Application of artificial neural network in fault location technique

Abstract

Recent restructuring of the power industries such as open access and deregulation have an impact on the reliability and security of power systems. New technologies for protection and control schemes are therefore necessary to be introduced in order to maintain the system reliability and security to an acceptable level. Artificial intelligence (AI) techniques naturally become the best choice to improve the performance of the present system used. Most faults which have infeed sources from both ends of the line, especially earth faults with fault resistance, are very difficult to identify. This paper presents a novel approach that can overcome the above difficulties. The artificial neural network (ANN) is used to identify the fault location, as well as the fault resistance in a wide range of system conditions. The training of the ANN is relatively simple and fast. The predicated results from the ANN are proved to be accurate for a wide range of system conditions.