Daogang Peng
Papers
1
Total Citations
2
H-Index
1
About
Daogang Peng is a leading researcher in intelligent power system monitoring and infrared image processing, with a focus on enhancing the reliability and automation of substation inspection. His work centers on developing advanced algorithms for fault detection, image segmentation, and multi-sensor data fusion, particularly for robotic inspection systems. Peng’s most notable contribution is his innovative integration of modified unit-linking pulse coupled neural networks (MUL-PCNN) with affine speeded up robust features (ASURF) to achieve precise fusion of infrared and visible images. This approach enables accurate temperature reading, fault point localization, and target device segmentation in substation environments—critical for early warning systems. His 2019 paper on this method, though early in its citation impact, demonstrates a novel solution to a pressing industry challenge. Peng’s research bridges computer vision and power engineering, offering practical tools for automated fault diagnosis. His work is especially valuable for students and researchers interested in applying deep learning and neural network techniques to real-world energy infrastructure problems, where even modest citation counts reflect the niche but vital nature of his contributions to substation safety and efficiency.
Research Focus
Key Achievements
Top Papers
- 1