Document technique

Enhancing multi-layer process defect prediction accuracy on an artificial intelligence/machine learning (AI/ML) platform

Feature vector fine-tuning with additional product failure analysis data. The design layout and PFA data are processed by an artificial intelligence/machine learning regression model, which fine tunes the feature vectors to reflect process effect.

Accurately predicting manufacturing defects is critical for semiconductor companies to reduce costs and get new chips to market faster. This paper presents two key advancements to an existing AI/ML-based defect prediction platform that significantly improve its accuracy.

First, the researchers incorporated physical failure analysis (PFA) data to fine-tune the feature vectors used in the AI model. This allowed the system to better capture real-world defect patterns that may not be apparent from design layout data alone. Second, they developed a reinforcement learning approach to reduce false positive defect predictions, further enhancing the platform's reliability.

These enhancements make the AI/ML defect prediction system more robust and valuable for semiconductor companies. By catching more actual defects while reducing false alarms, chipmakers can accelerate their design-to-manufacturing cycles and improve overall yield. The process-aware, self-learning capabilities showcased here represent an important step forward in making AI-powered defect detection a cornerstone of advanced chip design and manufacturing.

This paper was presented at the 2025 SPIE Advanced Lithography + Patterning symposium.

What you'll learn:

  • How incorporating physical failure analysis (PFA) data can improve the accuracy of AI/ML-based defect prediction models by better capturing real-world defect patterns
  • How a reinforcement learning approach reduces false positive defect predictions
  • What the benefits are of these advancements, including accelerated design-to-manufacturing cycles and improved chip yield
  • How process-aware, self-learning AI capabilities are advancing the state-of-the-art in semiconductor defect detection

Who should read this:

  • Semiconductor manufacturing engineers
  • Process integration and yield engineers
  • R&D teams working on AI/ML applications for semiconductor manufacturing
  • Engineering managers and leaders in the semiconductor industry
  • Researchers and academics studying advanced defect detection and prediction methods

Partager

Ressources associées