Particle Swarm Optimization Based Probabilistic Neural Network for Power Transformer Protection

This paper presents a novel current differential protection scheme based on Probabilistic Neural Network (PNN) for power transformer protection. Particle Swarm Optimization (PSO) technique is used for selecting optimal value of PNN parameter. An algorithm has been developed around the theme of the conventional differential protection of transformer. It makes use of ratio of voltage to frequency and amplitude of differential current for the determination of operating conditions of the transformer. For the evaluation of the algorithm, relaying signals for various operating conditions of a transformer, including internal and external faults and inrush conditions, were simulated in PSCAD/EMTDC. The results amply demonstrate the capability of the proposed algorithm in terms of accuracy and speed. The algorithm has been implemented in MATLAB.