A Motor Vibration Analysis Platform Using Typhoon-HIL Simulator

Motor vibration monitoring and analyses play a critical role in predictive maintenance, enabling the efficient management of motor-drive systems to prevent unplanned downtime and operational disruptions. This paper presents a real-time hardware-in-the-loop platform for easy deployment and enhanced fault diagnosis. The proposed system integrates advanced signal processing techniques, including Fast Fourier Transform, spectrogram analysis, and empirical mode decomposition, alongside machine learning algorithms. The developed motor condition monitoring model is evaluated under various fault scenarios, including misalignment, unbalance, and bearing defects. Experimental results demonstrate that models employing certain machine learning algorithms achieved 99.8% accuracy in predicting and classifying motor fault conditions. These findings confirm the effectiveness of the proposed system, offering a low-cost, reliable solution to support real-time motor condition monitoring and predictive maintenance.