Discrimination of Inrush Currents from Faults Current in Power Transformers using Gravitational Search Algorithm (GSA)

The magnetizing inrush current phenomenon is a large transient condition، which occurs when a transformer is energized. The inrush current magnitude may be as high as ten times of transformer rated current that causes mal-operation of protection systems. Indeed، the similarity between signatures of Inrush current and internal fault condition make this failure. So، for safe running of a transformer، it is necessary to distinguish inrush current from fault currents. In this project، an Artificial Neural Network (ANN) which is trained by two different swarm based algorithms; Gravitational Search Algorithm (GSA) and Particle Swarm Optimization (PSO) have been used to discriminate inrush current from fault currents in power transformers. GSA works based on gravity laws and in opposite of other swarm based algorithms، particles have identity and PSO is based on behaviors of bird flocking. Proposed approach has two general stages، in first step، obtained data from simulation have been processed and applied to ANN، and then in step two، using training data considered ANN has been trained by GSA & PSO. Proposed method has been compared with one of the common training approach which is called Back Propagation (BP) and Results show that proposed method is so quick and can do discrimination very accurate.