Power grid fault handling plan matching method based on a hybrid neural network

A matching method based on a hybrid neural network is proposed to improve the accuracy of online matching for a power grid fault handling plan. First, the ERNIE 3.0 encoding and double-pointer decoding module are used to replace the generative model in the universal information extraction (UIE) fram...

Full description

Saved in:
Bibliographic Details
Main Authors: Dajun Xiao, Xialing Xu, Bo Zhang, Yue Zhang, Lianfei Shan, Tao Liu, Xin Li, Yongtian Qiao, Tao Jiang, Yu Wang
Format: Article
Language:English
Published: Frontiers Media S.A. 2024-12-01
Series:Frontiers in Energy Research
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fenrg.2024.1468651/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850131269580488704
author Dajun Xiao
Xialing Xu
Bo Zhang
Yue Zhang
Lianfei Shan
Tao Liu
Xin Li
Yongtian Qiao
Tao Jiang
Yu Wang
author_facet Dajun Xiao
Xialing Xu
Bo Zhang
Yue Zhang
Lianfei Shan
Tao Liu
Xin Li
Yongtian Qiao
Tao Jiang
Yu Wang
author_sort Dajun Xiao
collection DOAJ
description A matching method based on a hybrid neural network is proposed to improve the accuracy of online matching for a power grid fault handling plan. First, the ERNIE 3.0 encoding and double-pointer decoding module are used to replace the generative model in the universal information extraction (UIE) framework, and the mapping relationship between entities and entity labels of the fault handling plan is trained by adjusting the hyperparameters of the UIE framework. Then, the semantic distance between the fault equipment, fault type, fault phenomenon, and the entity of the fault handling plan is calculated based on the residual vector-embedding vector-encoded vector (RE2). The hybrid neural network model for power grid fault handling plan matching is established. Finally, by verifying the fault-related data of a regional power grid, the proposed fault handling plan matching method shows higher matching accuracy and stronger generalization ability than other algorithms. The average precision rate, recall rate, and F1 value of the built fault handling plan matching model are 97.61%, 98.24%, and 97.91%, respectively, which can support auxiliary decisions for timely and rapid treatment of power grid faults.
format Article
id doaj-art-c2b437dade4a4ea99ad6ff0ff235d904
institution OA Journals
issn 2296-598X
language English
publishDate 2024-12-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Energy Research
spelling doaj-art-c2b437dade4a4ea99ad6ff0ff235d9042025-08-20T02:32:29ZengFrontiers Media S.A.Frontiers in Energy Research2296-598X2024-12-011210.3389/fenrg.2024.14686511468651Power grid fault handling plan matching method based on a hybrid neural networkDajun Xiao0Xialing Xu1Bo Zhang2Yue Zhang3Lianfei Shan4Tao Liu5Xin Li6Yongtian Qiao7Tao Jiang8Yu Wang9Central China branch of State Grid Co., Ltd. Central China Power Dispatching and Control Center of State Grid, Beijing, ChinaCentral China branch of State Grid Co., Ltd. Central China Power Dispatching and Control Center of State Grid, Beijing, ChinaBeijing Kedong Electric Power Control System Co., Ltd., Beijing, ChinaBeijing Kedong Electric Power Control System Co., Ltd., Beijing, ChinaBeijing Kedong Electric Power Control System Co., Ltd., Beijing, ChinaCentral China branch of State Grid Co., Ltd. Central China Power Dispatching and Control Center of State Grid, Beijing, ChinaCentral China branch of State Grid Co., Ltd. Central China Power Dispatching and Control Center of State Grid, Beijing, ChinaBeijing Kedong Electric Power Control System Co., Ltd., Beijing, ChinaBeijing Kedong Electric Power Control System Co., Ltd., Beijing, ChinaBeijing Kedong Electric Power Control System Co., Ltd., Beijing, ChinaA matching method based on a hybrid neural network is proposed to improve the accuracy of online matching for a power grid fault handling plan. First, the ERNIE 3.0 encoding and double-pointer decoding module are used to replace the generative model in the universal information extraction (UIE) framework, and the mapping relationship between entities and entity labels of the fault handling plan is trained by adjusting the hyperparameters of the UIE framework. Then, the semantic distance between the fault equipment, fault type, fault phenomenon, and the entity of the fault handling plan is calculated based on the residual vector-embedding vector-encoded vector (RE2). The hybrid neural network model for power grid fault handling plan matching is established. Finally, by verifying the fault-related data of a regional power grid, the proposed fault handling plan matching method shows higher matching accuracy and stronger generalization ability than other algorithms. The average precision rate, recall rate, and F1 value of the built fault handling plan matching model are 97.61%, 98.24%, and 97.91%, respectively, which can support auxiliary decisions for timely and rapid treatment of power grid faults.https://www.frontiersin.org/articles/10.3389/fenrg.2024.1468651/fullpower grid fault handling planuniversal information extraction frameworkresidual vector-embedding vector-encoded vectorhybrid neural network modelentity recognitiontext matching
spellingShingle Dajun Xiao
Xialing Xu
Bo Zhang
Yue Zhang
Lianfei Shan
Tao Liu
Xin Li
Yongtian Qiao
Tao Jiang
Yu Wang
Power grid fault handling plan matching method based on a hybrid neural network
Frontiers in Energy Research
power grid fault handling plan
universal information extraction framework
residual vector-embedding vector-encoded vector
hybrid neural network model
entity recognition
text matching
title Power grid fault handling plan matching method based on a hybrid neural network
title_full Power grid fault handling plan matching method based on a hybrid neural network
title_fullStr Power grid fault handling plan matching method based on a hybrid neural network
title_full_unstemmed Power grid fault handling plan matching method based on a hybrid neural network
title_short Power grid fault handling plan matching method based on a hybrid neural network
title_sort power grid fault handling plan matching method based on a hybrid neural network
topic power grid fault handling plan
universal information extraction framework
residual vector-embedding vector-encoded vector
hybrid neural network model
entity recognition
text matching
url https://www.frontiersin.org/articles/10.3389/fenrg.2024.1468651/full
work_keys_str_mv AT dajunxiao powergridfaulthandlingplanmatchingmethodbasedonahybridneuralnetwork
AT xialingxu powergridfaulthandlingplanmatchingmethodbasedonahybridneuralnetwork
AT bozhang powergridfaulthandlingplanmatchingmethodbasedonahybridneuralnetwork
AT yuezhang powergridfaulthandlingplanmatchingmethodbasedonahybridneuralnetwork
AT lianfeishan powergridfaulthandlingplanmatchingmethodbasedonahybridneuralnetwork
AT taoliu powergridfaulthandlingplanmatchingmethodbasedonahybridneuralnetwork
AT xinli powergridfaulthandlingplanmatchingmethodbasedonahybridneuralnetwork
AT yongtianqiao powergridfaulthandlingplanmatchingmethodbasedonahybridneuralnetwork
AT taojiang powergridfaulthandlingplanmatchingmethodbasedonahybridneuralnetwork
AT yuwang powergridfaulthandlingplanmatchingmethodbasedonahybridneuralnetwork