Rough set based multi-class fault diagnosis of induction motor using Hilbert Transform

The paper proposes a Rough-set Theory based methodology for multi-class fault diagnosis of induction motors using Hilbert Transform (HT). Depending on the motor condition the vibration signals are associated with unique predominant frequency components and instantaneous amplitudes. The axial vibration signals acquired through data acquisition system are split into different mono-components using Kaiser windowed FIR band pass filter. Statistical features of the Hilbert coefficients obtained from the mono-component signals are used as attributes for fault classification. Rough-set theory is successfully applied for dimensionality reduction of the attributes (by 67%) with almost no degradation of classification accuracy. The proposed Rough-set-Hilbert model eliminates the limitation of wavelet based fault diagnosis technique. The computational efficiency of the proposed classifiers increase due to selection of most relevant features, even at a low sampling frequency of 5120 Hz.