TSV Extrusion Morphology Classification Using Deep Convolutional Neural Networks

TL;DR

This paper presents a deep learning approach using CNNs to classify TSV extrusion morphologies in 3D ICs, achieving accuracy comparable to human experts by leveraging surface profile data from white light interferometry.

Contribution

It introduces a novel dataset and CNN-based classification method for TSV extrusion morphologies, improving reliability assessment in 3D integrated circuits.

Findings

CNN models achieved high classification accuracy

Data augmentation and dropout improved model performance

Automated classification matches human expert accuracy

Abstract

In this paper, we utilize deep convolutional neural networks (CNNs) to classify the morphology of through-silicon via (TSV) extrusion in three dimensional (3D) integrated circuits (ICs). TSV extrusion is a crucial reliability concern which can deform and crack interconnect layers in 3D ICs and cause device failures. Herein, the white light interferometry (WLI) technique is used to obtain the surface profile of the extruded TSVs. We have developed a program that uses raw data obtained from WLI to create a TSV extrusion morphology dataset, including TSV images with 54x54 pixels that are labeled and categorized into three morphology classes. Four CNN architectures with different network complexities are implemented and trained for TSV extrusion morphology classification application. Data augmentation and dropout approaches are utilized to realize a balance between overfitting and underfitting in the CNN models. Results obtained show that the CNN model with optimized complexity, dropout, and data augmentation can achieve a classification accuracy comparable to that of a human expert.