Application of Hybrid Model between the Technique for Order of Preference by Similarity to Ideal Solution and Feature Extractions for Bearing Defect Classification

This paper describes a development that offers new opportunities for detecting faulty bearings. Prioritization is based on the technique order of preference by similarity to ideal solution (TOPSIS) most discriminative features in bearing dataset. The proposed model divided into three steps: feature extraction, selection, and classification. In variational mode decomposition (VMD) fast Fourier transform (FFT) are used extract from measured signal test motors use symmetrical uncertainty (SU) value calculation, reducing redundancy data. terms TOPSIS method instead traditional filtering method, which applied analysis decision making, important selected seven methods. Finally, validate classification ability model, k-nearest neighbors (KNN), support vector machine (SVM), artificial neural networks (ANN) as independent classifiers. effectiveness evaluated applying two datasets, namely current dataset motor vibration signals provided Case Western Reserve University (CWRU). results show comparison with other models shows feasibility this study.