Data-Driven Incipient Ageing Location for Underground Power Distribution System Informed by Common-Mode Voltage Distribution

Incipient ageing in power cable insulation will eventually develop into severe faults. Effective location of incipient ageing can assist proactive maintenance, improving the reliability of power distribution system. However, accurate location of cable incipient ageing is difficult due to the nonlinear relationship between the measurements and ageing parameters, coupling between ageing location and severity, and existing numerous ageing patterns. To overcome these problems, a novel data-driven incipient ageing location method is designed in this paper, which innovatively combines physical analysis and data-driven approach to improve method effectiveness. The main idea is using the common-mode (CM) leakage current variation pattern as a novel ageing location indicator to realize the decoupling of ageing location and severity. Theoretical analysis has been conducted on CM voltage and leakage current pattern along the cable, which proves that the selected indicator is mainly dominated by the ageing location, regardless of different ageing severities. Furthermore, a data-driven incipient ageing location algorithm informed by the physical analysis is designed. The ageing location is estimated from the CM leakage current measurements accurately, with limited amount of data and high generalization ability. Simulations and experiments validate the proposed method. Compared with the existing methodology, more accurate location can be realized with a measurement frequency range lowered by 10 times.