Abstract
Under the complicated environment of large wind turbines, the vibration signal of a wind turbine has the characteristics of coupling and nonlinearity. The traditional feature extraction method for the signal is hard to accurately extract fault information, and there is a serious problem of information redundancy in fault diagnosis. Therefore, this paper proposed a multidomain feature fault diagnosis method based on complex empirical mode decomposition (CEMD) and random forest theory (RF). Firstly, this paper proposes a novel method of complex empirical mode decomposition by using the correlation information between two-dimensional signals and utilizing the idea of ensemble empirical mode decomposition (EEMD) by adding white noise to suppress the problem mode mixing in empirical mode decomposition (EMD). Secondly, the collected vibration signals are decomposed into IMFs by CEMD. Then, calculate 11 time domain characteristic parameters and 13 frequency domain characteristic parameters of the vibration signal, and calculate the energy and energy entropy of each IMF components. Make all the characteristic parameters as the multidomain feature vectors of wind turbines. Finally, the redundant feature vectors are eliminated by the importance of each feature vector which has been calculated, and the feature vectors selected are input to the random forest classifier to achieve the fault diagnosis of large wind turbines. Simulation and experimental results show that this method can effectively extract the fault feature of the signal and achieve the fault diagnosis of wind turbines, which has a higher accuracy of fault diagnosis than the traditional classification methods.
Highlights
As a kind of abundant, renewable, and efficient clean energy, wind energy has developed rapidly in recent years
In order to more comprehensively extract the fault feature information from the wind turbine vibration signal and solve the problem that the traditional fault diagnosis method has low recognition accuracy, this paper proposes a multidomain feature fault diagnosis method based on complex data empirical mode decomposition (CEMD) and random forest theory
In order to verify the advantage of complex data empirical mode decomposition (CEMD) this paper proposed in dealing with mode mixing in EMD, simulations were performed using simulation signals, considering that the mode mixing problem in EMD is usually caused by the presence of intermittent components or discontinuous components in the signal
Summary
As a kind of abundant, renewable, and efficient clean energy, wind energy has developed rapidly in recent years. A probabilistic neural network (PNN) model is established to achieve the fault classification These methods all use the signal processing method to extract the time-frequency characteristic information of the vibration signal, and the feature information extracted is often not comprehensive enough. There are still some shortcomings in the current research of multidomain feature fault diagnosis It includes that the effect of traditional time-frequency signal processing methods is often not ideal, and with the increase of feature vectors, it is more difficult for the wind turbine to diagnose and there will be redundant feature information in multidomain feature vectors. Considering the advantages of the two algorithms, this paper proposes a multidomain feature fault diagnosis method based on complex empirical mode decomposition and random forest theory and applies it to the fault diagnosis of wind turbines.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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
