Transformer fault diagnosis based on back-propagation neural network optimized by cuckoo search algorithm

The operation reliability of power transformer will influence the safety and stability of power system directly. As a widely used technique, the dissolved gas analysis in oil is an effective measure to diagnose the abnormal condition of transformer. In this paper, a new dissolved gas analysis based transformer fault diagnosis method is proposed, which use meta-heuristic search algorithm, called cuckoo search (CS), based on cuckoo bird's behavior to train BP in achieving fast convergence rate and to avoid local minima problem. The simulation results show that this method is effective.