Detection, Classification and Zone Location of Fault in Transmission Line using Artificial Neural Network

Faults in transmission lines have several adverse impacts on the overall health of the power system. Circuit breakers and relays help in isolating the fault and protecting the entire system. Prompt tripping of the circuit breakers is a vital aspect of power system protection, to minimize the extent of damage. Numerical relays could provide high degrees of accuracy and precision, supported by their powerful processing systems and the wide range of algorithms that could be incorporated. This paper presents an efficient algorithm to detect unsymmetrical faults, classify the fault type and locate the fault zone in transmission lines using Artificial Neural Network (ANN), which could be implemented in numerical relays. The complete system is capable of identifying no-fault condition, the three different line-to-ground faults, line-to-line faults and double line-to-ground faults, and indicating the zone in which the fault has developed. To locate the fault, three zones have been recognized in each transmission line. The same algorithm is implemented in hardware and results are presented.