Dengjie Yang
Papers
3
Total Citations
57
H-Index
3
About
Dengjie Yang is a researcher at the forefront of intelligent mining and automation, specializing in computer vision and reinforcement learning for coal gangue sorting robotics. His work addresses a critical industrial challenge: the efficient detection and removal of gangue and foreign matter from coal to improve thermal properties and protect transportation equipment. Yang’s major contributions include developing enhanced object detection and tracking algorithms, notably an improved YOLOv7 network integrated with DeepSORT for real-time foreign object identification in coal, which has garnered 39 citations. He further advanced trajectory control for robotic manipulators using an improved Deep Q-Network (DQN) model, achieving intelligent motion planning through reinforcement learning. With a cumulative citation count exceeding 57, Yang’s research demonstrates significant practical impact, directly supporting the deployment of gangue selection robots in mining operations. His work bridges deep learning and robotics, offering scalable solutions for automated coal processing and setting a foundation for future innovations in intelligent industrial sorting systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3