The Research On Feature Capture And Automatic Diagnosis Technology Of Wind Turbine Transmission System

Nowadays,the global environmental situation is increasingly grave.Wind energy as a pollution-free,renewable new energy is favored by the world.Gearbox and bearing,as important components of the wind turbine transmission system,their reliable operation directly affects the power generation performance and economic benefits of the whole wind turbine.At present,the diagnosis of the transmission system of wind turbines requires the participation of a large number of professionals.In the face of the massive monitoring data of wind turbine group,automatic fault diagnosis research has important theoretical and engineering significance.This paper develop automatic fault diagnosis research on the wind turbine transmission system,the specific contents are as follows:(1)The complexity and variability of wind turbine(WT)operating conditions bring many challenges to the diagnosis based on vibration analysis.Based on this,a multi-source date method combining vibration and synchronous SCADA(Supervisory Control and Data Acquisition)data is proposed to realize gearbox fault diagnosis under different working conditions.Firstly SCADA data is adopted to divide WT operation zones based on the theoretical operation zones analysis of variable-speed and constant-frequency Wls.Then directly using generator speed signal from SCADA which is sampled every second and vibration signal to develop order tracking.Finally,the fault diagnosis and analysis of gearbox under different operation zones are attained through the feature order automatic capture technology.The results show that the different operating zone has a different effect on the characteristics of order amplitude,the method based on multi-source data can accurately and stably extract the fault characteristics of gearbox and achieve the fault diagnosis of WT under the full operating zones(2)Bearings fault diagnosis is mainly based on its characteristic frequency,but finding a suitable frequency band for demodulation and searching for the fault characteristic frequencies consume a lot of time and manpower in practice.A data-driven method based on recursive variational mode decomposition(RVMD)and envelope order capture is proposed to realize the automatic fault diagnosis of bearing under different operating conditions.The signal is decomposed automatically by RVMD.Then the mode with maximum kurtosis of the unbiased autocorrelation of envelope is selected to get envelope order spectrum.Finally an order capture algorithm is designed to automatically search for the fault characteristic orders in theory which are used for constructing feature vectors for diagnosis.The proposed method is tested on two test-beds which both contain the same type of bearing,but operate in different conditions,and gets a good performance in bearing diagnosis.This result shows that the method has a well generalization eapability in fault diagnosis of the same type of rolling element bearing under different operating conditions.(3)Based on the above research,this paper developed the wind turbine transmission system fault diagnosis based on Lab VIE W,including parameter input module,data preprocessing module,fault diagnosis module and spectrum display module.VMD algorithm was embedded in the data preprocessing module.In the fault diagnosis module,joined the traditional spectrum analysis and time spectrum analysis.At the same time the order envelope spectrum was added.Finally,a variety of spectrum display and multi-method diagnosis are realized,which lays an important foundation for the next step of state monitoring and online automatic fault diagnosis of wind turbine transmission system.