Signal integrity analysis of chip package based on machine learning

Xiaobang Wu; Daoshuang Geng; Yang Liu; Chi Huang

doi:10.1117/12.3056084

19 December 2024 Signal integrity analysis of chip package based on machine learning

Xiaobang Wu, Daoshuang Geng, Yang Liu, Chi Huang

Author Affiliations +

Proceedings Volume 13444, Fifth International Conference on Mechanical Engineering, Intelligent Manufacturing, and Mechatronics (MEIMM 2024); 1344403 (2024) https://doi.org/10.1117/12.3056084
Event: The 5th International Conference on Mechanical Engineering, Intelligent Manufacturing, and Mechatronics, 2024, Guilin, China

Abstract

A machine learning approach to chip package signal integrity analysis is proposed. Combining the active learning model and the migrate learning model, the paper improves the performance of the simulation algorithm by fine-tuning the pretraining model, analyzes the convergent speed of the different scale models and the epoch needed before and after the freezing of the different learning rates, it is concluded that the convergence rate is the fastest when the labeled data is 80%, and the period of the unfrozen model is shorter than that of the frozen model.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Xiaobang Wu, Daoshuang Geng, Yang Liu, and Chi Huang "Signal integrity analysis of chip package based on machine learning", Proc. SPIE 13444, Fifth International Conference on Mechanical Engineering, Intelligent Manufacturing, and Mechatronics (MEIMM 2024), 1344403 (19 December 2024); https://doi.org/10.1117/12.3056084

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE