XLPE cable insulation early degradation multi-dimensional evaluation method based on machine learning

Abstract

The invention provides an XLPE cable insulation early degradation multi-dimensional evaluation method based on machine learning. The method comprises the steps of performing integration on current to construct an XLPE cable alternating current charge test system to obtain a space charge cumulant of a to-be-tested XLPE cable; then constructing an XLPE cable partial discharge monitoring system based on a high-frequency CT sensor, obtaining discharge basic parameters of an XLPE cable in a plurality of power frequency periods, integrating the discharge basic parameters in the plurality of power frequency periods into the same power frequency period, and extracting features of key parameters; and obtaining a degradation evaluation result according to the charge cumulant of the space charge of the XLPE cable and the characteristics of the key parameters in combination with the trained XLPE cable early-stage degradation multi-dimensional evaluation model.

Description

technical field [0001] The present disclosure relates to the technical field of cable insulation diagnosis, and in particular to a machine learning-based multidimensional evaluation system and method for early deterioration of XLPE cable insulation. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] Cross-linked polyethylene (XLPE) cables have been widely used in the power transmission process of the power system. The failures and hidden dangers caused by the aging of the insulation and the lack of early diagnosis and detection technology have become the bottlenecks that plague the safe, stable and reliable operation of the power system. Moreover, the cable lines that were put into operation in the early stage have gradually entered the end of their life. Due to the lack of diagnosis and status detection theory and technology, these cables ca...

AI Technical Summary

Problems solved by technology

[0003] Cross-linked polyethylene (XLPE) cables are widely used in the power transmission process of the power system. The failures and hidden dangers caused by the aging of the insulation and the lack of early diagnosis and detection technology have become the bottlenecks that plague the safe, stable and reliable operation of the power system.

Moreover, the cable lines that were put into operation in the early stage have gradually entered the end of their life. Due to the lack of diagnosis and status detection theory and technology, these cables can continue to operate safely and stably. Potential safety hazards, huge economic losses and social impact caused by failures

[0004] Therefore, the evaluation of the early degradation of the cable insulation can reflect the status of the cable in time, and timely intervention measures can be taken according to the evaluation results. However, the evaluation of the early degradation of the cable insulation in the prior art is mostly based on partial discharge or space charge alone, which cannot be accurate. Therefore, the multi-dimensional evaluation method that comprehensively considers space charge and partial discharge is of great significance to the fault diagnosis of XLPE cables.

Images