Parametric trends analysis of the critical heat flux based on artificial neural networks

Predicting the critical heat flux in concentric-tube open thermosiphon: a method based on support vector machine optimized by chaotic particle swarm optimization algorithm

“…The predicted Kutateladze number by 4 prediction models and the relative errors are shown in Figs. 7,8,9,10. Moreover, RMSE and MRE of the training sample and testing sample for these four prediction models are compared, which are shown in Table 5.…”

“…It is worthing to note that Islam et al [5] found that there was an optimum diameter of the inner tube at which the CHF was maximum, and the optimum diameter divided the CHF into two characteristic regions, Region I and Region II, where the CHF in Region I are recommended to predicted by the Correlation (3), and Region II by Correlation (1). Presently, artificial neural networks (ANNs) with strong nonlinear mapping ability are widely accepted as a technology offering an alternative way to solve the complex and ill-defined problems, which have been popularly applied to predict the CHF [7][8][9][10][11][12][13][14][15][16]. Artificial neural networks have been developed into the some different techniques: back propagation neural network (BPNN) [8][9][10][11][12][13][14][15][16], radial basis function neural network (RBFNN) [17][18][19] and general regression neural network (GRNN) [20,21], etc.…”

“…Presently, artificial neural networks (ANNs) with strong nonlinear mapping ability are widely accepted as a technology offering an alternative way to solve the complex and ill-defined problems, which have been popularly applied to predict the CHF [7][8][9][10][11][12][13][14][15][16]. Artificial neural networks have been developed into the some different techniques: back propagation neural network (BPNN) [8][9][10][11][12][13][14][15][16], radial basis function neural network (RBFNN) [17][18][19] and general regression neural network (GRNN) [20,21], etc. And in recent years, a new technique called support vector machine (SVM), developed by Vapnik and his colleague in 1995, has been widely employed in classification, forecasting and regression [22][23][24][25][26][27].…”

CRITICAL HEAT FLUX ENHANCEMENT IN FLOW BOILING OF Al2O3AND SiC NANOFLUIDS UNDER LOW PRESSURE AND LOW FLOW CONDITIONS

“…The pressure among these parameters is known to result in the increase of the CHF, which occurs according to the increase in the pressure [17,18]. Moreover, Moon et al [19] demonstrated that the pressure had an opposite trend for the LPLF conditions; Kim et al [4] revealed that the CHF slowly increased with pressure increases for higher mass fluxes, but that the effect becomes negligible at lower mass fluxes. In the present work, the pressure at the test section exit increased according to the increase of the mass flux, as shown in Fig.…”

Experimental study on critical heat flux characteristics of R134a flow boiling in horizontal helically-coiled tubes

“…Previous work discussed parametric effect on CHF in straight round tubes extensively [2,6,8,33], but discussion in helically coiled tubes was scarce. This paper analyzes the effect of parameters on CHF based on experiments from two aspects, geometrical parameters and system parameters.…”