Induction Motor Condition Monitoring for Sustainable Manufacturing

Abstract

Abstract As the power source for virtually all manufacturing systems, induction motor represents an integral part in modern manufacturing. Reliable functioning of induction motors is critical to minimizing machine downtime and maintaining high performance, which contributes to scrap-free production and overall sustainability in manufacturing. Due to the complex physical mechanisms, reliable and low-cost motor condition monitoring has remained a challenge, especially for small and medium-sized manufacturers (SMMs). This paper describes a data-driven method for real-time induction motor condition monitoring and fault diagnosis, based on Dictionary Learning and Nystrom method. The integrated method is highlighted by improved data discriminability and effectiveness in handling data high dimensionality. Experimental evaluation using vibration signal as fault indicator confirmed high accuracy of the proposed method in induction motor multi-fault classification and an 80% reduction in execution time.