Electric motors account for 95% of all prime movers in industrialised nations, and among these, three-phase induction motors consume typically 40 to 50% of all the generated electric energy. Induction motors are inherently reliable and require minimum maintenance. However like other motors, they eventually deteriorate and fail. This is mainly due to a combination of environmental, duty and installation related factors.
The principal aim of this project, which is funded by The Australian Research Council and National Instruments is to use hardware and custom-built signal processing and classification software tools to provide the necessary technology for the effective diagnosis and prediction of incipient failures in induction motors. This is being achieved by
Developing a comprehensive database of non-invasive sensor measurements of motors with known faults.
Analysing this database to obtain a detailed understanding of the effect of the faults on each sensor output.
Developing fault detection techniques to distinguish faults under practical operating conditions of motors, including light load.
Implementation of a continuous monitoring system with remote access capability.