Abstract
Implementation of radial basis neural network is demonstrated by considering a test case of non-Newtonian third-grade fluid flow and heat transfer through two parallel plates. Five commonly used stochastic optimization methods: genetic algorithm, global search algorithm, multiple starting point algorithm, simulated annealing algorithm, and pattern search algorithm, are employed to optimize the RBNN. Flow of a non-Newtonian third-grade fluid through two parallel plates, subjected to uniform heat flux, is considered. At first, governing equations, describing the flow and heat transfer problem, are solved by the least-square method, a semi-analytical tool. The velocity and the temperature profiles are obtained for different values of third-grade fluid parameter ‘A’, which are then used for training different stochastic optimization method-assisted RBNNs (SOMARBNNs). For proper functioning of RBNN, a suitable value for an important attribute called ‘spread’ is required. Deciding the value for ‘spread’ requires experience and knowledge of neural networks. The present approach makes the selection of proper value of ‘spread’ very easy, and beginners can use the RBNN for problem-solving. With the help of different stochastic optimization methods, the value of spread for the RBNN is determined. Once all SOMARBNNs are trained, the temperature profile and the corresponding third-grade fluid parameter ‘A’ are obtained as output, corresponding to any new velocity profile fed as input. Further, the data for training are perturbed by different levels of noise, and different SOMARBNNs are successfully employed to get the output. The performance evaluation of different SOMARBNNs is carried out in terms of CPU time and error in result. The results indicate that PSAARBNN is better than other SOMARBNNs, as it is able to generate results with high accuracy for both low noise data and high noise data. Moreover, the CPU time requirement by PSAARBNN is lowest.
Similar content being viewed by others
Abbreviations
- \(A\) :
-
Third-grade fluid parameter
- \(Ac\) :
-
Cross-sectional area [m2]
- \(A_{1} ,\,A_{2} ,\,A_{3} ,...A_{n}\) :
-
Kinematic tensor
- \(a_{0} ,\,a_{2} ,\,a_{4} ,\,a_{6} ,a_{8}\) :
-
Constants
- \(an\) :
-
Layer output vector in RBNN
- \(Br\) :
-
Brinkman number
- \(\begin{gathered} b_{0} ,\,b_{2} ,\,b_{4} ,\, \hfill \\ b_{6} ,\,b_{8} ,\,b_{10} ,\,b_{12} \hfill \\ \end{gathered}\) :
-
Constants
- bn:
-
Bias in RBNN
- \(C_{P}\) :
-
Specific heat at constant pressure [J/kg.K]
- \(c_{1} ,\,c_{2} ,...\,\) :
-
Constants
- \(c_{i}\) :
-
Ith constant
- \(D\) :
-
Differential operator
- D/Dt :
-
Material derivative
- \(f\) :
-
Body force per unit volume
- \(g\) :
-
Function
- \(h\) :
-
Half depth of channel [m]
- \(IWn^{1}\) :
-
Hidden layer weight matrix in RBNN
- \(k_{th}\) :
-
Thermal conductivity of the fluid [W/m K]
- \(L\) :
-
Length of the channel [m]
- \(LWn^{2}\) :
-
Output layer weight matrix in RBNN
- \(l_{1} ,\,l_{2}\) :
-
Constants
- \(N\) :
-
Non-dimensional pressure gradient
- \(Nu\) :
-
Nusselt number
- \(p^{*}\) :
-
Dimensional pressure [N/m2]
- \(q\) :
-
Heat flux ratio
- \(q_{1} ,\,q_{2}\) :
-
Heat fluxes at lower and upper walls [W/m2]
- \(R\) :
-
Residual
- \(Rn\) :
-
Number of observation points along y* direction (= 201)
- \(S\) :
-
Sum of square of residual
- \(sn\) :
-
Size of matrix in RANN
- \(T^{*}\) :
-
Dimensional temperature [K]
- \(T_{m}^{*}\) :
-
Bulk mean temperature [K]
- \(T_{{w_{l} }}^{*}\) :
-
Temperature of the lower wall [K]
- \(u\) :
-
Non-dimensional velocity along axial direction
- \(u_{N}\) :
-
Non-dimensional velocity for Newtonian fluid
- \(u^{*}\) :
-
Dimensional velocity along axial direction [m/s]
- \(u_{0}\) :
-
Average velocity [m/s]
- \(V^{*}\) :
-
Velocity vector [m/s]
- \(v,\,\tilde{v}\) :
-
Functions [m/s]
- \(x,\,y,\,z\) :
-
Non-dimensional coordinate
- \(x*,\,y*,\,z*\) :
-
Dimensional coordinates [m]
- \(Xn_{o} ,\;Xn_{1}\) :
-
Central point in PSA indifferent iterations
- \(xn_{i}\) :
-
Neuron input
- \(w_{i}\) :
-
Ith weight function
- \(Wn_{i}\) :
-
Neuron weight
- mse:
-
Mean squared error
- ANN:
-
Artificial neural network
- RBNN:
-
Radial basis neural network
- GA:
-
Genetic algorithm
- GAARBNN:
-
Genetic algorithm-assisted RBNN
- GSA:
-
Global search algorithm
- GSAARBNN:
-
Global search algorithm-assisted RBNN
- MSPA:
-
Multiple starting point algorithm
- MSPAARBNN:
-
Multiple starting point algorithm-assisted RBNN
- OF :
-
Objective function
- SAA:
-
Simulated annealing algorithm
- SAAARBNN:
-
Simulated annealing algorithm-assisted RBNN
- PSA:
-
Pattern search algorithm
- PSAARBNN:
-
Pattern search algorithm-assisted RBNN
- SOM:
-
Stochastic optimization method
- SOMARBNN:
-
Stochastic optimization method-assisted radial basis neural network
- TGF:
-
Third-grade fluid
- \(\alpha_{1} ,\,\alpha_{2}\) :
-
Material constants
- \(\beta\) :
-
Constant
- \(\beta_{1,\,} \,\beta_{2,\,} \,\beta_{3,\,} ...\) :
-
Material constants
- \(\rho\) :
-
Density of the fluid [kg/m3]
- \(\mu\) :
-
Dynamic viscosity of the fluid [N s/m2]
- \(\theta\) :
-
Non-dimensional temperature
- \(\theta_{N}\) :
-
Non-dimensional temperature for Newtonian fluid
- \(\tilde{\theta }\) :
-
Temperature obtained from SOMARBNNs
- Φi:
-
Base function
- τ:
-
Stress
- 1, 2:
-
Hidden layer and output layer variables
References
Mai-Duy, N.; Tanner, R.I.: Computing non-Newtonian fluid flow with radial basis function networks. Int. J. Numer. Methods Fluids. 48, 1309–1336 (2005)
Esfe, M.H.: Designing an artificial neural network using radial basis function (RBF-ANN) to model thermal conductivity of ethylene glycol–water-based TiO2 nanofluids. J Therm Anal Calorim. 127(3), 2125–2131 (2017)
Abualigah, L.; Diabat, A.: A novel hybrid antlion optimization algorithm for multi-objective task scheduling problems in cloud computing environments. Clust. Comput. 24, 205–223 (2021)
Abualigah, L.; Diabat, A.; Mirjalili, S.; Elaziz, M.A.; Gandomi, A.H.: The arithmetic optimization algorithm. Comput. Methods Appl. Mech. Eng. (2021). https://doi.org/10.1016/j.cma.2020.113609
Karimi, H.; Yousefi, F.; Rahimi, M.R.: Correlation of viscosity in nanofluids using genetic algorithm-neural network (GA-NN). Heat Mass Transf. 47, 1417–1425 (2011)
Li, S.J.; Liu, Y.X.; He, X.; Liu, Y.J.: Global search algorithm of minimum safety factor for slope stability analysis based on annealing simulation. Chinese J. Rock Mech. Eng. 22(2), 236–240 (2003)
Miri, T.; Tsoukalas, A.; Bakalis, S.; Pistikopoulos, E.N.; Rustem, B.; Fryer, P.J.: Global optimization of process conditions in batch thermal sterilization of food. J. Food Eng. 87, 485–494 (2008)
Saruhan, H.: Designing optimum oil thickness in artificial human knee joint by simulated annealing. Math. and Comp. Applic. 14(12), 109–117 (2009)
Torczon, V.: On the convergence of pattern search algorithms. SIAM J. Optim. 7, 1–25 (1997)
Mishra, V.K.; Mishra, S.C.; Basu, D.N.: Simultaneous estimation of four parameters in a combined mode heat transfer in a 2-D rectangular porous matrix with heat generation. Numerical Heat Transfer- A. 71(6), 677–692 (2017)
Mishra, V.K.; Mishra, S.C.; Basu, D.N.: Simultaneous estimation of properties in a combined mode conduction-radiation heat transfer in a porous medium. Heat Transf. Asian Res 45(8), 699–713 (2016)
Mulani, U.K.; Talukdar, P.; Das, A.; Alagirusamy, R.: Performance analysis and feasibility study of ant colony optimization, particle swarm optimization and cuckoo search algorithms for inverse heat transfer problems. Int. J. Heat Mass Transf. 89, 359–378 (2015)
Inaba, H.; Zhang, Y.; Horibe, A.; Haruki, N.: Numerical simulation of natural convection of latent heat phasechange-material microcapsulate slurry packed in a horizontal rectangular enclosure heated from below and cooled from above. Heat Mass Transfer. 43, 459–470 (2017)
Subba Rao, A.; Ramachandra Prasad, V.; Rajendra, P.; Sasikala, M.; Anwar Beg, O.: Numerical study of non-Newtonian polymeric boundary layer flow and heat transfer from a permeable horizontal isothermal cylinder. Front. Heat Mass Transfer. 9, 2 (2017)
Lim, H.; Back, S.M.; Hwang, M.H.; Lee, D.H.; Choi, H.; Nam, J.: Sheathless high-throughput circulating tumor cell separation using viscoelastic non-Newtonian fluid. Micromachines (Basel). 10, 462 (2019)
Glinski, G.P.; Bailey, C.; Pericleous, K.A.: A non Newtonian of the stencil printing process. Proc. Inst. Mech. Eng. 215(C4), 437–446 (2001)
Chaudhuri, S.; Das, P.K.: Semi-analytical solution of the heat transfer including viscous dissipation in the steady flow of a Sisko fuid in cylindrical tubes. J. Heat Transf (ASME). 140, 071701 (2018)
Kalani, H.; Sardarabadi, M.; Passandideh-Fard, M.: Using artificial neural network models and particle swarm optimization for manner prediction of a photovoltaic thermal nanofluid based collector. Appl. Therm. Eng. 113, 1170–1177 (2017)
Esfe, M.H.: Designing a neural network for predicting the heat transfer and pressure drop characteristics of Ag/water nanofluids in a heat exchanger. Appl. Therm. Eng. 126, 559–565 (2017)
Daneshfar, R.; Bemani, A.; Hadipoor, M.; Sharifpur, M.; Ali, H.M.; Mahariq, I.; Abdeljawad, T.: Estimating the heat capacity of non-Newtonian ionanofluid systems using ANN, ANFIS, and SGB tree algorithms. Appl. Sci. 10, 6432 (2020)
Esfe, M.H.: Designing an artificial neural network using radial basis function (RBF-ANN) to model thermal conductivity of ethylene glycol–water-based TiO2 nanofluids. J. Therm. Anal. Calorim. 127, 2125–2131 (2017). https://doi.org/10.1007/s10973-016-5725-y
Chhantyal, K.; Viumdal, H.; Mylvaganam, S.; Elseth, G.: Ultrasonic level sensors for flowmetering of non-Newtonian fluids in open Venturi channels: using data fusion based on artificial neural network and support vector machines. IEEE Sensors Applications Symposium (SAS), Catania. 1–6 (2016), https://doi.org/10.1109/SAS.2016.7479829
Eshgarf, H.; Sina, N.; Esfe, M.H., et al.: Prediction of rheological behavior of MWCNTs–SiO2/EG–water non-Newtonian hybrid nanofluid by designing new correlations and optimal artificial neural networks. J Therm Anal Calorim. 132, 1029–1038 (2018). https://doi.org/10.1007/s10973-017-6895-y
Wu, H.; Bagherzadeh, S.A.; D’Orazio, A.; Habibollahi, N.; Karimipour, A.; Goodarzi, M.; Bach, Q.-V.: Present a new multi objective optimization statistical Pareto frontier method composed of artificial neural network and multi objective genetic algorithm to improve the pipe flow hydrodynamic and thermal properties such as pressure drop and heat transfer coefficient for non-Newtonian binary fluids. Phys. Stat. Mech. Appl. 535, 122409 (2019)
Zhang, S.; Ge, Z.; Fan, X., et al.: Prediction method of thermal conductivity of nanofluids based on radial basis function. J. Therm. Anal. Calorim. 141, 859–880 (2020). https://doi.org/10.1007/s10973-019-09067-x
Mishra, V.K.; Chaudhuri, S.: Genetic algorithm-assisted artificial neural network for retrieval of a parameter in a third grade fluid flow through two parallel and heated plates. Heat Transfer (Wiley). (2020). https://doi.org/10.1002/htj.21970
Amani, M.; Amani, P.; Bahiraei, M., et al.: Prediction of hydrothermal behavior of a non-Newtonian nanofluid in a square channel by modeling of thermophysical properties using neural network. J Therm Anal Calorim. 135, 901–910 (2019). https://doi.org/10.1007/s10973-018-7303-y
Danish, M.; Kumar, S.; Kumar, S.: Exact analytical solutions for the Poiseuille and Couette-Poiseuille flow of third grade fluid between parallel plates. Commun. Non Linear Sci. 17, 1089–1097 (2012)
Balaji, C.: Thermal system design and optimization, 2nd edn. Ane Books Pvt. Ltd., New Delhi (2019)
Zsolt, U.; Lasdon, L.; Plummer, J.; Glover, F.; Kelly, J.; Martí, R.: Scatter Search and Local NLP Solvers: a Multistart Framework for Global Optimization. INFORMS J. Comput. 19(3), 328–340 (2007)
Glover, F.: A template for scatter search and path relinking. In: Hao, J.K.; Lutton, E.; Ronald, E.; Schoenauer, M.; Snyers, D. (Eds.) Artificial Evolution. AE 1997. Lecture Notes in Computer Science. Springer Berlin, Heidelberg (1998). https://doi.org/10.1007/BFb0026589
Zhou, H.; Jiang, Z.; Li, W.; Wang, G.; Tu, Y.: Optimal design for an extruder head runner based on response surface method and simulated annealing algorithm. Int. J. Polym. Sci. 7239618, 10 (2018). https://doi.org/10.1155/2018/7239618
Wu, C.; Wang, S.-S.; Jiang, X.; Li, J.: Thermodynamic analysis and performance optimization of transcritical power cycles using CO2-based binary zeotropic mixtures as working fluids for geothermal power plants. Appl. Therm. Eng. 115, 292–304 (2017)
Bar, N.; Bandyopadhyay, T.K.; Biswas, M.N.; Das, S.K.: Prediction of pressure drop using artificial neural network for non-Newtonian liquid flow through piping components. J. Pet. Sci. E. 71, 187–194 (2010)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Mishra, V.K., Chaudhuri, S. Implementation of Stochastic Optimization Method-Assisted Radial Basis Neural Network for Transport Phenomenon in Non-Newtonian Third-Grade Fluids: Assessment of Five Optimization Tools. Arab J Sci Eng 46, 11797–11818 (2021). https://doi.org/10.1007/s13369-021-05702-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13369-021-05702-8