A novel method for intelligent operation and maintenance of transformers using deep visual large model DETR + X and digital twin
2025

Intelligent Operation and Maintenance of Transformers Using Deep Learning

publication 10 minutes Evidence: high

Author Information

Author(s): Zhang Xuedong, Sun Wenlei, Chen Ke, Song Shijie

Primary Institution: Xinjiang University

Hypothesis

Can deep visual models and digital twin technology improve the monitoring and maintenance of transformers?

Conclusion

The proposed DETR+X model significantly enhances the accuracy and efficiency of transformer monitoring and maintenance.

Supporting Evidence

  • The DETR+X model achieved a classification accuracy of 100% for DGA feature maps.
  • It outperformed existing models in small object detection tasks.
  • The integration of digital twin technology allows for real-time monitoring.
  • Data augmentation techniques improved model robustness.
  • Deformable attention mechanisms enhanced feature extraction capabilities.

Takeaway

This study shows how using advanced computer models can help keep transformers running safely and efficiently by spotting problems early.

Methodology

The study integrates deep visual detection models with digital twin technology for real-time monitoring and maintenance of transformers.

Limitations

The model requires longer training times and may not effectively align multi-modal data.

Digital Object Identifier (DOI)

10.1038/s41598-024-83561-7

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication