Dongmei Huang
Papers
1
Total Citations
2
H-Index
1
About
Dongmei Huang is a researcher specializing in intelligent fault detection and industrial safety systems, with a particular focus on applying deep learning to critical infrastructure monitoring. Her most cited work, "Leakage Detection and Identification of Power Plant Pipelines Based on Improved Faster RCNN" (2022), addresses the pressing challenge of steam and oil leak detection in power plant pipelines. Huang’s key contribution lies in enhancing the Faster RCNN architecture by replacing the standard VGG16 backbone with ResNet101, enabling richer semantic feature extraction for more accurate leak identification. She further integrates a Convolutional Block Attention Module (CBAM) to refine detection precision, resulting in a robust system for real-time pipeline monitoring. While her citation count is currently modest at 2, this work represents a foundational step toward applying advanced computer vision to industrial safety, with potential for significant growth as the field expands. Huang’s research bridges the gap between state-of-the-art object detection algorithms and practical engineering challenges, offering a scalable solution for preventing costly and hazardous pipeline failures. Her work is particularly valuable for researchers and engineers developing AI-driven maintenance systems in energy and manufacturing sectors.
Research Focus
Key Achievements
Top Papers
- 1