Broken bar detection on squirrel cage induction motors with MCSA and EMD

Induction motors are an ubiquitous machine. In industrial settings, online monitoring of motors' health status in order to schedule maintenance operations with the goal of damage prevention has become an essential necessity. Broken rotor bar is one of the most common failures in the rotor of a squirrel cage motor. Motor current signature analysis (MCSA) has become a popular method for its detection due to its high reliability. Recent works perform MCSA with a combination of different signal processing techniques to identify the presence of broken bars. In this work, MCSA is done with Empirical Mode Decomposition (EMD) from which a set of Intrinsic Mode Functions (IMF) is obtained. The extracted features of the arithmetical sum of the obtained IMFs form the basis of the proposed classification criteria. Unlike other works, the only employed signal processing technique in our methodology is EMD. Experimental results using our method show high accuracy in the detection of one broken rotor bar.