Fault Diagnosis Method Of Low Speed Helical Gears Based On Adaptive Mode Decomposition

The helical gear transmission is stable and has high bearing capacity.It has been widely used in modern industrial equipment,especially wind turbines.Helical gear train failures often cause serious equipment accidents and cause heavy economic losses.The speed of low-speed rotating machinery is generally lower than 600 rpm.Broken helical gear,pitting and fatigue spalling occurred during the helical gear system,which will have a periodic pulse impact force,resulting in the modulation of the vibration signal in the spectrum of performance at the meshing frequency or natural frequency on both sides appear evenly spaced modulation side band.This article puts forward an effective solution for gear fault diagnosis under low speed conditions.The main research contents are as follows:(1)Discusse the background and research significance of the subject.Expound the research status of low-speed helical gear fault diagnosis at home and abroad.Introduce the development of adaptive mode decomposition algorithm and pattern recognition algorithm.Show the improved object and algorithm theoretical basis of the proposed method.(2)The variational mode decomposition algorithm and the cyclic autocorrelation function theory were discussed.The fault feature extraction method of low speed helical gear based on parameter optimization variational mode decomposition was proposed.The method was applied to the fault feature extraction of low-speed gear fault simulation signal and test gear signal.The results demonstrated the effectiveness of the proposed method.(3)Aiming at the shortcomings of the second chapter,which is suitable for constant working conditions,the fault feature extraction method of helical gears under variable speed is studied.A fault diagnosis method for variable speed helical gear based on order analysis is proposed.The simulation and experimental signals verify the effectiveness of the proposed method(4)In view of the complicated working conditions of the wind turbines in the wind turbine,the methods of Chapter 3 were made up to solve the shortcomings of helical gear fault diagnosis with more complex conditions.The multiclass multikernel relevance vector Machine of helical gear fault diagnosis method were proposed.It was verified by the test signal that the method can accurately identify the state of the gear under the condition of variable speed,different load and different measuring points,and had better generalization ability.(5)Introduce the low-speed helical gear test content.Build a low speed helical gear signal acquisition and analysis system based on software LabVIEW.The system can not only monitor and display the real-time running status of the low-speed helical gear,save the data and analyze it offline,but also embed the feature extraction method of the above chapter into the program,and develop the pattern recognition fault model into a convenient and convenient system.It will help the latest methods to be applied in the engineering field,and provide reference for the development of state monitoring and fault diagnosis systems for low-speed helical gears.