AI-based Quality Control

This project focused on the development of efficient AI-driven quality control methodologies for industrial inspection and monitoring applications. The work investigated how deep neural networks can be deployed on resource-constrained and edge-oriented hardware platforms while maintaining robustness against operational variability and its impact on the quality of the products. Particular emphasis was placed on hardware-aware AI optimization, lightweight inference, and dependable deployment strategies suitable for real-time industrial environments. Activities included algorithmic optimization, reliability analysis, experimental evaluation, and dissemination of the obtained results. The project served as an important foundation for subsequent research and practical directions on AI systems for industrial environments.