Turkish Journal of Electrical Engineering and Computer Sciences




The information of the fault frequency characteristics is of great importance for all associated fault diag nostics. This requires a high-resolution spectrum analysis to achieve efficient monitoring of machinery faults, especially while diagnosing rotor bar breakage under light load conditions, because the fault frequencies almost overlap with the fundamental. In this context, rather than looking for frequencies associated with rotor faults, several frequency bands are observed separately in terms of the entropy contained within these bands. First, the motor current signal has been divided into several frequency bands using the continuous wavelet transform (CWT), and the spectral entropy is calculated from each band as the features to describe the rotor condition. Principal component analysis (PCA) has been used as a feature reduction tool, and the features projected onto the first two principal components have been fed into the SVM for inference. SVM is a supervised learning method used for classification and regression analysis. To improve classification performance, a radial basis function (RBF) kernel has been employed, and to find the optimal value of the kernel parameters, a metaheuristic approach, namely teaching learning-based optimization (TLBO), is utilized. The ANSYS 2D workbench is used to simulate the finite element model (FEM) of an induction motor with broken rotor bars, and the efficacy of the proposed method is then tested using simulated data. To investigate the robustness of the proposed approach, white Gaussian noise has also been added to the simulated data, and the performance of the SVM is tested with these spectral features.


Broken rotor bar fault, continuous wavelet transform, spectral entropy features, teaching learning-based optimization, support vector machine

First Page


Last Page