ANN–based prediction of two‐phase gas– liquid flow patterns in a circular conduit

Sharma, Himanshu; Das, Gargi; Samanta, Arghya

doi:10.1002/aic.10922

Cited by 29 publications

(10 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The spread constant is chosen for a network that gives the minimum prediction error in training and test period. Some of the algorithms like genetic algorithm and trial error method are used to find out the optimum spread constant. The spread constant ( σ ) is founded out by using trial and error method in the present study as it involves simple operation process.…”

Section: Resultsmentioning

confidence: 99%

Flow pattern transition, frictional pressure drop, and holdup of gas non‐Newtonian fluid flow in helical tube

Thandlam

Mandal

Majumder

2015

Asia-Pacific J Chem Eng

View full text Add to dashboard Cite

An investigation on flow pattern, pressure drop, and holdup of cocurrent upward two-phase flow in a vertical helical coil tube has been carried out with Newtonian and non-Newtonian fluids. The flow patterns observed in the present study are divided into three main regimes, i.e. plug flow, slug flow, and stratified flow. Lockhart-Martinelli parameter (X) was used to predict the friction factor and frictional pressure drop of two-phase flow. Correlations for the frictional pressure drop were developed to interpret the observed flow patterns with various operating variables. The effect of geometrical parameters on flow pattern, pressure drop, and holdup are enunciated. Based on the experimental data, a correlation was proposed to predict the flow transitions of flow patterns (i.e. plug-slug flow and slug-stratified flow) by dimensional analysis. Probabilistic neural network model has also been developed to predict the flow patterns of two-phase flow. Figure 5. Effect of coil diameter (D c ) on flow regime of non-Newtonian fluids at constant tube diameter d t = 0.015 m, SCMC concentration = 1.0 kg/m 3 and pitch difference (p/D c ) = 1.0. Asia-Pacific Journal of Chemical Engineering FLOW PATTERNS OF GAS NON-NEWTONIAN FLUID FLOW 429 R 2 , correlation coefficient; SE, standard error.Figure 11. Effect of different variables [(a) superficial liquid velocity at d t = 0.02 m; D c = 0.2 m; P/D c = 1.0; SCMC-1.5 kg/m 3 , (b) coil diameter at d t = 0.02 m; P/D c = 0.5; Usl = 1.238 m/s; SCMC-3.0 kg/m 3 , (c) tube diameter at D c = 0.075 m; P/D c = 1.0; SCMC-3.0kg/m 3 and (d) pitch difference at d t = 0.15 m; D c = 0.117 m; SCMC-3.0 kg/m 3 ] on frictional pressure drop.

show abstract

Section: Resultsmentioning

confidence: 99%

Flow pattern transition, frictional pressure drop, and holdup of gas non‐Newtonian fluid flow in helical tube

Thandlam

Mandal

Majumder

2015

Asia-Pacific J Chem Eng

View full text Add to dashboard Cite

show abstract

“…Xie et al 25 classified flow patterns in three-phase gas−liquid−pulp fiber systems using a transportable ANN-based technique by designing a three-layer feed-forward ANN that used seven inputs representing the characteristics of the PSD distribution of normalized pressure fluctuations. Sharma et al 26 attempted to train ANNs to develop an objective flow pattern indicator for air−water flows on the basis of the vast amount of literature data. They investigated three different types of ANN.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Liquid–Liquid Flow Patterns in a Y-Junction Circular Microchannel Using Advanced Neural Network Techniques

Nandagopal

Selvaraju

2016

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

The flow pattern map for a liquid–liquid system in a 600 μm circular microchannel was experimentally investigated for a varying Y-junction confluence angle (10° to 180°). The experimental results showing the distinguishing nature of transition boundaries were established using graphical interpretation. This paper tries to find a better objective flow pattern indicator for vast amounts of experimental data. Studies have been carried out using significant feed-forward back-propagation networks and radial-basis networks such as artificial neural network–pattern recognition (ANN-PR), artificial neural network–function fitting (ANN-FF), cascade-forward network (CFN), probabilistic neural network (PNN), generalized-regression neural network (GRNN), and adaptive neuro-fuzzy inference system (ANFIS). From the study, we found that GRNN showed better prediction ability than the other prediction techniques. Discrete- and continuous-time state-space models for the system were also developed using the system identification technique.

show abstract

“…ANNs have been applied successfully for modeling, pattern recognition, and prediction in engineering systems. Application of these techniques to recognition of two-phase flow patterns have been reported previously [8][9][10][11][12][13][14][15][16].…”

Section: Introductionmentioning

confidence: 99%

ANN‐Based Correlation for Heat Transfer Coefficient of Gas‐Liquid Flow for Different Flow Patterns in Horizontal Pipes

Karimi

Sobhanifar

2015

Heat Trans. Asian Res.

View full text Add to dashboard Cite

Flow patterns and local heat transfer coefficients were measured for air–water flow in a horizontal pipe. A technique based upon a cascade neural network was developed for simultaneously recognition of the flow pattern (FP) and the corresponding heat transfer coefficient (hTP) for each FP. The results show good agreement between the estimated and the experimental values with 98.35% accuracy for FP and 95.6% accuracy for hTP. The results were compared with the Kim and Ghajar heat transfer correlation. The findings revealed that the proposed model is efficient and predicts flow more accurately than the Kim and Ghajar correlation.

show abstract

ANN–based prediction of two‐phase gas– liquid flow patterns in a circular conduit

Cited by 29 publications

References 21 publications

Flow pattern transition, frictional pressure drop, and holdup of gas non‐Newtonian fluid flow in helical tube

Flow pattern transition, frictional pressure drop, and holdup of gas non‐Newtonian fluid flow in helical tube

Prediction of Liquid–Liquid Flow Patterns in a Y-Junction Circular Microchannel Using Advanced Neural Network Techniques

ANN‐Based Correlation for Heat Transfer Coefficient of Gas‐Liquid Flow for Different Flow Patterns in Horizontal Pipes

Contact Info

Product

Resources

About