Robust metamodels for accurate quantitative estimation of turbulent flow in pipe bends

Pipe bends are inevitable in industrial piping systems, turbomachinery, heat exchangers, etc. Computational fluid dynamics (CFD), which is commonly employed to understand the flow behavior in such systems has very accurate estimation but is computationally cost intensive. Thus, in this paper, an efficient computational approach for such computationally expensive problems is presented. Using genetic programming (GP), metamodels are built using a small number of samples points from the CFD data. These GP metamodels are then shown to be able to replace the actual CFD models with considerable accuracy. The applicability and suitability of the GP metamodels are validated using a variety of statistical metrics on the training as well as independent test data. It is shown that the use of metamodels leads to significant savings in computational cost.

[1]  John R. Koza,et al.  Genetic Programming II , 1992 .

[2]  Sondipon Adhikari,et al.  A Critical Assessment of Kriging Model Variants for High-Fidelity Uncertainty Quantification in Dynamics of composite Shells , 2016, Archives of Computational Methods in Engineering.

[3]  Mehrshad Mehrpouya,et al.  An investigation on the optimum machinability of NiTi based shape memory alloy , 2017 .

[4]  K. Sudo,et al.  Experimental investigation on turbulent flow in a circular-sectioned 90-degree bend , 1998 .

[5]  Seungjin Kim,et al.  Characteristics of Secondary Flow Induced by 90-Degree Elbow in Turbulent Pipe Flow , 2014 .

[6]  Hidesato Ito,et al.  Flow in curved pipes. , 1987 .

[7]  Sondipon Adhikari,et al.  A Response Surface Modelling Approach for Resonance Driven Reliability Based Optimization of Composite Shells , 2016 .

[8]  M. K. Tripathi,et al.  Evolution of glass forming ability indicator by genetic programming , 2016 .

[9]  Lan Ming-Shong,et al.  ACOUSTIC EMISSION AND MACHINING - PROCESS ANALYSIS AND CONTROL , 1986 .

[10]  S. Datta,et al.  Design of novel age-hardenable aluminium alloy using evolutionary computation , 2017 .

[11]  P. Dutta,et al.  Effect of Reynolds Number and Curvature Ratio on Single Phase Turbulent Flow in Pipe Bends , 2015 .

[12]  R. S. Govindaraju,et al.  Artificial Neural Networks in Hydrology , 2010 .

[13]  R. Jamaati,et al.  Microstructure and texture evolution of friction stir welded dissimilar aluminum alloys: AA2024 and AA6061 , 2018 .

[14]  Sondipon Adhikari,et al.  Rotational and ply-level uncertainty in response of composite shallow conical shells , 2015 .

[15]  John R Weske.  Experimental Investigation of Velocity Distributions of Downstream of Single Duct Bends , 1948 .

[16]  Laszlo Fuchs,et al.  Numerical computations of steady and unsteady flow in bended pipes , 2007 .

[17]  Cathal Heavey,et al.  A comparison of genetic programming and artificial neural networks in metamodeling of discrete-event simulation models , 2012, Comput. Oper. Res..

[18]  S. Dey,et al.  Stochastic dynamic analysis of twisted functionally graded plates , 2018, Composites Part B: Engineering.

[19]  Anupam Chakrabarti,et al.  Structural Damage Identification Using Response Surface-Based Multi-objective Optimization: A Comparative Study , 2015, Arabian Journal for Science and Engineering.

[20]  Donald R. Jones,et al.  Efficient Global Optimization of Expensive Black-Box Functions , 1998, J. Glob. Optim..

[21]  Shubhabrata Datta,et al.  Incorporation of prior knowledge in neural network model for continuous cooling of steel using genetic algorithm , 2017, Appl. Soft Comput..

[22]  Vassili Toropov,et al.  Multi-objective Computational Fluid Dynamics (CFD) design optimisation in commercial bread-baking , 2013 .

[23]  Jiyuan Tu,et al.  Computational Fluid Dynamics: A Practical Approach , 2007 .

[24]  Jack Legrand,et al.  Numerical investigation of bend and torus flows, part I : effect of swirl motion on flow structure in U-bend , 2004 .

[25]  Mohammad Javad Yazdanpanah,et al.  Wave hindcasting by coupling numerical model and artificial neural networks , 2008 .

[26]  M. Meinke,et al.  Large-eddy simulation of low frequency oscillations of the Dean vortices in turbulent pipe bend flows , 2005 .

[27]  B. P. Swain,et al.  Genetically optimized diamond-like carbon thin film coatings , 2019, Materials and Manufacturing Processes.

[28]  H. Kamide,et al.  Influence of elbow curvature on flow structure at elbow outlet under high Reynolds number condition , 2011 .

[29]  P. Dutta,et al.  Numerical Study on Turbulent Separation Reattachment Flow in Pipe Bends with Different Small Curvature Ratio , 2018, Journal of The Institution of Engineers (India): Series C.

[30]  Prasun Dutta,et al.  Numerical study on flow separation in 90° pipe bend under high Reynolds number by k-ε modelling , 2016 .

[31]  Tanmoy Mukhopadhyay,et al.  A multivariate adaptive regression splines based damage identification methodology for web core composite bridges including the effect of noise , 2018 .

[32]  Tanmoy Mukhopadhyay,et al.  Metamodel based high-fidelity stochastic analysis of composite laminates: A concise review with critical comparative assessment , 2017 .

[33]  Sondipon Adhikari,et al.  Stochastic natural frequency of composite conical shells , 2015 .

[34]  Dong Zhao,et al.  A comparative study of metamodeling methods considering sample quality merits , 2010 .

[35]  P. Roache.  Perspective: A Method for Uniform Reporting of Grid Refinement Studies , 1994 .

[36]  P. Bradshaw.  Effects of Streamline Curvature on Turbulent Flow. , 1973 .

[37]  Ozgur Kisi,et al.  Comparison of four heuristic regression techniques in solar radiation modeling: Kriging method vs RSM, MARS and M5 model tree , 2018 .

[38]  Vladan Babovic,et al.  Neural networks as routine for error updating of numerical models , 2001 .

[39]  M. Sumida,et al.  Experimental investigation on turbulent flow in a square-sectioned 90-degree bend , 1998 .

[40]  Susmita Naskar,et al.  Uncertain natural frequency analysis of composite plates including effect of noise – A polynomial neural network approach , 2016 .

[41]  K. Kalita,et al.  PECVD process parameter optimization: towards increased hardness of diamond-like carbon thin films , 2018, Materials and Manufacturing Processes.

[42]  Chen Xu,et al.  Application of Artificial Neural Network and Genetic Programming in Modeling and Optimization of Ultraviolet Water Disinfection Reactors , 2015 .

[43]  William J. Pitz,et al.  An Approach for Formulating Surrogates for Gasoline with Application toward a Reduced Surrogate Mechanism for CFD Engine Modeling , 2011 .

[44]  Frank T. Smith,et al.  Fluid flow into a curved pipe , 1976, Proceedings of the Royal Society of London. A. Mathematical and Physical Sciences.