WU Dingyong

Papers

Total Citations

108

H-Index

About

WU Dingyong is a researcher specializing in robotic welding automation, computer vision, and intelligent manufacturing systems. His work sits at the intersection of industrial robotics, machine learning, and human-machine interaction, with a particular focus on advancing the precision and autonomy of welding processes. Wu's most influential contribution is his development of sophisticated seam tracking systems for robotic multi-pass Metal Active Gas (MAG) welding. His 2020 paper on vision-based seam tracking with human-machine interaction has garnered 60 citations, establishing him as a key voice in intelligent robotic welding. Building on this foundation, his 2022 work introduced conditional generative adversarial networks (CGANs) combined with laser vision sensing for multi-layer and multi-pass welding applications, earning 43 citations and demonstrating his commitment to integrating deep learning into real-world manufacturing workflows. His earlier 2019 study on visual sensing-based weld seam correction further reflects his sustained research trajectory in this domain. Collectively, Wu's research addresses critical challenges in welding automation, including real-time error correction, adaptive control, and reducing reliance on manual intervention — contributions that are increasingly relevant to modern smart manufacturing environments.