Study On Condition Monitoring And Fault Diagnosis System Of Wind Power Gearbox

With the progress of society and the rapid development of science and technology,people’s demand for energy continues to grow.Wind energy has been widely used as a renewable clean energy in the world.Wind turbines generally work in harsh environments and are easy when a fault occurs,the gearbox as a key component of the wind turbine directly determines whether the entire wind turbine can operate normally.Studying the status monitoring and fault diagnosis of wind power gearbox is of great practical significance for ensuring the safe and stable operation of wind turbines.The work done and results achieved are as follows.The structure of the wind turbine is analyzed,and the common faults and fault characteristics of the wind power gearbox are mainly discussed.On this basis,the overall scheme design of the wind turbine gearbox condition monitoring and fault diagnosis system is carried out.The characteristics of the wind power gearbox condition monitoring system were analyzed,and the hardware selection and system construction were completed.Based on the Lab VIEW graphical programming language,a set of wind power gearbox condition monitoring and fault diagnosis system was developed.The system can realize the operation status monitoring of the gearboxes of multiple wind turbine units.The main functions include: parameter setting,data collection and storage,offline analysis and fault diagnosis.The monitored parameters include temperature,pressure and vibration signals.The offline analysis module can realize the fault feature analysis of vibration signal in time domain,frequency domain and short-time Fourier transform.Aiming at the problem that it is difficult to extract rolling bearing fault features in wind power gearboxes,a rolling bearing fault diagnosis method based on adaptive local iterative filtering(ALIF)multi-scale permutation entropy(MPE)and K nearest neighbor(KNN)algorithm is studied.First,the vibration signal of the rolling bearing is decomposed by ALIF,then the main analysis component is selected according to the principle of maximum kurtosis,and the entropy value of the main analysis component is calculated by MPE to realize the fault feature extraction of the rolling bearing.Finally,the entropy value is input into the KNN classifier as the feature vector to realize the fault feature analysis of the rolling bearing.The research results of the thesis have certain reference significance for further research on the actual wind turbine’s condition monitoring and fault diagnosis system.