Application of Artificial Neural Network to Transmission Line Faulty Phase Selection and Fault Distance Location

A. Jain, V.S. Kale, and A.S. Thoke (India)


Transmission Line Protection, Fault Detection, Phase Selection, Fault location, Inception angle, Fault resistance, Neural Network.


A novel application of neural network approach to protection of double end fed transmission line is demonstrated in this paper. Different system faults (including high impedance fault HIF) on a protected transmission line should be detected classified and located rapidly and correctly. This paper presents the use of neural networks as a protective relaying fault detector and fault locator. The proposed fault detector algorithm uses current signals to learn the hidden relationship in the input patterns. Using the proposed approach, fault detection and faulted phase selection could be achieved within a quarter cycle. The proposed fault locator algorithm uses fundamental components of current & voltage signals to learn the hidden relationship in the input patterns An improved performance is obtained once the neural network is trained sufficiently and suitably, thus performing correctly when faced with different system parameters and conditions (including high impedance fault HIF) e.g. 0-100Ω fault resistance, ±45 degrees initial power flow angle δs etc.

Important Links:

Go Back