Gear Fault Diagnosis Based on Angular Measurements and Support Vector Machines in Normal and Nonstationary Conditions

Abstract

AbstractContrary to time-sampled acceleration signals (TA), angular measurements like instantaneous angular speed (IAS), transmission error (TE), and angular sampled acceleration (AA) represent all potential sources of relevant information in fault detection and diagnosis systems, but also to construct feature vector (FV) to make the methods of classification robust and effective even for different running speed or load conditions. In this work, we propose to use angular measurements and support vector machines (SVM) to detect and diagnose gear faults in normal and nonstationary conditions. For this purpose, features are extracted from angular and angle frequency domains of AA, TE, and IAS. Then, the classification is performed by SVM in order to improve the detection and identification of gear defects.KeywordsFault diagnosisGearboxAngular measurementsNonstationary conditionsMulticlass support vector machines