Faculty of Business Administration

Data Driven Power Prediction and Fault Diagnosis of Wind Turbines

Prof. Yanting LI

Shanghai Jiao Tong University

Abstract

Wind power is one of the main renewable energy. Wind power prediction and predictive fault diagnosis are crucial to the wind farm owners. Precise power prediction will greatly facilitate the power grid operation and reduce the operation cost. Meanwhile, effective condition monitoring and predictive fault diagnosis of wind turbines are crucial for avoiding serious damages to wind turbines. Based on the NWP data, wind farm historical data, a wind power forecasting model was proposed by combing discrete wavelet decomposition, k-means clustering and 1DCNN. Discrete wavelet decomposition is used to extract the best representation of low frequency information and the corresponding coefficients are used for k-means clustering. The clustered information was then used to build the 1DCNN model to make predictions based on the similarity between the clustered data and the new input data. The new method was compared with several other popularly used models such as LSTM, DBN and BPNN, the results show the proposed model outperforms other methods. Based on the operational data collected from the supervisory control and data acquisition (SCADA) systems, we investigated fault diagnosis of wind turbines by using Gaussian process classifiers (GPC). Both real-time and predictive fault diagnosis were considered. As an alternative to the support vector machine (SVM) technique, the GPC possesses the capability of providing probabilistic information about the fault types, which is valuable for making maintenance plan in real practice. The comparison results show that the GPC method is able to provide more accurate fault diagnosis results than the SVM technique on average.

Date: Aug 2, 2019 (Friday)

Time: 10:00 – 11:30

Venue: E22-2007

Biography

Prof. Yanting LI received her Bachelor and Master degrees from Nankai University and her PHD in Department of Industrial Engineering and Engineering Management from the Hong Kong. Respectively. She is currently an associate professor and doctoral supervisor in the Department of Industrial Engineering and Logistics Engineering of Shanghai Jiao Tong University. Her scientific research focuses on the modeling, prediction and process control of quality data of complex products in manufacturing industry. She was supported by three projects of the National Natural Science Foundation of China. More than 20 papers have been published in journals including IIE Transactions and Technometrics. In 2018, she was awarded IISE Best Paper Application Award by American Association of Industrial Engineers in 2018.