Neurosymbolic AI-Driven Zero-Defect Manufacturing in Semiconductor Assembly: A Hybrid Framework

This paper presents an innovative framework for defect diagnosis and quality control in semiconductor manufacturing using neurosymbolic AI. By integrating knowledge graphs, ontologies, and deep neural networks, the approach harmonizes human expertise and machine learning to predict, diagnose, and mitigate defects in real time. Focusing on Failure Mode and Effects Analysis (FMEA) and other expert sources, the research transforms this knowledge into structured physics-aware ontologies and knowledge graphs to enable seamless integration with neural networks. Additionally, novel ensemble neural network architectures are explored to leverage the full potential of physics-aware neurosymbolic techniques. The proposed framework enhances defect prediction and root cause analysis and also paves the way for more interpretable and adaptive AI-driven quality control systems in semiconductor manufacturing.