用AI优化X射线检测设计，提升先进封装良率。
Design Guidelines for In-line X-ray Inspection in Advanced Packaging Technology: A CoWoS Case Study
- 结合AI与实验设计，系统分析封装参数
- 在CoWoS案例中显著提升检测准确率
- 适合半导体制造与检测工程师参考
先进封装技术（如2.5D/3D集成）虽提升性能与集成度，但复杂三维结构带来测量挑战。X射线成像作为无损检测关键手段，常受材料密度相似与噪声散射影响。本文提出基于AI融合实验设计（DoE）的框架，以CoWoS封装为案例，系统分析设计参数与材料特性，生成优化X射线兼容性的设计指南。该方法利用AI预测结果并优化流程，确保高质量图像与缺陷检出能力。实施后可显著提高检测准确性与可靠性，降低生产成本，支持先进半导体技术的高效与规模化发展。
原文摘要 · Abstract (English)
The shift towards advanced packaging technologies, including 2.5D and 3D integration, addresses the limitations of traditional methods while meeting increasing demands for performance, miniaturization, and efficiency. These methods enhance functionality and support heterogeneous integration but also introduce metrology challenges due to complex, three-dimensional structures. X-ray imaging, crucial for nondestructive inspection, faces compatibility issues such as material density similarities and noise scattering. To address these challenges, we propose a framework based on AI-integrated Design of Experiment (DoE) to develop design guidelines to optimize X-ray compatibility during the design stage. This framework, demonstrated through a case study on Chip-on-Wafer-on-Substrate (CoWoS) packaging, systematically analyzes design parameters and material properties to develop guidelines for improved inspection accuracy. Our method integrates AI to predict outcomes and optimize processes, ensuring high-quality X-ray images and enhancing defect detection. Implementing these guidelines can significantly improve inspection accuracy and reliability, reducing production costs and supporting the efficiency and scalability of advanced semiconductor technologies.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。