Kanghui Zhao

Beijing University of Civil Engineering and Architecture

Papers

Total Citations

H-Index

About

Kanghui Zhao is a researcher advancing the automation of industrial casting processes through innovative computer vision and deep learning techniques. Their primary research focuses on developing lightweight, high-accuracy object detection algorithms specifically designed for pouring robots in complex foundry environments. Zhao’s major contributions include the creation of LPO-YOLOv5s, a streamlined object detection model that addresses the critical challenge of balancing detection accuracy with computational efficiency for real-time deployment in resource-constrained industrial settings. This work has garnered 8 citations, reflecting its relevance to the manufacturing automation community. Building on this foundation, Zhao introduced CP-RDM, a more sophisticated algorithm tailored to identify and precisely locate target pouring holes amidst the visual clutter of casting workshops. This research directly tackles the longstanding difficulty of automating the pouring process, where traditional detection methods falter. By pioneering these specialized deep learning solutions, Zhao is helping to bridge the gap between advanced AI and practical industrial robotics, paving the way for smarter, more autonomous manufacturing systems.