Machine Learning (ML) Based Thermal Management for Cooling of Electronics Chips by Utilizing Thermal Energy Storage (TES) in Packaging That Leverages Phase Change Materials (PCM)

Miniaturization of electronics devices is often limited by the concomitant high heat fluxes (cooling load) and maldistribution of temperature profiles (hot spots). Thermal energy storage (TES) platforms providing supplemental cooling can be a cost-effective solution, that often leverages phase chang...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Aditya Chuttar, Debjyoti Banerjee
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	thermal management electronics cooling thermal energy storage TES duty cycle phase change materials Electronics TK7800-8360
Acceso en línea:	https://doaj.org/article/de7dd1e229db4f9d8cf2b222d93981b6
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:de7dd1e229db4f9d8cf2b222d93981b6
record_format	dspace
spelling	oai:doaj.org-article:de7dd1e229db4f9d8cf2b222d93981b62021-11-25T17:24:37ZMachine Learning (ML) Based Thermal Management for Cooling of Electronics Chips by Utilizing Thermal Energy Storage (TES) in Packaging That Leverages Phase Change Materials (PCM)10.3390/electronics102227852079-9292https://doaj.org/article/de7dd1e229db4f9d8cf2b222d93981b62021-11-01T00:00:00Zhttps://www.mdpi.com/2079-9292/10/22/2785https://doaj.org/toc/2079-9292Miniaturization of electronics devices is often limited by the concomitant high heat fluxes (cooling load) and maldistribution of temperature profiles (hot spots). Thermal energy storage (TES) platforms providing supplemental cooling can be a cost-effective solution, that often leverages phase change materials (PCM). Although salt hydrates provide higher storage capacities and power ratings (as compared to that of the organic PCMs), they suffer from reliability issues (e.g., supercooling). “Cold Finger Technique (CFT)” can obviate supercooling by maintaining a small mass fraction of the PCM in a solid state for enabling spontaneous nucleation. Optimization of CFT necessitates real-time forecasting of the transient values of the melt-fraction. In this study, the artificial neural network (ANN) is explored for real-time prediction of the time remaining to reach a target value of melt-fraction based on the prior history of the spatial distribution of the surface temperature transients. Two different approaches were explored for training the ANN model, using: (1) transient PCM-temperature data; or (2) transient surface-temperature data. When deployed in a heat sink that leverages PCM-based passive thermal management systems for cooling electronic chips and packages, this maverick approach (using the second method) affords cheaper costs, better sustainability, higher reliability, and resilience. The error in prediction varies during the melting process. During the final stages of the melting cycle, the errors in the predicted values are ~5% of the total time-scale of the PCM melting experiments.Aditya ChuttarDebjyoti BanerjeeMDPI AGarticlethermal managementelectronics coolingthermal energy storageTESduty cyclephase change materialsElectronicsTK7800-8360ENElectronics, Vol 10, Iss 2785, p 2785 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	thermal management electronics cooling thermal energy storage TES duty cycle phase change materials Electronics TK7800-8360
spellingShingle	thermal management electronics cooling thermal energy storage TES duty cycle phase change materials Electronics TK7800-8360 Aditya Chuttar Debjyoti Banerjee Machine Learning (ML) Based Thermal Management for Cooling of Electronics Chips by Utilizing Thermal Energy Storage (TES) in Packaging That Leverages Phase Change Materials (PCM)
description	Miniaturization of electronics devices is often limited by the concomitant high heat fluxes (cooling load) and maldistribution of temperature profiles (hot spots). Thermal energy storage (TES) platforms providing supplemental cooling can be a cost-effective solution, that often leverages phase change materials (PCM). Although salt hydrates provide higher storage capacities and power ratings (as compared to that of the organic PCMs), they suffer from reliability issues (e.g., supercooling). “Cold Finger Technique (CFT)” can obviate supercooling by maintaining a small mass fraction of the PCM in a solid state for enabling spontaneous nucleation. Optimization of CFT necessitates real-time forecasting of the transient values of the melt-fraction. In this study, the artificial neural network (ANN) is explored for real-time prediction of the time remaining to reach a target value of melt-fraction based on the prior history of the spatial distribution of the surface temperature transients. Two different approaches were explored for training the ANN model, using: (1) transient PCM-temperature data; or (2) transient surface-temperature data. When deployed in a heat sink that leverages PCM-based passive thermal management systems for cooling electronic chips and packages, this maverick approach (using the second method) affords cheaper costs, better sustainability, higher reliability, and resilience. The error in prediction varies during the melting process. During the final stages of the melting cycle, the errors in the predicted values are ~5% of the total time-scale of the PCM melting experiments.
format	article
author	Aditya Chuttar Debjyoti Banerjee
author_facet	Aditya Chuttar Debjyoti Banerjee
author_sort	Aditya Chuttar
title	Machine Learning (ML) Based Thermal Management for Cooling of Electronics Chips by Utilizing Thermal Energy Storage (TES) in Packaging That Leverages Phase Change Materials (PCM)
title_short	Machine Learning (ML) Based Thermal Management for Cooling of Electronics Chips by Utilizing Thermal Energy Storage (TES) in Packaging That Leverages Phase Change Materials (PCM)
title_full	Machine Learning (ML) Based Thermal Management for Cooling of Electronics Chips by Utilizing Thermal Energy Storage (TES) in Packaging That Leverages Phase Change Materials (PCM)
title_fullStr	Machine Learning (ML) Based Thermal Management for Cooling of Electronics Chips by Utilizing Thermal Energy Storage (TES) in Packaging That Leverages Phase Change Materials (PCM)
title_full_unstemmed	Machine Learning (ML) Based Thermal Management for Cooling of Electronics Chips by Utilizing Thermal Energy Storage (TES) in Packaging That Leverages Phase Change Materials (PCM)
title_sort	machine learning (ml) based thermal management for cooling of electronics chips by utilizing thermal energy storage (tes) in packaging that leverages phase change materials (pcm)
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/de7dd1e229db4f9d8cf2b222d93981b6
work_keys_str_mv	AT adityachuttar machinelearningmlbasedthermalmanagementforcoolingofelectronicschipsbyutilizingthermalenergystoragetesinpackagingthatleveragesphasechangematerialspcm AT debjyotibanerjee machinelearningmlbasedthermalmanagementforcoolingofelectronicschipsbyutilizingthermalenergystoragetesinpackagingthatleveragesphasechangematerialspcm
_version_	1718412440751833088

Machine Learning (ML) Based Thermal Management for Cooling of Electronics Chips by Utilizing Thermal Energy Storage (TES) in Packaging That Leverages Phase Change Materials (PCM)

Ejemplares similares