Application of EEMD Fuzzy Entropy and Grey Relation Degree in Gear Fault Diagnosis

Abstract

Focusing on the gear measured signal can not accurately reflect the fault characteristics due to noise interference, a novel way was introduced for gearbox fault recognition in the article. By using the rank-order morphological filter, the influence of noises was eliminated from the original signal. Then the ensemble empirical mode decomposition (EEMD) method was utilized for decomposition of the de-noised data. From these decomposition results, some useful components were selected and calculated the fuzzy entropy. Then the grey relation degree method was used to recognize different gear fault type. Recognition results express the effectiveness of the proposed method.