Study On Fault Feature Extraction Of Gearbox Based On Emd

As a necessary part of connecting and force transmission in mechanical equipment, gearbox system is played a comprehensive role, with the development of modern industry. And gearbox is also the mechanical part which is damaged easiest. When the gear system works, periodic impulse impact force will produce owing to the faults of gear abruption or corrosive pitting, etc. So phenomena of modulation produced at this moment and spectrum of the vibration signal has symmetrical modulation side-bands besides the meshing frequency or natural frequency. Extracted modulation information and its strength and modulation frequency order can be analyzed which can be used to judge the fault parts. It is a compressively used in mechanical fault diagnosis.In order to effectively extract the feature vector of fault in the vibration signals of gear and achieve the purposes of identifying and eliminating the faults, according to the mechanism and characteristics of gearbox vibration, the following researches is based on EMD by using DASP and MATLAB. In this paper, the fault gears vibration signal of normal working state, abrasion working state and rupture working state are the studied objects.1) The development of technology of fault diagnosis for gearbox, the mechanism and characteristics of gear and bear vibration are discussed.2) Some existing gear fault diagnosis methods, which are mainly based on the basic principles and methods of vibration analysis, are analyzed and discussed in detail. The analysis methods of vibration signals are discussed thoroughly, including time domain analysis, frequency domain analysis and EMD. The way of extracting the feature vector of fault in the time domain and frequency domain is also discussed.3) The gearbox vibration experiment terrace is designed. The vibration signals of gear with different state are extracted. The feature vector of fault in the time domain and frequency domain is also extracted.4) The fundamental theory of EMD analysis and its application are introduced on the application of fault diagnosis for gearbox. Then by means of the EMD, the fault feature vectors of fault are successfully extracted and this effective method is employed to identify the fault pattern.5) Through PCA and cluster analysis, independent principal components are then extracted from the abnormal data.6) Through multivariate statistics analysis, the analysis method of AR model based on EMD is proposed and applied to gear fault diagnosis. The research results show that the work state and fault patterns of gear can be identified by the proposed method efficiently.Experimental results show these proposed methods, which can protrude the fault character of the gearbox, are practical in gearbox local fault diagnosis and of important meaning.