Haiyue Yu

Papers

Total Citations

H-Index

About

Haiyue Yu is a researcher whose work lies at the intersection of manufacturing optimization and intelligent algorithm design, with a primary focus on improving the efficiency and precision of automotive body-in-white assembly. Yu’s most significant contribution is the development of a novel spot-welding path planning method for curved surface workpieces, which addresses a critical bottleneck in automotive manufacturing. By proposing a hybrid approach based on a memetic algorithm, Yu’s method intelligently separates the problem into two sub-tasks: welding sequence planning and path planning between joints. This dual-stage optimization dramatically reduces computational complexity and travel time for industrial robots, offering a practical, high-impact solution for real-world production lines. The core paper on this work has garnered 13 citations, demonstrating its relevance and utility among peers in manufacturing and robotics. Yu’s research is particularly notable for bridging the gap between theoretical evolutionary computation and tangible industrial application, making complex path planning problems more tractable for curved, non-planar surfaces. For students and researchers in manufacturing engineering or applied metaheuristics, Yu’s work provides a clear example of how memetic algorithms can be tailored to solve specific, high-stakes industrial challenges.