Heterogenous Package Stress Modeling Using Polynomial Deep Regression with Latin Hypercube Sampling and Factorial Analysis

High stress occurs when 3D heterogeneous IC packages are subjected to thermal cycling at extreme temperatures. Testing and production require simplified but accurate stress prediction tools. This allows engineers with no Finite Element Analysis (FEA) background to perform fast and efficient routine package stresses check for testing/production purpose. To this end, we develop an AI/ ML based stress predictor for heterogeneous packages.