DLAG-TA: Deep Learning-Based Adaptive Grid Builder for System-Level Thermal Analysis

Wen Sheng Lo, Hong Wen Chiou, Shih Chieh Hsu, Yu Min Lee

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This work develops an adaptive grid builder for system-level thermal simulators by embedding a well trained deep neural network (DNN) model, and we call it DLAG-TA. To automatically generate adaptive grids for various sizes/structures of handheld devices, it also contains a parameter scaling procedure and a virtual block to element grid mapping procedure to assist the trained DNN model. The results show that DLAG-TA can effectively build grids with high quality.

Original languageEnglish
Title of host publicationProceedings of the 20th InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems, ITherm 2021
PublisherIEEE Computer Society
Pages477-483
Number of pages7
ISBN (Electronic)9781728185392
DOIs
StatePublished - 2021
Event20th InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems, ITherm 2021 - Virtual, San Diego, United States
Duration: 1 Jun 20214 Jun 2021

Publication series

NameInterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems, ITHERM
Volume2021-June
ISSN (Print)1936-3958

Conference

Conference20th InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems, ITherm 2021
Country/TerritoryUnited States
CityVirtual, San Diego
Period1/06/214/06/21

Keywords

  • Adaptive grid
  • Deep learning
  • System-level thermal analysis

Fingerprint

Dive into the research topics of 'DLAG-TA: Deep Learning-Based Adaptive Grid Builder for System-Level Thermal Analysis'. Together they form a unique fingerprint.

Cite this