Ensemble Learning for Predicting Temperature of Heat Sources for Minimizing Electronic Failures

Durgam, Shankar; Bhosale, Ajinkya; Bhosale, Vivek; Deshpande, Revati; Sutar, Pankaj; Kamble, Subodha

doi:10.1109/icnte51185.2021.9487663

Cited by 2 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They proposed artificial neural network as alternative tool to CFD. Durgam et al [13,14,15,16] have used machine learning algorithms viz. support vector regression, XG Boost, random forest regression, and artificial neural network as an alternative to simulation software for cooling of heaters with dummy components on PCB under forced convection.…”

Section: Introductionmentioning

confidence: 99%

Computational cooling performance of electronic chips on printed circuit boards

Durgam¹

2022

J. Phys.: Conf. Ser.

Self Cite

View full text Add to dashboard Cite

Effect of cooling performance of heated modules resembling integrated circuit (IC) chips on printed circuit boards (PCBs) under natural and forced convection is investigated. Commercially available four different types of substrate materials viz. silica glass, glass epoxy FR4, bakelite, and copper-clad board (CCB) is used for the simulation study. Natural and forced convection cooling scenarios are used for thermal performance with a power input of 7.5 W and 15 W for heaters equipped on a substrate. The main motive of this work is to present and compare thermal performance of heated modules on different substrate materials. Results of FR4 and bakelite with a power input of 7.5 under natural convection are compared with forced convection results at Re = 500 for the same power input. The results show that copper clad boards give a better cooling performance in natural convection scenarios for both the power inputs of 7.5 W and 15 W.

show abstract

Section: Introductionmentioning

confidence: 99%