This paper presents a 3-input and a 4-input Artificial Neural Network (ANN) model for the prediction of the thermal conductivity of oxide–water nanofluids. Both models account for the effect of temperature, nanoparticle volume fraction, and nanoparticle thermal conductivity, whereas the 4-input model also considers the effect of nanoparticle cluster average size. The models have been trained on a set of data obtained by the present authors and tested both with cross-validation and on data coming from other authors. Both models show a reasonable agreement in predicting experimental data, even if the 4-input model exhibits better performance. The inclusion of the cluster average size within the input variables improves the predicting performance of the ANN nanofluid thermal conductivity model; however, this parameter is usually missing from data presented in literature. The characteristic parameters of the presented ANN models are fully reported in the paper.

Application of artificial neural network (ANN) for the prediction of thermal conductivity of oxide–water nanofluids

LONGO, GIOVANNI ANTONIO;ZILIO, CLAUDIO;REGGIANI, MONICA
2012

Abstract

This paper presents a 3-input and a 4-input Artificial Neural Network (ANN) model for the prediction of the thermal conductivity of oxide–water nanofluids. Both models account for the effect of temperature, nanoparticle volume fraction, and nanoparticle thermal conductivity, whereas the 4-input model also considers the effect of nanoparticle cluster average size. The models have been trained on a set of data obtained by the present authors and tested both with cross-validation and on data coming from other authors. Both models show a reasonable agreement in predicting experimental data, even if the 4-input model exhibits better performance. The inclusion of the cluster average size within the input variables improves the predicting performance of the ANN nanofluid thermal conductivity model; however, this parameter is usually missing from data presented in literature. The characteristic parameters of the presented ANN models are fully reported in the paper.
2012
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11577/2476687
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 128
  • ???jsp.display-item.citation.isi??? 120
  • OpenAlex ND
social impact