Qianyu Zhou
Papers
3
Total Citations
7
H-Index
2
About
Qianyu Zhou’s research advances automated visual inspection in manufacturing, focusing on overcoming data scarcity and adapting to complex part geometries. Their key contributions lie in surface defect detection for high-value components like engine blades, where minor scratches or dents can compromise quality. Zhou pioneered the use of generative adversarial networks (GANs) for data augmentation, introducing an adaptive learning bias that significantly improves defect detection accuracy when training data is limited—a paper already garnering 3 citations since 2024. Earlier work established semi-supervised learning methods for part surface inspection, enabling reliable detection with minimal labeled examples, and developed a flexible quality inspection robot system capable of handling multi-type surface defects across diverse objects, moving beyond rigid, task-specific designs. With a citation count of 7 across their most-cited works, Zhou’s research directly addresses industrial challenges in quality assurance, reducing labor costs and improving effectiveness. Their adaptable, data-efficient approaches are particularly notable for their potential to transform automated inspection in small-batch, high-mix manufacturing environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3