Aiming at the problem that wind turbine blade icing seriously affects the generating efficiency, safety and economy of wind turbines, a Stacked AutoEncoder (SAE) network based prediction model was proposed based on SCADA (Supervisory Control And Data Acquisition) data. The unsupervised method of encoding-decoding was utilized to pre-train the unlabeled dataset, and then the back propagation algorithm was utilized to train and fine tune the labeled dataset to achieve adaptive fault feature extraction and fault state classification. The complexy of the traditional prediction models was simplified effectively, and the influence of artificial feature extraction was avoided on model performance. The historical data of wind turbine No.15 collected by SCADA system was used for training and testing. The accuracy of the test results was 97.28%. Compared with the models based on Support Vector Machine (SVM) and Principal Component Analysis-Support Vector Machine (PCA-SVM), which accuracies are 91% and 93% respectively, the result indicates that the proposed model is more accurate than the other two.

Concerning that the existing visibility estimation methods based on region growing method has shortcomings of low precision and high computational complexity, a new algorithm was proposed to measure the visibility based on Inflection Point Line (IPL). Firstly, the three characteristics including anisotropy, continuity and level of inflection point line were analyzed. Secondly, a new 2-D filter to detect the IPL based on the three characteristics was proposed to improve the accuracy and speed of the inflection point detection. Finally, the visibility of fog weather could be calculated through combing the visibility model and detection results of the proposed filter. Compared with the visibility estimation algorithm based on region growing, the proposed algorithm decreased the time cost by 80% and detection error by 12.2%, respectively. The experimental results demonstrate that the proposed algorithm can effectively improve the detection accuracy, meanwhile reducing the computational complexity of positioning inflection points.