Yingda Dai

Papers

Total Citations

H-Index

About

Yingda Dai’s research bridges robotics and intelligent manufacturing, with a focus on cooperative motion control and automated welding quality assurance. In his foundational work on cooperative motion control of 2-DOF robot arms, Dai pioneered the use of recurrent neural networks (RNNs) to enable synchronized, adaptive coordination between multiple robotic manipulators—a critical capability for complex assembly tasks. This work, cited in subsequent robotics control studies, laid the groundwork for more responsive multi-robot systems. Dai’s most impactful contribution, however, lies in industrial welding automation. He led the development of a blowhole detection system for robotic multi-layered pulse MAG welding, a process essential for large-scale structures. By integrating advanced sensing technology, his system can identify welding defects in real time, directly improving productivity and weld quality in heavy industries. This work, published in 2017, has been recognized for its practical value in reducing costly post-weld inspections. With a career spanning foundational neural network control to applied defect detection, Dai demonstrates how theoretical advances in robotics can solve real-world manufacturing challenges. His research continues to influence both academic studies in cooperative robotics and industrial implementations of intelligent welding systems.