FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3163634674> ?p ?o ?g. }

• W3163634674 abstract "Deep learning based transformer protection has attracted increasing attention. However, its poor generalization abilities hinder the application of deep learning in the power system owing to the limited training samples. In order to improve its generalization abilities, this paper proposes a knowledge- based convolutional neural network (CNN) for the transformer protection. In general, the power experts can reliably discriminate between faulty transformers and healthy transformers only through the unsaturated parts of equivalent magnetization curve (voltage of magnetizing branch-differential current curve) but deep learning intends to focus on the combined features of saturated and unsaturated parts. Inspired by the identification process of power experts, CNN adopted a specially designed loss function in this paper which is used to identify the running states of power transformers. Specifically, the presented Restrictive Weight Sparsity substitutes a special regularization term for the common L1 regularization. The presented Adaptive Sample Weight Adjustment endows the softmax loss of each sample with the optimizable weight the softmax loss of each sample with the optimizable weights to increase the impact of more-difficult-to-identify cases on the training process. With the modified loss function, the knowledge is abstractly introduced into the training process of CNN so as to successfully imitate the identification process of power experts. Accordingly, the proposed knowledge- based CNN will pay more attention to the unsaturated parts of equivalent magnetization curve even if only limited samples are included in the training process. The results of simulations and dynamic model experiments reveal that the knowledge-based CNN exhibits an improved generalization ability and the knowledge-based deep learning algorithm is a promising research direction." @default.
• W3163634674 created "2021-05-24" @default.
• W3163634674 creator A5001176139 @default.
• W3163634674 creator A5017100899 @default.
• W3163634674 creator A5065656469 @default.
• W3163634674 date "2020-01-01" @default.
• W3163634674 modified "2023-09-24" @default.
• W3163634674 title "Professional knowledge-based convolutional neural network for transformer protection" @default.
• W3163634674 cites W1532940862 @default.
• W3163634674 cites W1994605497 @default.
• W3163634674 cites W2021022493 @default.
• W3163634674 cites W2029659091 @default.
• W3163634674 cites W2066318905 @default.
• W3163634674 cites W2080975658 @default.
• W3163634674 cites W2082424749 @default.
• W3163634674 cites W2089492819 @default.
• W3163634674 cites W2091849019 @default.
• W3163634674 cites W2102259958 @default.
• W3163634674 cites W2104612563 @default.
• W3163634674 cites W2140865022 @default.
• W3163634674 cites W2158246475 @default.
• W3163634674 cites W2343421684 @default.
• W3163634674 cites W2963410812 @default.
• W3163634674 cites W2993533229 @default.
• W3163634674 doi "https://doi.org/10.17775/cseejpes.2020.04480" @default.
• W3163634674 hasPublicationYear "2020" @default.
• W3163634674 type Work @default.
• W3163634674 sameAs 3163634674 @default.
• W3163634674 citedByCount "0" @default.
• W3163634674 crossrefType "journal-article" @default.
• W3163634674 hasAuthorship W3163634674A5001176139 @default.
• W3163634674 hasAuthorship W3163634674A5017100899 @default.
• W3163634674 hasAuthorship W3163634674A5065656469 @default.
• W3163634674 hasBestOaLocation W31636346741 @default.
• W3163634674 hasConcept C119599485 @default.
• W3163634674 hasConcept C127413603 @default.
• W3163634674 hasConcept C154945302 @default.
• W3163634674 hasConcept C165801399 @default.
• W3163634674 hasConcept C200601418 @default.
• W3163634674 hasConcept C41008148 @default.
• W3163634674 hasConcept C50644808 @default.
• W3163634674 hasConcept C66322947 @default.
• W3163634674 hasConcept C81363708 @default.
• W3163634674 hasConceptScore W3163634674C119599485 @default.
• W3163634674 hasConceptScore W3163634674C127413603 @default.
• W3163634674 hasConceptScore W3163634674C154945302 @default.
• W3163634674 hasConceptScore W3163634674C165801399 @default.
• W3163634674 hasConceptScore W3163634674C200601418 @default.
• W3163634674 hasConceptScore W3163634674C41008148 @default.
• W3163634674 hasConceptScore W3163634674C50644808 @default.
• W3163634674 hasConceptScore W3163634674C66322947 @default.
• W3163634674 hasConceptScore W3163634674C81363708 @default.
• W3163634674 hasLocation W31636346741 @default.
• W3163634674 hasOpenAccess W3163634674 @default.
• W3163634674 hasPrimaryLocation W31636346741 @default.
• W3163634674 hasRelatedWork W2285788670 @default.
• W3163634674 hasRelatedWork W2521062615 @default.
• W3163634674 hasRelatedWork W2735477435 @default.
• W3163634674 hasRelatedWork W2748952813 @default.
• W3163634674 hasRelatedWork W2899084033 @default.
• W3163634674 hasRelatedWork W2955938200 @default.
• W3163634674 hasRelatedWork W2998526951 @default.
• W3163634674 hasRelatedWork W3090822330 @default.
• W3163634674 hasRelatedWork W3119610945 @default.
• W3163634674 hasRelatedWork W3181746755 @default.
• W3163634674 isParatext "false" @default.
• W3163634674 isRetracted "false" @default.
• W3163634674 magId "3163634674" @default.
• W3163634674 workType "article" @default.