Abstract
R22 and R407C mass flow rates through straight and coiled adiabatic capillary tubes are analyzed with three ANN models, i.e., the feed forward network with back propagation (BP) algorithm, GA-BP (genetic algorithm optimized BP network) and PSO-BP (BP algorithm combined with particle swarm optimization). The modelled outputs by these ANN methods are compared with experimental data. The results showed that the predicted mass flow rates with the three models of BP, GA-BP and PSO-BP agree quite well with the experimental data with the mean relative error of 3.82 %, 3.14 % and 2.3 % for R22, and 3.17 %, 2.66 % and 2.46 % for R407C, respectively. PSO-BP network is then employed to predict the coiling effect of capillary tubes on the mass flow rate. It is shown that the mass flow rates with coiled diameter between 0.04 m and 0.6 m are about 4 %–13 % lower than that of the straight capillary tube.
Similar content being viewed by others
Abbreviations
- a :
-
Half width of possible measured value interval
- c 1 :
-
Self-adjustment weight
- c 2 :
-
Social-adjustment weight
- D :
-
Coiled diameter (m)
- d :
-
Inner diameter (mm)
- f :
-
Activation function
- Gbest :
-
Global best position
- k u :
-
Coverage factor for uniform distribution assumption
- L :
-
Length (m)
- m :
-
Mass flow rate (kg h−)
- mxgen :
-
Largest iteration number
- n :
-
Total number of test samples
- P :
-
Pressure (bar)
- Pbest :
-
Particle best position
- r1, r2 :
-
Uniformly (0, 1) distributed pseudorandom numbers
- t :
-
Current iteration number
- T cn :
-
Condensation temperature (°C)
- T e :
-
Evaporation temperature (°C)
- T suc :
-
Suction vapor temperature (°C)
- W :
-
Connection weight
- u′b(m):
-
Relative standard uncertainty of mass flow rate
- u′E(m):
-
Relative expanded uncertainty of mass flow rate
- v :
-
Particle velocity
- V th :
-
Theoretical displacement volume (m3·h−1)
- x :
-
Input of the neuron
- X :
-
Particle position
- y :
-
Output of the neuron
- y p :
-
Predicted output
- α :
-
Learning rate
- θ :
-
Threshold (bias)
- ΔT sub :
-
Degree of inlet subcooling (°C)
- ε :
-
Inertia weight
- λ :
-
Volumetric efficiency of the compressor
- ρ suc :
-
Density of suction vapor (kg m−3)
- cn:
-
Condensation
- e:
-
Evaporation
- ei:
-
Experimental value of a test sample
- i:
-
The neuron number of input layer
- in:
-
Inlet
- j :
-
The neuron number of hidden layer
- k:
-
The neuron number of output layer
- out:
-
Outlet
- pi:
-
Predicted value of a test sample
- sub:
-
Subcooling
- suc:
-
Suction
- I:
-
Total number of output layer neurons
- new:
-
New value
- old:
-
Old value
- ANN:
-
Artificial neural network
- ANFIS:
-
Adaptive neuro-fuzzy inference system
- BP:
-
Back propagation
- Eq.:
-
Equation
- GA:
-
Genetic algorithm
- MAPE:
-
Mean absolute percentage error
- MRE:
-
Mean relative error
- MSE:
-
Mean square error
- PSO:
-
Particle swarm optimization
- RE:
-
Relative error
References
Q. S. Yan, Refrigeration Technology for Air Conditioning, China Architecture and Building Press, Beijing (1997).
P. K. Bansal and G. Wang, Numerical analysis of choked refrigerant flow in adiabatic capillary tubes, Appl. Therm. Eng., 24(5–6) (2004) 851–863.
H. Shokouhmand and M. Zareh, Experimental investigation and numerical simulation of choked refrigerant flow through helical adiabatic capillary tube, Appl. Therm. Eng., 63(1) (2014) 119–128.
S. D. Deodhar, H. B. Kothadia, K. N. Iyer and S. V. Prabhu, Experimental and numerical studies of choked flow through adiabatic and diabatic capillary tubes, Appl. Therm. Eng., 90(5) (2015) 879–894.
C. Z. Wei, Y. T. Lin, C. C. Wang and J. S. Leu, An experimental study of the performance of capillary tubes for R-407C refrigerant, ASHRAE Trans., 105(2) (1999) 634–638.
M. K. Mittal, R. Kumar and A. Gupta, An experimental study of the flow of R-407C in an adiabatic helical capillary tube, Int. J. Refrig., 33(4) (2010) 840–847.
R. R. Bittle, D. A. Wolf and M. B. Pate, Generalized performance prediction method for adiabatic capillary tubes, HVAC&R Res., 4(1) (1998) 27–43.
C. Melo, R. T. S. Ferreira, C. B. Neto, J. M. Concalves and M. M. Mezavila, Experimental analysis of adiabatic capillary tubes, Appl. Therm. Eng., 19(6) (1999) 669–684.
S. G. Kim, S. T. Ro and M. S. Kim, Experimental investigation of the performance of R22, R407C and R410A in several capillary tubes for air-conditioners, Int. J. Refrig., 25(5) (2002) 521–531.
J. Choi, Y. Kim and H. Y. Kim, A generalized correlation for refrigerant mass flow rate through adiabatic capillary tubes, Int. J. Refrig., 26 (2003) 881–888.
M. Kaleem Khan, R. Kumar and P. K. Sahoo, An experimental study of the flow of R-134a inside an adiabatic spirally coiled capillary tube, Int. J. Refrig., 31(6) (2008) 970–978.
W. J. Lee and J. H. Jeong, Evaluation of the constituent correlations for predicting the refrigerant flow characteristics in adiabatic helically coiled capillary tubes, J. Mech. Sci. Technol., 33(5) (2019) 2123–2136.
J. N. Gorasia, N. Dubey and K. K. Jain, Computer-aided design of capillaries of different configurations, ASHRAE Trans., (pt 1) (1991) 132–138.
E. P. Mikol, Adiabatic single and two-phase flow in small bore tubes, ASHRAE J., 57(11) (1963) 75–86.
R. Y. Li, S. Lin, Z. Y. Chen and Z. H. Chen, Metastable flow of R12 through capillary tubes, Int. J. Refrig., 13(3) (1990) 181–186.
O. García-Valladares, Numerical simulation and experimental validation of coiled adiabatic capillary tubes, Appl. Therm. Eng., 27(5–6) (2007) 1062–1071.
C. Park, S. Lee, H. Kang and Y. C. Kim, Experimentation and modeling of refrigerant flow through coiled capillary tubes, Int. J. Refrig., 30(7) (2007) 1168–1175.
S. Chingulpitakab and S. Wongwises, A comparison of flow characteristics of refrigerants flowing through adiabatic straight and helical capillary tubes, Int. Commun. Heat Mass Transf., 38(3) (2011) 398–404.
J. Wang, F. Cao, Z. Z. Wang, Y. Y. Zhao and L. S. Li, Numerical simulation of coiled adiabatic capillary tubes in CO2 transcritical systems with separated flow model including metastable flow, Int. J. Refrig., 35(8) (2012) 2188–2198.
M. Zareh, H. Shokouhmand, M. R. Salimpour and M. Taeibi, Numerical simulation and experimental analysis of refrigerants flow through adiabatic helical capillary tube, Int. J. Refrig., 38 (2014) 299–309.
P. Jadhav, N. Agrawal and O. Patil, Flow characteristics of helical capillary tube for transcritical CO2 refrigerant flow, Energy Procedia, 109 (2017) 431–438.
G. B. Zhou and Y. F. Zhang, Numerical and experimental investigations on the performance of coiled adiabatic capillary tubes, Appl. Therm. Eng., 26(11–12) (2006) 1106–1114.
C. L. Zhang, Generalized correlation of refrigerant mass flow rate through adiabatic capillary tubes using artificial neural network, Int. J. Refrig., 28(4) (2005) 506–514.
V. Vins and V. Vacek, Mass flow rate correlation for two-phase flow of R218 through a capillary tube, Appl. Therm. Eng., 29(14–15) (2009) 2816–2823.
Y. Islamoglu, A. Kurt and C. Parmaksizoglu, Performance prediction for non-adiabatic capillary tube suction line heat exchanger: an artificial neural network approach, Energy Convers. Manage., 46(2) (2005) 223–232.
M. Heimel, W. Lang and R. Almbauer, Performance predictions using artificial neural network for isobutane flow in non-adiabatic capillary tubes, Int. J. Refrig., 38 (2014) 281–289.
J. Gill and J. Singh, Adaptive neuro-fuzzy inference system approach to predict the mass flow rate of R-134a/LPG refrigerant for straight and helical coiled adiabatic capillary tubes in the vapor compression refrigeration system, Int. J. Refrig., 78 (2017) 166–175.
J. Gill and J. Singh, Use of artificial neural network approach for depicting mass flow rate of R134a/LPG refrigerant through straight and helical coiled adiabatic capillary tubes of vapor compression refrigeration system, Int. J. Refrig., 38 (2018) 228–238.
L. I. Díez, C. Cortés, I. Arauzo and A. Valero, Combustion and heat transfer monitoring in large utility boilers, Int. J. Therm. Sci., 40 (2001) 489–496.
J. J. Meyer and W. E. Dunn, New insights into the behavior of the metastable region of an operating capillary tube, HVAC&R Res., 4(1) (1998) 105–115.
Z. H. Zhou, Machine Learning, Tsinghua University Press, Beijing (2016).
Help documentation for Matlab R2017b, The MathWorks, Inc. (2017).
Acknowledgments
This work was supported in part by Scientific Research Foundation for the Returned Overseas Chinese Scholars, State Education Ministry (No. 2012940), China and Beijing Natural Science Foundation (No. 3192034), China.
Author information
Authors and Affiliations
Corresponding author
Additional information
Recommended by Editor Yong Tae Kang
Guobing Zhou is a Professor of the School of Energy, Power and Mechanical Engineering, North China Electric Power University, Beijing, China. He received his Ph.D. in Thermal Engineering from Tianjin University. His research interests include micro-channel flow and heat transfer, HVAC&R, solar thermal storage and applications.
Yuchen Zhou is currently working toward the Bachlor’s degree with the School of Software Engineering, South China University of Technology, Guangzhou, China. Her current research interests include swarm intelligence, machine learning, and natural language processing.
Rights and permissions
About this article
Cite this article
Zhou, G., Zhou, Y. Analysis on mass flow rate of R22 and R407C through coiled adiabatic capillary tubes with GA and PSO optimized BP networks. J Mech Sci Technol 34, 3445–3455 (2020). https://doi.org/10.1007/s12206-020-0737-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12206-020-0737-8