A Simple and Effective Sound-based Five-Class Classifier for Induction Motor Overload

Overloading can shorten operating life of induction motors. It is also a primary cause of some faults, such as excessive temperatures or tooth breakage. Detecting and classifying overload levels are very essential to ensure durable and stable operations of those electromechanical energy converters. In our research, sounds recorded by a single microphone is analyzed to categorize five levels of overload status. Three acoustic features and six classification models are evaluated. Acquired results show that this is a promising way to build a real-time and inexpensive monitoring system for induction motor overload.