A Method and System for Identifying Partial Discharge Defects in DC Cables

Abstract

The invention discloses a method for identifying a partial discharge defect fault of a direct-current cable. The method comprises the following steps of (1) collecting partial discharge pulse waveformsignals of multiple insulation defect discharge models of the direct-current cable; (2) extracting effective information of the partial discharge pulse waveform signals to obtain training samples; (3) constructing a deep belief network based on a restricted Boltzmann machine, and performing unsupervised training on the deep belief network by adopting the training samples to obtain network parameters; (4) performing supervised training on the deep belief network to optimize the network parameters; and (5) inputting the to-be-identified partial discharge pulse waveform signals into the traineddeep belief network, so as to obtain an identification result from an output of the deep belief network. In addition, the invention discloses a system for identifying the partial discharge defect fault of the direct-current cable. The system comprises a signal collection module, a preprocessing module and a signal processing module. The method and system for identifying the partial discharge defect fault of the direct-current cable are high in accuracy.

Description

technical field [0001] The present invention relates to an identification method and system, in particular to an identification method and system for DC cable faults. Background technique [0002] With the rapid development of flexible high-voltage DC transmission, DC cross-linked polyethylene (XLPE) cables have been used more and more due to their excellent insulation properties. As more and more HVDC projects are put into operation, it is urgent to improve the online monitoring and fault warning system to ensure the reliability of power supply. Since partial discharge (PD) has been included in the detection standard by the International Electrotechnical Commission as an important indicator for judging the status of power equipment, the research on pattern recognition and fault diagnosis of DC cable partial discharge is still in its infancy. [0003] At present, the research on cable partial discharge is mostly aimed at AC XLPE cables, and there is no unified detection met...

AI Technical Summary

Problems solved by technology

Partial discharge (PD) has been included in the detection standard by the International Electrotechnical Commission as an important indicator for judging the status of power equipment, but the research on pattern recognition and fault diagnosis of DC cable partial discharge is still in its infancy.

[0003] At present, the research on cable partial discharge is mostly aimed at AC XLPE cables, and there is no unified detection method and evaluation standard for DC cables. Therefore, there is still a lot of room for research on the pattern recognition of partial discharge signals of DC cables.

Images