Fault diagnosis of induction motor using CWT and rough-set theory

The paper proposes a Rough-Set CWT based algorithm for multi-class fault diagnosis of induction motor. Use of powerful signal processing technique like CWT drastically reduces the hardware (sensor) requirement of the diagnostic system. Only axial vibration signal is enough to classify seven different types of motor faults. Moreover, successful application of Rough Set theory has enabled to select most relevant CWT scales and corresponding coefficients. Thus, the inherent deficiencies and limitations of CWT are eliminated. Consequently, the computational efficiency has also improved to a great extend. With reduction of attributes by 65% the classification accuracy of the classifiers is very consistent even in presence of high level of noise and with a low frequency sampling frequency of 5120 Hz.