No abstract

The blades of wind turbines located at high latitudes are often covered with ice in late autumn and winter, where this affects their capacity for power generation as well as their safety. Accurately identifying the icing of the blades of wind turbines in remote areas is thus important, and a general model is needed to this end. This paper proposes a universal model based on a Deep Neural Network (DNN) that uses data from the Supervisory Control and Data Acquisition (SCADA) system. Two datasets from SCADA are first preprocessed through undersampling, that is, they are labeled, normalized, and balanced. The features of icing of the blades of a turbine identified in previous studies are then used to extract training data from the training dataset. A middle feature is proposed to show how a given feature is correlated with icing on the blade. Performance indicators for the model, including a reward function, are also designed to assess its predictive accuracy. Finally, the most suitable model is used to predict the testing data, and values of the reward function and the predictive accuracy of the model are calculated. The proposed method can be used to relate continuously transferred features with a binary status of icing of the blades of the turbine by using variables of the middle feature. The results here show that an integrated indicator system is superior to a single indicator of accuracy when evaluating the prediction model.

In the frequency modulation process of the heavy power generation gas turbine, the variation of output power will cause the fluctuation of the operating parameters. In order to detect the anomaly of the true performance deterioration accurately, a novel statistical anomaly detection model was developed. First, the mathematical description of the operating parameters under three different operating conditions—unsteady-state, steady-state and normal, steady-state and anomaly—was presented according to the characteristics of parameters and output power. Second, the new characteristic test statistic P-ratio based on the T-statistic was proposed for the anomaly detection under the steady-state condition. Then, the on-line steady-state detection algorithm based on the Gaussian mixture model was built for the unsteady-state identification. Finally, the efficacy of the model was examined on the synthetic deterioration data, which superimposes the anomaly simulation signal data on the real healthy data from a real power generation gas turbine. The testing result is shown to be satisfactory with respect to the false positive rate and the true positive rate. Future research is required to further improve the accuracy of the proposed model.

No abstract

No abstract