Research On Gearbox Fault Diagnosis Based On EMD Approximate Entropy And LS-SVM

The gearbox is important transmission parts in the mechanical equipment. Research ongearbox fault diagnosis has very real sense. In this paper, EMD (Empirical ModeDecomposition) approximate entropy and LSSVM (Least Square Support Vector Machine)are combined to achieve the gearbox fault diagnosis. EMD method has good localization forsignal processing, moreover has very good decomposition effect for non-linear andnon-stationary signal. Approximate entropy contains more information in thecharacterization of the signal dynamics, and has inherent advantages to extract the signalfault feature. The LSSVM make modifications and variations for the drawbacks of too longrunning time and excessive calculation of the SVM (Support Vector Machine) as aclassification algorithm. Experiments show that LSSVM can achieve accurate and fast faultidentification in the gearbox fault diagnosis.This paper firstly expounds significance, purpose and domestic and foreign researchsituation of gearbox fault diagnosis, simultaneously provides an overview of the currentfault diagnosis technology. Secondly, the gearbox vibration mechanism and fault types areintroduced. Then the endpoint effect drawbacks while EMD method is decomposing signalare focused on, in order to improve the EMD method, mirror extension, as well ascombination of approaches of a windowing function in the signal sequence are proposed.The experiments show that the improved EMD method achieves very good results in thesignal decomposition. Then gearbox fault feature extraction is completed through theapplication of EMD and approximate entropy method of combining, and LSSVM highlightsthe advantage of fault identification by comparing SVM and LSSVM from theory andspecific experiments. Finally, the improved EMD method combined with the approximate entropy completes fault feature extraction. Then using LSSVM to identify the fault featureextraction, compared to the effect of SVM fault identification, the article shows that EMDapproximate entropy and LSSVM can improve the accuracy and efficiency of the gearboxfault diagnosis.