Fault Location for Transmission Lines using Inference Model Neural Network

Abstract

The authors propose a new fault location method which uses neural network to analyze the distribution pattern of the ground wire current along the power line. This method is capable for locating the fault section even for secondary power lines with complicated configurations. Our method has the structure based on the inference process that human experts will analyze the distribution pattern of the current amplitude and phase angle. In locating fault sections, higher precision than ordinary 3-layer neural network or the expert system of our previous development can be obtained.
The proposed neural network comprises 3 sets of 3-layer neural networks which follow the back propagation learning procedure. The 1st and 2nd neural networks calculate the candidate-1 and candidate-2 for the fault section using current amplitude and phase angle distribution patterns respectively. The 3rd neural network then performs final fault location using these candidates and current amplitude distribution pattern. The results evaluated with all possible fault cases indicate that the new method achieves its precision as high as 98.4% even when the measured values differ by 30% from predicted ones with EMTP.