network can be improved. The experimental results of the proposed FL-2DCNN based on real SCADA data of wind turbines show that the proposed FL-2DCNN can effectively solve the sample imbalance problem and has significant potential in the blade icing detection task compared with other deep learning methods.

This content is only available via PDF.
You do not currently have access to this content.