Feature selection and fault classification for an induction motor bearing data by using random forest classifier

• DOI: 10.1504/ijqet.2023.134886
• Publication Date: 2023-11-16T12:30:19Z
• Authors: Raj Kumar Patel; Sudhir Agrawal; Anshul Sharma
• Keywords: Feature vector; Relevance vector machine

In induction machine, faults can be avoided if it is detected early. Bearing failure the major cause and accounts for up to 41% of that occur in rotating machines. This fault distinguished by vibration signals whose amplitude however low linked with frequencies. A study accomplished magnify diagnostic pertinence measurement using recognition indicative features damage classification, location, severity. To accomplish task, a composite feature pool developed calculating from different domains, i.e., time, frequency, time-frequency. totality, 46 are calculated out most desirable selected applying principal component analysis (PCA) minimum redundancy maximum relevance (mRMR) technique. The characteristic given as input radial basis function neural network (RBFNN), support vector machine (SVM), random forest (RF) classifier, finally, realisation these classifiers correlated. proposed selection method along classifier gives better results.