A kind of cable local aging detection method and detection device

Abstract

The invention relates to a cable local aging detection method and detection device. By measuring the transfer function of the cable in a frequency range, according to the amplitude of the transfer function, based on a deep learning algorithm, the detection deep neural network D-CNN and the positioning deep neural network are used. L‑CNN detects local aging of cables and estimates the location and degree of aging. Since the transfer function is not affected by the phase angle error caused by the real-time communication in the system, it is easy to realize on-line detection. The detection method provided by the invention is suitable for the detection of various local aging modes, and can realize the estimation of the aging degree, so as to provide a basis for the follow-up preventive maintenance; at the same time, it also proposes to solve the local problem under the condition of variable load based on migration learning. Aging positioning problem, based on parameter fine-tuning can improve the accuracy of the detection method under the condition of variable load, save the calculation cost and calculation time.

Description

technical field [0001] The invention relates to the technical field of power system equipment detection, in particular to a method and a detection device for local aging detection of cables. Background technique [0002] Underground cables in the distribution network often age due to moisture or overheating, which eventually leads to insulation breakdown and short-circuit faults, affecting the safe and reliable operation of the power system and causing huge economic losses. Especially for the urban distribution network that is gradually expanding, the operating environment of underground cables is complex, and a branch cable may be overheated due to long-term high-load current operation, resulting in partial aging in sections, or due to some insulation during production and processing. Defects cause localized hot spot aging to occur. However, most of the current research focuses on locating the short-circuit fault of the cable, which is a passive protection method, and it i...

AI Technical Summary

Problems solved by technology

[0004] (1) It can only realize offline detection, which limits the application of this method in practical systems; (2) This method relies on the significant change of impedance at the end of the aging section of the locally aged cable, resulting in low monitoring sensitivity, and it is difficult to apply to the environment with smooth impedance changes (3) This method can only determine the impedance change point, and it is difficult to estimate the aging degree

It is also difficult to apply to the case of terminal aging

Images