Artificial Based Techniques for Distinguishing Inrush Current from Faults in Large Power Transformers

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. It should be mentioned that, transformers outage may result in costly and time-consuming repair or replacement. In this paper, 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 between inrush current and fault currents in power transformers. In fact, GSA operates based on gravity law 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 an ANN, and then in second step, using training data considered ANN has been trained by GSA & PSO. Proposed technique has been compared with one of the common training approach which is called Back Propagation (BP) and finally, results show that proposed technique is so quick and can do discrimination very accurate and without any computational burdens.

Artificial Neural Network, Gravitational Search Algorithm, Inrush Current, Internal Faults, Particle Swarm Optimization, Power Transformers.Artificial Neural Network, Gravitational Search Algorithm, Inrush Current, Internal Faults, Particle Swarm Optimization, Power Transformers.