Zijian Tang
Papers
2
Total Citations
6
H-Index
1
About
Zijian Tang is a leading researcher in intelligent inspection and fault diagnosis for power systems, with a primary focus on the internal health of large oil-immersed transformers. His work addresses the critical challenge of operating miniature robots within these metal-enclosed, high-risk environments. Tang’s major contributions include pioneering localization and visual inspection techniques for in-tank robots. His 2024 paper on spatial localization, which has garnered 5 citations, introduced an adaptive denoising method combined with SCOT-β generalized cross-correlation to overcome the severe signal attenuation inside transformer enclosures. More recently, in 2025, he developed DCMC-UNet, a novel segmentation model enhanced with dynamic feature fusion and adaptive illumination, achieving 1 citation for its ability to accurately identify carbon traces—a key indicator of insulation failure. By enabling precise robot positioning and robust defect detection in visually challenging conditions, Tang’s work directly enhances the safety and reliability of power transformers, reducing the need for costly manual inspections. His research is essential for advancing autonomous maintenance in the energy sector.
Research Focus
Key Achievements
Top Papers
- 1
- 2