Page 14 - IJAMD-2-1

International Journal of AI for
Materials and Design

ORIGINAL RESEARCH ARTICLE
Predicting effective thermal conductivity of

sintered nano-Ag with artificial neural networks

Libo Zhao , Jiahui Wei , Yanwei Dai * , Daowei Wu 2 , Yuting Zhang 2 ,
1†
1†
1
Kui Li 3 , and Fei Qin 1
1 Department of Mechanics, Institute of Electronics Packaging Technology and Reliability, Beijing
University of Technology, Beijing, China
2 Advanced Packaging Division, Xi’an Institute of Microelectronics Technology, Xi’an, Shaanxi, China
3 R&d Innovation Center, Xi’an Institute of Microelectronics Technology, Xi’an, Shaanxi, China
(This article belongs to the Special Issue: AI for Multiscale Analysis and Defect Identification in
Packaging Structures and Semiconductor Chips)

Abstract

Due to the demand for high reliability and thermal conductivity of high-power
modules operating at high temperatures, sintered nano-silver (Ag) has garnered
significant attention as an excellent interconnect and heat transfer layer, particularly
† These authors contributed equally for its thermal conductivity and other reliability research. Since the mechanical
to this paper. behavior and heat conduction capacity of sintered Ag is generally regulated by
*Corresponding author: changes in temperature, its microstructure will change accordingly, affecting its
Yanwei Dai performance. In this study, a machine learning model was used to evaluate and
(ywdai@bjut.edu.cn) predict the thermal conductivity of sintered Ag, providing an effective method to
Citation: Zhao L, Wei J, Dai Y, analyze the influence of microstructural characteristics on its heat transfer properties.
et al. Predicting effective thermal Image processing and model simulation of scanning electron microscopy images of
conductivity of sintered nano-Ag sintered nano-Ag nanostructures were performed using MATLAB and Ansys software.
with artificial neural networks. Int J
AI Mater Design. 2025;2(1):8-20. A batch calculation of the thermal conductivity of 2D images of sintered nano-Ag
doi: 10.36922/ijamd.5744 nanostructures was performed to obtain sufficient data sets. Based on the artificial
Received: November 1, 2024 neural network model of Bayesian optimization, the equivalent thermal conductivity
of different sintered nano-Ag microstructures was predicted with high accuracy using
1st revised: December 10, 2024
the microstructure image and characteristic parameters of sintered nano-Ag. The
2nd revised: December 19, 2024 proposed method enables rapid, effective, and accurate evaluation and prediction
3rd revised: January 13, 2025 of the thermal conductivity of sintered nano-Ag, contributing significantly to the
reliability of power modules.
Accepted: January 15, 2025
Published online: February 6, 2025
Keywords: Artificial neural networks; Sintered nano-Ag; Effective thermal conductivity;
Copyright: © 2025 Author(s). Finite element modeling
This is an Open-Access article
distributed under the terms of the
Creative Commons Attribution
License, permitting distribution,
and reproduction in any medium, 1. Introduction
provided the original work is
properly cited. Silicon carbide (SiC)-based power devices face limitations in achieving more effective
Publisher’s Note: AccScience energy conversion. To address the high reliability and thermal conduction demands
Publishing remains neutral with of power modules operating at high temperatures, sintered nano-silver (Ag) has been
regard to jurisdictional claims in
published maps and institutional developed and utilized frequently as the die-attaching material for SiC devices, due to its
affiliations. excellent performance in heat transfer and chip joining.

Volume 2 Issue 1 (2025) 8 doi: 10.36922/ijamd.5744