Incipient fault identification of distribution networks based on feature matching of power disturbance data

Accurate identification of incipient cable fault is helpful to improve the reliability of power system. This paper proposes an incipient fault identification method for distribution networks cables based on feature matching of power disturbance data. Firstly, based on the power disturbance data provided by the power quality monitor about the incipient faults, a characteristic analysis is performed, and three characteristics F1 to F3 that can distinguish the incipient faults of the cable are extracted. Then, the common abnormal condition of 10 kV system is simulated, and the feature quantity is extracted to establish the feature database. Finally, a topic search algorithm is used to perform correlation matching, so as to quickly and accurately identify incipient cable faults from a variety of abnormal conditions. This method can be used to predict cable faults and evaluate the health status, while providing system operation engineers and dispatchers with advanced situational awareness and the causes of impending failures to reduce accident losses and hazards. Simulation results show that the proposed method has high accuracy.