Kefei Qian

Papers

Total Citations

H-Index

About

Kefei Qian is a researcher whose work lies at the intersection of intelligent sensing, mechanical systems, and deep learning. His primary research focuses on developing advanced computational methods for condition monitoring and structural health assessment, with a particular emphasis on industrial machinery. Qian’s most notable contribution is his pioneering application of deep learning architectures—specifically U-Net-based models—to the quantification and monitoring of belt morphology and wear. His highly cited 2022 paper, "A U-net-based intelligent approach for belt morphology quantification and wear monitoring," has garnered 26 citations, establishing a new paradigm for non-destructive, automated inspection in manufacturing and mining environments. By integrating convolutional neural networks with traditional mechanical diagnostics, Qian has enabled real-time, high-precision wear assessment that reduces downtime and enhances safety. His work bridges the gap between computer vision and mechanical engineering, offering practical solutions for predictive maintenance. Qian’s research is particularly impactful for students and engineers interested in the convergence of AI and industrial IoT, demonstrating how deep learning can transform routine mechanical monitoring into a proactive, data-driven discipline.