Research On Trend Prediction Method Of Running State For Wind Turbine Transmission System

Whether the large rotating electromechanical equipment running in safe and stable state has an important impact on the economy and society,so,researched on trend prediction method of running stability deterioration is significant.Wind turbines are typical large rotating machinery,and running state deterioration of its transmission system is a time course with the development of faults.If the state evolution form fault appearance to fault manifestation macroscopically can be revealed by trend prediction of running state deterioration,it will provide scientific means to implement predictive maintenance,avoid occurrence of fatal accidents.This research mainly makes an emphasis on trend prediction method of running stability deterioration for wind turbine transmission system.The main research contents:(1)The novel weak information pretreatment algorithm based on ?-SVD and LMD was proposed.?-SVD algorithm was used to determine the denoising parameters to solve the problem which traditional SVD denoising algorithm is lack of unified principle of parameter choice.Then LMD method for noise reduction of residual information decomposition,the decomposition of the proceeds of the PF component again separately based on ?-SVD denoising,finally complete extraction signal of useful information.Simulation data and experimental data were used to validate the proposed algorithm,and the results showed that this algorithm not only highlighted state feature,but also obtained a smaller Root mean square error and higher Signal to Noise Ratio.In the early stages of the running state of degradation in weak information preprocessing has received the good effect.(2)An intrinsic mode function selection method using energy conservation and sensitive factor for feature extraction was proposed.Experiment data of varying degrees of deterioration under various types of deterioration were carried out to validate the proposed method,and the results showed that feature extracting method can separate the deterioration characteristic from non-degradation characteristics.It provided ways to solve the uncertainty problems of wind turbine transmission system in the fault detection(3)The multi-sensor distributed fault detection method based on uncertainty reasoning was proposed.The algorithm by using Subjective Bayesian reasoning,acquired the local detection device of decision rules,and selected the local decision rules suitable to the fusion center,finally produced a global decision.Experiments showed that in the fault diagnosis system contains a lot of information uncertainty,distributed detection fusion algorithm based on subjective Bayesian inference had the advantages of high recognition rate of fault information,diagnosis speed.Diagnosis error rate of multi-sensor distributed detection fusion algorithm was significantly lower than that of single sensor and the serial structure.(4)The trend prediction method of transmission system state deterioration based on hilbert degradation characteristics entropy and HMM was proposed.The concept of the hilbert degradation characteristics entropy was proposed,and the feature vector of state deterioration was obtained by feature extraction method of hilbert degradation characteristics entropy,then a variety of diagnostic models of transmission system were established.Based on state deterioration diagnosis results,state deterioration squence was obtained according to the hilbert degradation characteristics entropy,and the trend prediction method was applied to predict deterioration trend.Real state vibration data were collected on the industrial scene,and the data analysis results showed that this trend prediction method is feasible and effective.(5)The on-line detection and diagnosis system for Wind turbines group was developed and the unitmodularembeddeddetection system of reconstructible was built.Remoteman-machine interface was designed.By the software and hardware resources,the system was formed.The system could provide the convenient conditions for verifying the diagnosis methods.Field application showed that the system can effectively warn early fault of wind turbine transmission system.