Abstract
Among the various maintenance technologies of wind turbines, online fault prediction technology is a kind of more cost-effective and reliable method. It may also be the most promising method for wind turbines with potential mechanical faults. SCADA data-based online condition monitoring technology has become a hot spot in current researches. Therefore, a novel fault prediction method based on the Pair-Copula model is proposed in this study. First, the conditional mutual information method is introduced to screen out useful variables from a number of variables. Then aiming at the limitation that the conventional Copula model can only deal with two-dimensional variables, the Pair-Copula model is introduced. In addition, the complexity of the prediction model and the dimension of the input variables are greatly reduced by the Pair-Copula model. So, the BP neural network is selected to complete the prediction model. A combined model based on BP neural network and Pair-Copula model is proposed. In order to solve the problem that the conventional Pair-Copula model cannot process real-time data which must be required in fault prediction, a kind of improved Pair-Copula model combined with the kernel density estimation is used to calculate the real-time data. Finally, the proposed method is validated with real data from a 1.5 MW wind turbine, and the effectiveness is confirmed.
Highlights
According to the structure of the transmission system, wind turbines (WTs) are mainly divided into two categories: doubly-fed WTs with gearbox, and direct-drive WTs without gearbox [1]
The residual data sequence is denoted as E, and the i-th data sample in the sequence is denoted as ei, where i = 1, 2, · · ·, n. n is the number of data samples in the sequence
Based on the Pair-Copula model, a novel WT gearbox fault prediction method is proposed in this paper
Summary
According to the structure of the transmission system, wind turbines (WTs) are mainly divided into two categories: doubly-fed WTs with gearbox, and direct-drive WTs without gearbox [1]. The maintenance cost of the gearbox is relatively high, the repair time and cost are at the forefront of all major equipment. An effective way to reduce the cost of breakdown maintenance is to use condition monitoring technology for early detection of faults. Carrying out research on the condition monitoring and fault early warning of WT gearbox, and rationally adjusting the operation and arranging maintenance according to the healthy. The gearbox condition monitoring methods mainly include oil analysis, vibration analysis and SCADA data analysis. The health state of the gearbox is monitored by indicators such as metal abrasive particles, which can directly reflect its mechanical deterioration and has a high accuracy [8]–[10]. The cost of metal abrasive particle sensors is high and the real-time performance of oil analysis method is poor. It is necessary to further investigate low-cost solutions [11]–[13]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
