Predicting thermal–hydraulic performances in compact heat exchangers by support vector regression

Peng, Hao; Ling, Xiang

doi:10.1016/j.ijheatmasstransfer.2015.01.017

Cited by 43 publications

(19 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fully connected ANN [5][6][7][8][9][10] [11] SVR, RBNN, Kriging [9] [ 12,13] CFD models are increasingly being used for predictive design, even in critical applications such as nuclear reactor thermal-hydraulics [14], provided that rigorous verification and validation practices are adhered to. In the context of fin-tube bundles, CFD models can provide heat transfer and pressure drop coefficients in a consistent and time efficient manner.…”

Section: Data Source Experimental Correlation or Cfdmentioning

confidence: 99%

A Machine Learning Approach to Correlation Development Applied to Fin-Tube Bundle Heat Exchangers

et al. 2018

View full text Add to dashboard Cite

Heat exchanger designers need reliable thermal-hydraulic correlations to optimize heat exchanger designs. This work combines an adaptive sampling method with a Computational Fluid Dynamics (CFD) simulator to obtain increased accuracy and validity range of heat transfer and pressure drop predictions using a limited number of data points. Correlation efficacy was evaluated based on a steam generator case study. The sensitivity to the design parameters was analyzed in detail. The RMSE (root mean square error) of the developed correlations were reduced, through CFD sampling, from 28% to 15% for pressure drop, and from 33% to 25% heat transfer, compared to regression on experimental data only. The best reference correlations have RMSE values of 43% and 33% on pressure drop and heat transfer, respectively, on an independent validation set. Indeed, a radically different fin-tube geometry was suggested for the case study, compared to results using the Escoa correlations.The developed correlations show good to excellent agreement with trends in the CFD model. The quantitative error of predicted heat transfer and pressure drop coefficients at the case study optimum, however, was as large as those of the Escoa correlations. More data are likely needed to improve accuracy for compact heat exchanger designs further.

show abstract

Section: Data Source Experimental Correlation or Cfdmentioning

confidence: 99%

A Machine Learning Approach to Correlation Development Applied to Fin-Tube Bundle Heat Exchangers

et al. 2018

View full text Add to dashboard Cite

show abstract

“…The Li and Wu correlation [26] was developed for water, refrigerants, ethanol, propane, and CO 2 . It is given below (d h = 0.16-3.1 mm).…”

Section: And Wu Correlationmentioning

confidence: 99%

“…This results in overtraining, i.e., high accuracy for the training dataset and low for test data, giving poor generalization performance [12,20]. Furthermore, none of the existing correlations (namely Piasecka [24], Dutkowski [24,25], and Li and Wu [26]) predict the heat transfer coefficient of R600a accurately. This might be due to the fact that these correlations have been developed for different refrigerants with different flow conditions.…”

Section: Comparative Studymentioning

confidence: 99%

Development and Analyses of Artificial Intelligence (AI)-Based Models for the Flow Boiling Heat Transfer Coefficient of R600a in a Mini-Channel

Parveen¹,

Zaidi²,

Danish³

2018

ChemEngineering

View full text Add to dashboard Cite

Environmental friendly refrigerants with zero ozone depletion potential (ODP) and zero global warming potential (GWP) are in great demand across the globe. One such popular refrigerant is isobutane (R600a) which, having zero ODP and negligible GWP, is considered in this study. This paper presents the two most popular artificial intelligence (AI) techniques, namely support vector regression (SVR) and artificial neural networks (ANN), to predict the heat transfer coefficient of refrigerant R600a. The independent input parameters of the models include mass flux, saturation temperature, heat flux, and vapor fraction. The heat transfer coefficient of R600a is the dependent output parameter. The prediction performance of these AI-based models is compared and validated against the experimental results, as well as with the existing correlations based on the statistical parameters. The SVR model based on the structural risk minimization (SRM) principle is observed to be superior compared with the other models and is more accurate, precise, and highly generalized; it has the lowest average absolute relative error (AARE) at 1.15% and the highest coefficient of determination (R 2) at 0.9981. ANN gives an AARE of 5.14% and a R 2 value of 0.9685. Furthermore, the simulated results accurately predict the effect of input parameters on the heat transfer coefficient.

show abstract

“…Recently, the thermo-hydraulic performance of a compact fin and tube heat exchanger with different tube configurations [17] and Titanium brazed plate fin heat exchanger [18] were analysed. Also, the researchers attempted to enhance the performance of compact heat exchanger through evaporation cooling and predicted the thermo-hydraulic performance by an artificial neural network model [19].…”

Section: Introductionmentioning

confidence: 99%

Fanning friction (f) and colburn (j) factors of a louvered fin and flat tube compact heat exchanger

Periyasamy¹,

Kumaresan

Velraj

2017

THERM SCI

View full text Add to dashboard Cite

In the present study, the heat transfer and pressure drop characteristics of air over the louvered fins in a compact heat exchanger, used as a radiator in the automobiles have been experimentally investigated. The experiments were conducted at various flow rates of air and the results showed a decrease in goodness factor of 22.7% with respect to increase in Reynolds number from 231 to 495. The experimental results were compared with the CFD results and the f and j factors from the CFD analysis are in good agreement with the experimental data. Also, the experimental f and j factors were compared with the predicted values from the available correlations in the literature for the louvered fin and tube compact heat exchangers. The large deviation of the predicted results revealed that the correlations are not reliable for the design of the compact heat exchanger. Hence, the CFD analysis is more advantageous for the optimal design of compact heat exchanger, which also reduces the experimentation time and cost.

show abstract

Predicting thermal–hydraulic performances in compact heat exchangers by support vector regression

Cited by 43 publications

References 35 publications

A Machine Learning Approach to Correlation Development Applied to Fin-Tube Bundle Heat Exchangers

A Machine Learning Approach to Correlation Development Applied to Fin-Tube Bundle Heat Exchangers

Development and Analyses of Artificial Intelligence (AI)-Based Models for the Flow Boiling Heat Transfer Coefficient of R600a in a Mini-Channel

Fanning friction (f) and colburn (j) factors of a louvered fin and flat tube compact heat exchanger

Contact Info

Product

Resources

About