Intelligent Determining of Amount of Inter-Turn Stator Winding Fault in Permanent Magnet Synchronous Motor (PMSM) Part II: Using an Artificial Neural Network Trained with Improved Gravitational Search Algorithm

Faults are inevitable in man-made systems, so that appearance the smallest fault in complex systems can effect on normal system behavior. As mentioned in Part I, Permanent Magnet Synchronous Motors may encounter inter-turn fault. Extension such fault in windings of PMSM can damage all part of electrical systems, and in some cases in sensitive applications may lead to irreparable events. Identification of such small faults at incipient steps can be so helpful to protect entire part of electrical system. In the Part I, modeling PMSM under inter-turn stator winding fault using SIMPOWER elements in MATLAB software is presented and requirement waveforms are extracted. In part II, using an intelligent protection system is designed which is made by two major parts. In the first part of intelligent protection system minimum distance classifier is used as detecting system to discriminate inter-turn fault from normal condition, phase to phase fault and open circuit condition and also to detect faulty phase, simultaneity. After that if inter-turn fault is happened, second part of proposed system which is based on an Artificial Neural Network Trained with Improved Gravitational Search Algorithm determine the amount of fault. Obtained results show that both part of intelligent proposed intelligent protection system can do their best performance. It can successfully detect inter-turn fault and follow it and predict amount of this fault.

کلیدواژه ها:

population optimization algorithm ، gravitational search algorithm ، negative sequence current ، inter-turn stator winding fault ، the minimum distance classifier ، an effective amount of current ، permanent magnet synchronous motor