A novel method for intelligent operation and maintenance of transformers using deep visual large model DETR + X and digital twin
Abstract To achieve real-time monitoring and intelligent maintenance of transformers, a framework based on deep vision and digital twin has been developed. An enhanced visual detection model, DETR + X, is proposed, implementing multidimensional sample data augmentation through Swin2SR and GAN networ...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-83561-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559594485153792 |
|---|---|
| author | Xuedong Zhang Wenlei Sun Ke Chen Shijie Song |
| author_facet | Xuedong Zhang Wenlei Sun Ke Chen Shijie Song |
| author_sort | Xuedong Zhang |
| collection | DOAJ |
| description | Abstract To achieve real-time monitoring and intelligent maintenance of transformers, a framework based on deep vision and digital twin has been developed. An enhanced visual detection model, DETR + X, is proposed, implementing multidimensional sample data augmentation through Swin2SR and GAN networks. This model converts one-dimensional DGA data into three-dimensional feature images based on Gram angle fields, facilitating the transformation and fusion of heterogeneous modal information. The Pyramid Vision Transformer (PVT) is innovatively adopted as the backbone for image feature extraction, replacing the traditional ResNet structure. A Deformable Attention mechanism is employed to handle the complex spatial structure of multi-scale features. Testing results indicate that the improved DETR + X model performs well in transformer state recognition tasks, achieving a classification accuracy of 100% for DGA feature maps. In object detection tasks, it surpasses advanced models such as Faster R-CNN, RetinaNet, YOLOv8, and Deformable DETR in terms of overall mAP50 scores, particularly demonstrating significant enhancements in small object detection. Furthermore, the Llava-7b model, fine-tuned based on domain expertise, serves as an expert decision-making tool for transformer maintenance, providing accurate operational recommendations based on visual detection results. Finally, based on digital twin and inference models, a comprehensive platform has been developed to achieve real-time monitoring and intelligent maintenance of transformers. |
| format | Article |
| id | doaj-art-495588aae7e543f0a1d950b88992cabc |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-495588aae7e543f0a1d950b88992cabc2025-01-05T12:21:07ZengNature PortfolioScientific Reports2045-23222025-01-0115112210.1038/s41598-024-83561-7A novel method for intelligent operation and maintenance of transformers using deep visual large model DETR + X and digital twinXuedong Zhang0Wenlei Sun1Ke Chen2Shijie Song3School of Intelligent Manufacturing Modern Industry, Xinjiang UniversitySchool of Intelligent Manufacturing Modern Industry, Xinjiang UniversityTBEA Co., Ltd.School of Intelligent Manufacturing Modern Industry, Xinjiang UniversityAbstract To achieve real-time monitoring and intelligent maintenance of transformers, a framework based on deep vision and digital twin has been developed. An enhanced visual detection model, DETR + X, is proposed, implementing multidimensional sample data augmentation through Swin2SR and GAN networks. This model converts one-dimensional DGA data into three-dimensional feature images based on Gram angle fields, facilitating the transformation and fusion of heterogeneous modal information. The Pyramid Vision Transformer (PVT) is innovatively adopted as the backbone for image feature extraction, replacing the traditional ResNet structure. A Deformable Attention mechanism is employed to handle the complex spatial structure of multi-scale features. Testing results indicate that the improved DETR + X model performs well in transformer state recognition tasks, achieving a classification accuracy of 100% for DGA feature maps. In object detection tasks, it surpasses advanced models such as Faster R-CNN, RetinaNet, YOLOv8, and Deformable DETR in terms of overall mAP50 scores, particularly demonstrating significant enhancements in small object detection. Furthermore, the Llava-7b model, fine-tuned based on domain expertise, serves as an expert decision-making tool for transformer maintenance, providing accurate operational recommendations based on visual detection results. Finally, based on digital twin and inference models, a comprehensive platform has been developed to achieve real-time monitoring and intelligent maintenance of transformers.https://doi.org/10.1038/s41598-024-83561-7Transformer peration and maintenanceVision detection large modelDigital twinMulti-modalMulti-scaleDecision-making suggestions generation |
| spellingShingle | Xuedong Zhang Wenlei Sun Ke Chen Shijie Song A novel method for intelligent operation and maintenance of transformers using deep visual large model DETR + X and digital twin Scientific Reports Transformer peration and maintenance Vision detection large model Digital twin Multi-modal Multi-scale Decision-making suggestions generation |
| title | A novel method for intelligent operation and maintenance of transformers using deep visual large model DETR + X and digital twin |
| title_full | A novel method for intelligent operation and maintenance of transformers using deep visual large model DETR + X and digital twin |
| title_fullStr | A novel method for intelligent operation and maintenance of transformers using deep visual large model DETR + X and digital twin |
| title_full_unstemmed | A novel method for intelligent operation and maintenance of transformers using deep visual large model DETR + X and digital twin |
| title_short | A novel method for intelligent operation and maintenance of transformers using deep visual large model DETR + X and digital twin |
| title_sort | novel method for intelligent operation and maintenance of transformers using deep visual large model detr x and digital twin |
| topic | Transformer peration and maintenance Vision detection large model Digital twin Multi-modal Multi-scale Decision-making suggestions generation |
| url | https://doi.org/10.1038/s41598-024-83561-7 |
| work_keys_str_mv | AT xuedongzhang anovelmethodforintelligentoperationandmaintenanceoftransformersusingdeepvisuallargemodeldetrxanddigitaltwin AT wenleisun anovelmethodforintelligentoperationandmaintenanceoftransformersusingdeepvisuallargemodeldetrxanddigitaltwin AT kechen anovelmethodforintelligentoperationandmaintenanceoftransformersusingdeepvisuallargemodeldetrxanddigitaltwin AT shijiesong anovelmethodforintelligentoperationandmaintenanceoftransformersusingdeepvisuallargemodeldetrxanddigitaltwin AT xuedongzhang novelmethodforintelligentoperationandmaintenanceoftransformersusingdeepvisuallargemodeldetrxanddigitaltwin AT wenleisun novelmethodforintelligentoperationandmaintenanceoftransformersusingdeepvisuallargemodeldetrxanddigitaltwin AT kechen novelmethodforintelligentoperationandmaintenanceoftransformersusingdeepvisuallargemodeldetrxanddigitaltwin AT shijiesong novelmethodforintelligentoperationandmaintenanceoftransformersusingdeepvisuallargemodeldetrxanddigitaltwin |