Development of GUI-Driven AI Deep Learning Platform for Predicting Warpage Behavior of Fan-Out Wafer-Level Packaging.

Abstract

This study presents an artificial intelligence (AI) prediction platform driven by deep learning technologies, designed specifically to address the challenges associated with predicting warpage behavior in fan-out wafer-level packaging (FOWLP). Traditional electronic engineers often face difficulties in implementing AI-driven models due to the specialized programming and algorithmic expertise required. To overcome this, the platform incorporates a graphical user interface (GUI) that simplifies the design, training, and operation of deep learning models. It enables users to configure and run AI predictions without needing extensive coding knowledge, thereby enhancing accessibility for non-expert users. The platform efficiently processes large datasets, automating feature extraction, data cleansing, and model training, ensuring accurate and reliable predictions. The effectiveness of the AI platform is demonstrated through case studies involving FOWLP architectures, highlighting its ability to provide quick and precise warpage predictions. Additionally, the platform is available in both uniform resource locator (URL)-based and standalone versions, offering flexibility in usage. This innovation significantly improves design efficiency, enabling engineers to optimize electronic packaging designs, reduce errors, and enhance the overall system performance. The study concludes by showcasing the structure and functionality of the GUI platform, positioning it as a valuable tool for fostering further advancements in electronic packaging.