Signal integrity analysis of interconnect systems using neural networks

The simulation and analysis of interconnect systems are becoming challenging and time consuming with the increase in interface speeds. The analysis of the signal and power delivery networks of the complete high-speed links is often performed in time domain using a time-consuming approach of the time marching methods. However, the interconnect systems are accurately characterized in frequency domain. Analyzing interconnect systems in time domain without order reduction results in extreme inefficiency and inaccuracy. Therefore, this thesis discusses an efficient and unsupervised method for reducing the order of interconnect system for subsequent time domain simulation.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Electrical & Computer Engr

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2022

Author dc:creator

• Konduru, Juhitha

Contributors dc:contributor

• Schutt-Ainé, José

• Engineering

Statement dc:rights

• Copyright 2021 Juhitha Konduru

Language dc:language

en, eng

Handle dc:identifier

http://hdl.handle.net/2142/113925

OAI record oai:identifier

https://www.ideals.illinois.edu/oai-pmh?verb=GetRecord&metadataPrefix=etdms&identifier=oai%3Awww.ideals.illinois.edu%3A2142%2F113925