KEYWORDS: Data modeling, Principal component analysis, Wind turbine technology, Wind energy, Neural networks, Feature extraction, Data analysis, Convolution, Analytical research
The diverse and dynamic working environment of a wind turbine (WT) frequently makes it difficult to monitor and identify abnormalities. In this study, a novel approach is proposed for abnormal recognition of WT generator, in which the convolutional neural network (CNN) cascades to the long and short term memory network (LSTM) based on nuclear principal component analysis (KPCA). Firstly, the quartile method is used to preprocess SCADA data to delete abnormal data and improve data effectiveness. Then, by selecting the input variables based on Pearson correlation coefficient, KPCA can eliminate the nonlinearity of process variables and enhance the generalization ability of the algorithm. In this study, CNN and LSTM based on KPCA state recognition model is established by extracting principal com-ponents from KPCA. The model can warn the abnormal state of the generator through the prediction residual. The prediction residual exceeds the threshold for many times, indicating that the operation state is abnormal. Finally, to demonstrate the effectiveness of this approach, the state of WTs generator is forecasted using examples.
The working state of the pitch motor has a great influence on the operation of the wind turbine. In this paper, the 2MW wind turbine is taken as the research object. Based on the historical operation data of the wind turbine, the influencing factors of the pitch motor temperature deviating from the normal range are analyzed. First, the range of the pitch motor temperature is counted by the quartile method. Then, using Relief-F for feature selection, the characteristic parameters that have a great influence on the pitch motor temperature are screened out. According to the selected characteristic parameters, combined with the historical operation data of the wind turbine, the influencing factors of the abnormal temperature of the pitch motor are analyzed. Through analysis, it is found that the blade pitch angle, the pitch motor current and the battery box temperature show obvious trend changes in the period before and after the abnormality of the pitch motor temperature. They are related factors that affect the abnormal of the pitch motor temperature. The main meaning of this paper is to screen the characteristic parameters that affect the pitch motor temperature through the Relief-F algorithm. The selected characteristic parameters are representative and can be used as the input parameters of the prediction model of the pitch motor temperature. It can better deal with the difficult problem of parameter selection for early warning model modeling.
Due to frequent changes in wind speed and wind direction, the yaw system needs to be frequently aligned with the wind direction, which may cause a series of engineering problems such as downtime caused by frequent actions. In this paper, SCADA data is used to filter out abnormal data such as shutdown and power limit through empirical analysis. Then the DBSCAN algorithm is used to filter the data to obtain a better SCADA data set. The data set is modeled by curved surface polynomial least squares. Through the analysis of the model, it is concluded that the yaw coefficient and wind speed have different influence characteristics on power. The yaw coefficient above rated wind speed has less influence on output power, and the yaw of different wind speed has different influence on power.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.