An adaptive, on-line, statistical method for detection of broken bars in motors using stator current and torque estimation

In this paper, we propose an adaptive statistical time-frequency method to detect broken bars using digital torque estimation. The key idea in the proposed method is to transform motor current into a time-frequency spectrum to capture the time variation of the frequency components and to analyze the spectrum statistically to distinguish fault conditions from the normal operating conditions of the motor. Since each motor has a distinct geometry, we adapt a supervised approach in which the algorithm is trained to recognize the normal operating conditions of the motor prior to actual fault detection. To estimate the broken bar frequencies, we utilize the digital torque estimator.