Single phase grounding fault location of low voltage distribution network based on artificial neural network

The actual low-voltage distribution network environment is complex and changeable, and there are noise, interference and other factors. Existing methods may have some limitations on fault location in these complex environments, resulting in poor fault location performance. In this regard, the single-phase grounding fault location method of low-voltage distribution network based on artificial neural network is studied. In this paper, the characteristics of single-phase grounding fault in low-voltage distribution network are analyzed, and a fault location method based on artificial neural network is proposed. By dividing the fault into steady-state and transient features, the feature quantity is extracted as the input, and the BP neural network model is used for fault location. After training and optimizing the network weight and bias, the accurate single-phase grounding fault location of low-voltage distribution network is realized. The experimental results show that the designed fault location method has obvious advantages in accuracy and reliability, can improve the efficiency and accuracy of fault location, and provide important support for the reliable power supply of power system.