Fault Diagnosis Of Hydroelectric Generating Set Based On Variational Mode Decomposition And Multi-dimensional Permutation Entropy

Hydroelectric generating set is the key equipment for safe and stable operation of power system.With the development of water conservancy in China,the single machine capacity of the hydropower unit is becoming more and more large,the structure of the unit is more and more complex,and the problem of reliability and stability of the unit is becoming more and more prominent.It is of great significance for the safe and stable operation of the power grid system to accurately detect the fault characteristic information and realize the fault diagnosis of the generating units.In this paper,a hydraulic turbine generator set is taken as an example,the feature extraction method based on VMD-MPE is used to extract the fault characteristics of the vibration signal of the unit.On this basis,a fault diagnosis model based on fuzzy C mean clustering is established,and the simulation verification is carried out.The main contents of this paper are as follows:First,the vibration mechanism of the hydropower unit is analyzed,the frequency characteristics and the state characteristics of the different vibration causes are summarized.The vibration fault identification method is introduced from three aspects of the vibration test,the vibration frequency and the vibration part,and the state monitoring and fault diagnosis of the turbine generator set is set up.Break the system.Secondly,based on the variational modal decomposition(Variational mode decomposition,VMD)and multiscale permutation entropy(Multiscale permutation entropy,MPE),a feature extraction method based on VMD-MPE(Multiscale permutation entropy,MPE)is proposed,aiming at the non stationary and nonlinear characteristics of the vibration signals of the hydropower units.The feature fault information and the Principal component analysis(PCA)are used to reduce the complexity of fault feature vectors.Finally,using the vibration signals collected by the on-line monitoring system of the hydroelectric unit to form the fault samples,the time frequency characteristics of the vibration signals are analyzed,and a fault diagnosis model based on the fuzzy C mean clustering(Fuzzy C mean clustering,FCM)is constructed.The simulation results show that the average diagnostic accuracy of the vibration fault diagnosis method of VMD-MPE and FCM is 96.9%.