This paper presents an Artificial Neural Network (ANN) based numerical differential protection scheme for power transformer protection and condition monitoring. The scheme includes two feedforward neural networks (FFNNs). One ANN is used for fault detection and the other is used for monitoring different operating conditions of the transformer, detects the fault and issues the trip signal in case of internal fault only. The proposed protection scheme is accurate, fast, efficient and reliable. This protection scheme has been evaluated using simulated data obtained through EMTP package. The results amply demonstrate the capabilities of fault detector (FD) and condition Monitor (CM) in terms of accuracy and speed with respect to detection of fault, classification and pattern recognition of different events of power transformer.

كلمات كليدي:

Artificial Neural Network, Fault Detection, Condition Monitoring, Feed-forward back -propagation, power transformer protection.