In:
Journal of Physics: Conference Series, IOP Publishing, Vol. 2474, No. 1 ( 2023-04-01), p. 012081-
Abstract:
For ensuring the safe operation of distribution switch cabinet, a regular maintenance system is implemented. As the specific conditions of the equipment operation are not considered, there are too many unnecessary shutdowns and maintenance, resulting in the situation that “the equipment is not damaged, but repaired”. Moreover, troubleshooting mainly depends on the sense organs, experience and instruments of the maintenance personnel. The ability and experience of the maintenance staff is what limits the quality of the maintenance since the time spent identifying the fault reasons typically makes up more than 60% of the overall troubleshooting time. The stability of the entire power supply system is directly impacted by the dependability and safety of the power distribution switchgear. To prevent “insufficient maintenance” and “excessive maintenance” brought on by planned maintenance. This paper examines the RBF neural network’s offline and online training techniques as a result. Additionally, the analysis of the RBF neural network’s offline and online training techniques is proposed using the closest neighbor-gradient hybrid learning algorithm. Additionally, the hybrid closest neighbor-gradient training approach is suggested. Experiments using Matlab simulations show that the diagnostic results are more accurate.
Type of Medium:
Online Resource
ISSN:
1742-6588
,
1742-6596
DOI:
10.1088/1742-6596/2474/1/012081
Language:
Unknown
Publisher:
IOP Publishing
Publication Date:
2023
detail.hit.zdb_id:
2166409-2
Permalink
