Research on digital twin modelling technique for ±800 kV converter transformers scene based on hybrid attention mechanism and multiresolution hash encoding

Abstract Digital twin (DT) modelling is a prerequisite for the successful application of DT technology in the power industry. However, traditional scene modelling methods are costly, time‐consuming, focus on overall features and lack real‐time updates, hindering the interaction between DT models and...

Full description

Saved in:
Bibliographic Details
Main Authors: Hao Luo, Li Cheng, Pengyong Yi, Jiuyi Wang, Xuetong Zhao, Lijun Yang, Ruijin Liao
Format: Article
Language:English
Published: Wiley 2025-04-01
Series:High Voltage
Online Access:https://doi.org/10.1049/hve2.70019
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849713183357403136
author Hao Luo
Li Cheng
Pengyong Yi
Jiuyi Wang
Xuetong Zhao
Lijun Yang
Ruijin Liao
author_facet Hao Luo
Li Cheng
Pengyong Yi
Jiuyi Wang
Xuetong Zhao
Lijun Yang
Ruijin Liao
author_sort Hao Luo
collection DOAJ
description Abstract Digital twin (DT) modelling is a prerequisite for the successful application of DT technology in the power industry. However, traditional scene modelling methods are costly, time‐consuming, focus on overall features and lack real‐time updates, hindering the interaction between DT models and physical power equipment scenes. Therefore, a scene DT modelling technique focusing on local features in risk areas and real‐time updates is urgently needed. Herein, real‐time modelling of the ±800 kV converter transformer is achieved by improving the neural radiation field based on a hybrid attention mechanism and multiresolution hash encoding. Compared to traditional methods, modelling time is reduced from hours to 1 min without professional equipment or manual intervention. The model quality is more concerned with local features of risk areas in transformers while ensuring the overall scene, and the accuracy is improved by about 6%, realising the real‐time modelling of transformers and the DT of scenes.
format Article
id doaj-art-e5d03e2beccf421b892cdd7edce1fead
institution DOAJ
issn 2397-7264
language English
publishDate 2025-04-01
publisher Wiley
record_format Article
series High Voltage
spelling doaj-art-e5d03e2beccf421b892cdd7edce1fead2025-08-20T03:14:01ZengWileyHigh Voltage2397-72642025-04-0110229430410.1049/hve2.70019Research on digital twin modelling technique for ±800 kV converter transformers scene based on hybrid attention mechanism and multiresolution hash encodingHao Luo0Li Cheng1Pengyong Yi2Jiuyi Wang3Xuetong Zhao4Lijun Yang5Ruijin Liao6State Key Laboratory of Power Transmission Equipment Technology School of Electrical Engineering Chongqing University Chongqing ChinaState Key Laboratory of Power Transmission Equipment Technology School of Electrical Engineering Chongqing University Chongqing ChinaTsinghua University Shenzhen International Graduate School Shenzhen ChinaState Key Laboratory of Power Transmission Equipment Technology School of Electrical Engineering Chongqing University Chongqing ChinaState Key Laboratory of Power Transmission Equipment Technology School of Electrical Engineering Chongqing University Chongqing ChinaState Key Laboratory of Power Transmission Equipment Technology School of Electrical Engineering Chongqing University Chongqing ChinaState Key Laboratory of Power Transmission Equipment Technology School of Electrical Engineering Chongqing University Chongqing ChinaAbstract Digital twin (DT) modelling is a prerequisite for the successful application of DT technology in the power industry. However, traditional scene modelling methods are costly, time‐consuming, focus on overall features and lack real‐time updates, hindering the interaction between DT models and physical power equipment scenes. Therefore, a scene DT modelling technique focusing on local features in risk areas and real‐time updates is urgently needed. Herein, real‐time modelling of the ±800 kV converter transformer is achieved by improving the neural radiation field based on a hybrid attention mechanism and multiresolution hash encoding. Compared to traditional methods, modelling time is reduced from hours to 1 min without professional equipment or manual intervention. The model quality is more concerned with local features of risk areas in transformers while ensuring the overall scene, and the accuracy is improved by about 6%, realising the real‐time modelling of transformers and the DT of scenes.https://doi.org/10.1049/hve2.70019
spellingShingle Hao Luo
Li Cheng
Pengyong Yi
Jiuyi Wang
Xuetong Zhao
Lijun Yang
Ruijin Liao
Research on digital twin modelling technique for ±800 kV converter transformers scene based on hybrid attention mechanism and multiresolution hash encoding
High Voltage
title Research on digital twin modelling technique for ±800 kV converter transformers scene based on hybrid attention mechanism and multiresolution hash encoding
title_full Research on digital twin modelling technique for ±800 kV converter transformers scene based on hybrid attention mechanism and multiresolution hash encoding
title_fullStr Research on digital twin modelling technique for ±800 kV converter transformers scene based on hybrid attention mechanism and multiresolution hash encoding
title_full_unstemmed Research on digital twin modelling technique for ±800 kV converter transformers scene based on hybrid attention mechanism and multiresolution hash encoding
title_short Research on digital twin modelling technique for ±800 kV converter transformers scene based on hybrid attention mechanism and multiresolution hash encoding
title_sort research on digital twin modelling technique for 800 kv converter transformers scene based on hybrid attention mechanism and multiresolution hash encoding
url https://doi.org/10.1049/hve2.70019
work_keys_str_mv AT haoluo researchondigitaltwinmodellingtechniquefor800kvconvertertransformersscenebasedonhybridattentionmechanismandmultiresolutionhashencoding
AT licheng researchondigitaltwinmodellingtechniquefor800kvconvertertransformersscenebasedonhybridattentionmechanismandmultiresolutionhashencoding
AT pengyongyi researchondigitaltwinmodellingtechniquefor800kvconvertertransformersscenebasedonhybridattentionmechanismandmultiresolutionhashencoding
AT jiuyiwang researchondigitaltwinmodellingtechniquefor800kvconvertertransformersscenebasedonhybridattentionmechanismandmultiresolutionhashencoding
AT xuetongzhao researchondigitaltwinmodellingtechniquefor800kvconvertertransformersscenebasedonhybridattentionmechanismandmultiresolutionhashencoding
AT lijunyang researchondigitaltwinmodellingtechniquefor800kvconvertertransformersscenebasedonhybridattentionmechanismandmultiresolutionhashencoding
AT ruijinliao researchondigitaltwinmodellingtechniquefor800kvconvertertransformersscenebasedonhybridattentionmechanismandmultiresolutionhashencoding