Thermal-hydraulic performance prediction of two new heat exchangers using RBF based on different DOE

Thermal performance prediction with high precision and low cost is always the need for designers of heat exchangers. Three typical design of experiments (DOE) known as Taguchi design method (TDM), Uniform design method (UDM), and Response surface method (RSM) are commonly used to reduce experimental...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yu Chulin, Wang Youqiang, Zhang Haiqing, Gao Bingjun, He Yin
Formato:	article
Lenguaje:	EN
Publicado:	De Gruyter 2021
Materias:	heat exchanger thermal-hydraulic performance prediction rbf design of experiments Physics QC1-999
Acceso en línea:	https://doaj.org/article/a79bb17e48e7438788d3c7f34766a85f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a79bb17e48e7438788d3c7f34766a85f
record_format	dspace
spelling	oai:doaj.org-article:a79bb17e48e7438788d3c7f34766a85f2021-12-05T14:11:01ZThermal-hydraulic performance prediction of two new heat exchangers using RBF based on different DOE2391-547110.1515/phys-2021-0017https://doaj.org/article/a79bb17e48e7438788d3c7f34766a85f2021-06-01T00:00:00Zhttps://doi.org/10.1515/phys-2021-0017https://doaj.org/toc/2391-5471Thermal performance prediction with high precision and low cost is always the need for designers of heat exchangers. Three typical design of experiments (DOE) known as Taguchi design method (TDM), Uniform design method (UDM), and Response surface method (RSM) are commonly used to reduce experimental cost. The radial basis function artificial neural network (RBF) based on different DOE is used to predict the thermal performance of two new parallel-flow shell and tube heat exchangers. The applicability and expense of ten different prediction methods (RBF + TDML9, RBF + TDML18, RBF + UDM, RBF + TDML9 + UDM, RBF + TDML18 + UDM, RBF + RSM, RBF + RSM + TDML9, RBF + RSM + TDML18, RBF + RSM + UDM, RSM) are discussed. The results show that the RBF + RSM is a very efficient method for the precise prediction of thermal-hydraulic performance: the minimum error is 2.17% for Nu and 5.30% for f. For RBF, it is not true that the more of train data, the more precision of the prediction. The parameter “spread” of RBF should be adjusted to optimize the prediction results. The prediction using RSM only can also obtain a good balance between precision and time cost with a maximum prediction error of 14.52%.Yu ChulinWang YouqiangZhang HaiqingGao BingjunHe YinDe Gruyterarticleheat exchangerthermal-hydraulic performancepredictionrbfdesign of experimentsPhysicsQC1-999ENOpen Physics, Vol 19, Iss 1, Pp 285-304 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	heat exchanger thermal-hydraulic performance prediction rbf design of experiments Physics QC1-999
spellingShingle	heat exchanger thermal-hydraulic performance prediction rbf design of experiments Physics QC1-999 Yu Chulin Wang Youqiang Zhang Haiqing Gao Bingjun He Yin Thermal-hydraulic performance prediction of two new heat exchangers using RBF based on different DOE
description	Thermal performance prediction with high precision and low cost is always the need for designers of heat exchangers. Three typical design of experiments (DOE) known as Taguchi design method (TDM), Uniform design method (UDM), and Response surface method (RSM) are commonly used to reduce experimental cost. The radial basis function artificial neural network (RBF) based on different DOE is used to predict the thermal performance of two new parallel-flow shell and tube heat exchangers. The applicability and expense of ten different prediction methods (RBF + TDML9, RBF + TDML18, RBF + UDM, RBF + TDML9 + UDM, RBF + TDML18 + UDM, RBF + RSM, RBF + RSM + TDML9, RBF + RSM + TDML18, RBF + RSM + UDM, RSM) are discussed. The results show that the RBF + RSM is a very efficient method for the precise prediction of thermal-hydraulic performance: the minimum error is 2.17% for Nu and 5.30% for f. For RBF, it is not true that the more of train data, the more precision of the prediction. The parameter “spread” of RBF should be adjusted to optimize the prediction results. The prediction using RSM only can also obtain a good balance between precision and time cost with a maximum prediction error of 14.52%.
format	article
author	Yu Chulin Wang Youqiang Zhang Haiqing Gao Bingjun He Yin
author_facet	Yu Chulin Wang Youqiang Zhang Haiqing Gao Bingjun He Yin
author_sort	Yu Chulin
title	Thermal-hydraulic performance prediction of two new heat exchangers using RBF based on different DOE
title_short	Thermal-hydraulic performance prediction of two new heat exchangers using RBF based on different DOE
title_full	Thermal-hydraulic performance prediction of two new heat exchangers using RBF based on different DOE
title_fullStr	Thermal-hydraulic performance prediction of two new heat exchangers using RBF based on different DOE
title_full_unstemmed	Thermal-hydraulic performance prediction of two new heat exchangers using RBF based on different DOE
title_sort	thermal-hydraulic performance prediction of two new heat exchangers using rbf based on different doe
publisher	De Gruyter
publishDate	2021
url	https://doaj.org/article/a79bb17e48e7438788d3c7f34766a85f
work_keys_str_mv	AT yuchulin thermalhydraulicperformancepredictionoftwonewheatexchangersusingrbfbasedondifferentdoe AT wangyouqiang thermalhydraulicperformancepredictionoftwonewheatexchangersusingrbfbasedondifferentdoe AT zhanghaiqing thermalhydraulicperformancepredictionoftwonewheatexchangersusingrbfbasedondifferentdoe AT gaobingjun thermalhydraulicperformancepredictionoftwonewheatexchangersusingrbfbasedondifferentdoe AT heyin thermalhydraulicperformancepredictionoftwonewheatexchangersusingrbfbasedondifferentdoe
_version_	1718371491412705280

Thermal-hydraulic performance prediction of two new heat exchangers using RBF based on different DOE

Ejemplares similares