Load Unbalance Detection Improvement in Three-Phase Induction Machine Based on Current Space Vector Analysis

Although the asynchronous machine is renowned for its qualities of robustness, reliability, low cost of construction and efficiency, it happens nevertheless that faulty operations may appear during its lifetime. Numerous papers have studied the mechanical defects detection in electric motors using stator currents. The present paper is focused on the detection of load unbalance in three-phase induction motor relying on stator currents analysis. The proposed approach is based on the analysis of current space vector transformation, which takes in consideration all the information provided by the induction machine, this information is analysed by the means of Power Spectral Density and the Wavelet Packet Decomposition techniques. For this purpose, an experimental setup is designed to conduct experimental tests and show the advantages of space vector transformation compared to single-phase analysis. The obtained results are discussed and analysed.