Motor monitoring, incipient fault detection, and diagnosis are very important and difficult topics in the engineering field. The applications range from a small DC motor used in the intensive care unit to the huge motors used in nuclear power plants. With proper machine monitoring and fault detection schemes, improved safety and reliability can be achieved for different engineering system operations. The importance of incipient fault detection can be found in the cost savings which are realized by detecting potential machine failures before they occur. Non-invasive, inexpensive, and reliable fault detection techniques are often preferred by many engineers. With the emerging technology of artificial neural networks and fuzzy logic, the motor fault detection problem can be solved using an innovative approach based on easy accessible measurements, without the need for expensive equipment or accurate mathematical models that are needed for conventional fault detection techniques.

This project has been investigating, analyzing, and developing a framework/principle for the detection of incipient faults in three-phase induction motors via set theoretical formulation, and it demonstrates the feasibility of using neural network and fuzzy logic technologies(NN/FZ) to provide both an accurate and reliable motor incipient fault detection technique as well as the heuristic explanation of the fault detection process, for different operating environments including different load conditions, ambient temperatures, motor saturation effects, and line noises.