PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
February 19, 2026Journal of Electronic Packaging0 citations

A Hybrid FEA-Machine Learning-Generative AI (GANs) Framework for Predicting Reliability Risks in 3D IC Packaging

View Full Paper
URUnique RahangdalePRPranali RahangdaleSWShouyi Wang

Key Points

  • The study aims to develop an accelerated predictive framework for reliability risks in 3D IC packaging using advanced simulation and machine learning techniques.
  • Conducted thermal finite element analysis using synthetic load profiles derived from real data-center data
  • Extracted reliability indicators through structural finite element analysis to inform machine learning models
  • Trained regression models on a dataset formed from hundreds of simulations to predict thermal and mechanical metrics rapidly
  • Implemented a conditional Generative Adversarial Network (cGAN) to produce intuitive thermal maps for visual prognosis
  • Developed models that significantly reduce the time required for reliability predictions in 3D IC packaging
  • Demonstrated the capability of the cGAN to generate FEA-like thermal images for real-time monitoring
  • Achieved improved accuracy in predicting solder joint plastic strain and stress concentration under varying conditions

Abstract

Abstract The rapid rise in power density for modern AI and data-center hardware has made thermal management and long-term reliability major challenges in advanced electronics. Ensuring high availability requires predictive tools capable of estimating component lifespan under continuously changing operating conditions. Three-Dimensional Integrated Circuit (3D IC) technology enables high functional density 1, but predicting its lifetime under realistic workloads remains difficult. Prior studies have examined individual failure mechanisms, such as solder joint fatigue, yet a fast and comprehensive prognostic reliability framework is still missing. This work proposes a two-stage methodology that integrates physics-based simulations with machine learning (ML) and Conditional Generative Adversarial Network (cGAN) models to accelerate reliability prediction for 3DIC. First, detailed thermal Finite Element Analysis (FEA) was conducted using synthetic thermal and thermomechanical load profiles derived from real data-center behavior. These simulations capture temperature distribution across the stacked dies under varying power and cooling conditions. A subsequent structural FEA extracts key reliability indicators, such as solder joint plastic strain and stress. Hundreds of simulations form the dataset for training ML regression models that rapidly predict thermal and mechanical metrics, serving as surrogate models for expensive FEA runs. The second component introduces an ML-based visual prognosis method. FEA-generated thermal images were used to train a cGAN that can instantly produce FEA-like thermal maps. This provides real-time, intuitive insight into thermal behavior and stress concentration. By replacing slow simulations with fast ML predictions and images, the framework supports continuous reliability monitoring.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Rahangdale et al. (2026) studied this question.

synapsesocial.com/papers/6996a957ecb39a600b3f05fbhttps://doi.org/10.1115/1.4071142
Ask AI
Helpful
Bookmark
Share
View Full Paper