Application of artificial intelligence to the optimal operation of thermoelectric cooling systems
碩士 === 國立臺灣科技大學 === 機械工程系 === 87 === A Thermoelectric(TE) cooling system, which was comprised of several TE modules, was designed and investigated in the present study. When a DC current passes through the junction of a TE couple, one side of the junction will become cold while the other...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
1999
|
Online Access: | http://ndltd.ncl.edu.tw/handle/99325407340658004522 |
id |
ndltd-TW-087NTUST489058 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-087NTUST4890582016-02-01T04:12:44Z http://ndltd.ncl.edu.tw/handle/99325407340658004522 Application of artificial intelligence to the optimal operation of thermoelectric cooling systems 以人工智慧優化熱電冷卻空調系統 Lin Chia-te 林佳德 碩士 國立臺灣科技大學 機械工程系 87 A Thermoelectric(TE) cooling system, which was comprised of several TE modules, was designed and investigated in the present study. When a DC current passes through the junction of a TE couple, one side of the junction will become cold while the other side hot. This is how a TE cooler works. When a TE cooling system operating between two flowing fluids reaches a certain length, the temperature of the cold fluid will not drop but increase with distance. This is because the conduction loss is greater than the Seebeck cooling effect of the TE couple when the temperature difference across the TE couple is large. The objective of the present study is to investigate the feasibility of using variable electric currents to optimize the performance of a TE cooling system operating between two flowing fluids. Artificial intelligence(AI) techniques were employed to determine the optimal current distribution for maximum efficiency and/or minimum refrigeration temperature. Experiments were also carried out to verify the theoretical results. In the experiments 8 TE modules were connected in series. Genetic algorithm(GA) and simulated annealing(SA) were used for optimizing the current distributions for both parallel-flow and counter-flow arrangements. It was found that the coefficient of performance(COP) of the parallel-flow arrangement could be increased by as much as 70 % and the exit temperature of the cold fluid could be lowered by 3 degrees Celsius when the current distribution was optimized using AI techniques. The theoretical and experimental results of the present investigation indicate the necessity of optimizing TE cooler operation if good system performance is desired. We hope this study will stimulate more research on TE coolers, and lead to TE cooling applications beyond the military and high-tech areas. Kuan Chen 陳 冠 1999 學位論文 ; thesis 120 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立臺灣科技大學 === 機械工程系 === 87 === A Thermoelectric(TE) cooling system, which was comprised of several TE modules, was designed and investigated in the present study. When a DC current passes through the junction of a TE couple, one side of the junction will become cold while the other side hot. This is how a TE cooler works. When a TE cooling system operating between two flowing fluids reaches a certain length, the temperature of the cold fluid will not drop but increase with distance. This is because the conduction loss is greater than the Seebeck cooling effect of the TE couple when the temperature difference across the TE couple is large. The objective of the present study is to investigate the feasibility of using variable electric currents to optimize the performance of a TE cooling system operating between two flowing fluids. Artificial intelligence(AI) techniques were employed to determine the optimal current distribution for maximum efficiency and/or minimum refrigeration temperature. Experiments were also carried out to verify the theoretical results. In the experiments 8 TE modules were connected in series. Genetic algorithm(GA) and simulated annealing(SA) were used for optimizing the current distributions for both parallel-flow and counter-flow arrangements.
It was found that the coefficient of performance(COP) of the parallel-flow arrangement could be increased by as much as 70 % and the exit temperature of the cold fluid could be lowered by 3 degrees Celsius when the current distribution was optimized using AI techniques. The theoretical and experimental results of the present investigation indicate the necessity of optimizing TE cooler operation if good system performance is desired. We hope this study will stimulate more research on TE coolers, and lead to TE cooling applications beyond the military and high-tech areas.
|
author2 |
Kuan Chen |
author_facet |
Kuan Chen Lin Chia-te 林佳德 |
author |
Lin Chia-te 林佳德 |
spellingShingle |
Lin Chia-te 林佳德 Application of artificial intelligence to the optimal operation of thermoelectric cooling systems |
author_sort |
Lin Chia-te |
title |
Application of artificial intelligence to the optimal operation of thermoelectric cooling systems |
title_short |
Application of artificial intelligence to the optimal operation of thermoelectric cooling systems |
title_full |
Application of artificial intelligence to the optimal operation of thermoelectric cooling systems |
title_fullStr |
Application of artificial intelligence to the optimal operation of thermoelectric cooling systems |
title_full_unstemmed |
Application of artificial intelligence to the optimal operation of thermoelectric cooling systems |
title_sort |
application of artificial intelligence to the optimal operation of thermoelectric cooling systems |
publishDate |
1999 |
url |
http://ndltd.ncl.edu.tw/handle/99325407340658004522 |
work_keys_str_mv |
AT linchiate applicationofartificialintelligencetotheoptimaloperationofthermoelectriccoolingsystems AT línjiādé applicationofartificialintelligencetotheoptimaloperationofthermoelectriccoolingsystems AT linchiate yǐréngōngzhìhuìyōuhuàrèdiànlěngquèkōngdiàoxìtǒng AT línjiādé yǐréngōngzhìhuìyōuhuàrèdiànlěngquèkōngdiàoxìtǒng |
_version_ |
1718175085685112832 |