Abstract
The efficient design of a throttle element is still a challenging open problem in fluid flow engineering, considering the flow characteristics, turbulence, and cavitation phenomenon. An optimization framework based on the Optimized Latin Hypercube Sampling method and Bayesian optimization is proposed, where the Optimized Latin Hypercube Sampling method is used to build a preliminary surrogate model within limited sampling points, then the best candidate location is guessed by the Bayesian optimization. First, two numerical cases are discussed to verify the correctness of the proposed optimization framework in mathematics, both cases find the best candidate in less than 200 iterations. Second, a two-stage throttle plate is used to verify whether the optimization framework is suitable for an engineering problem. The computational fluid dynamics is less than 5% error compared to the experimental data. In the two-variable case, the optimal candidate is better than the candidate of the exhaustive method with fewer simulations. Some common features of the geometric structure and flow characteristics are discussed in the five-variable case. Finally, the complex engineering design of the multi-stage orifice plate is optimized, and the best candidate is generated after 130 iterations, showcasing close flow velocity performance comparable to the two-stage case, a unique “X”-shaped flow path is observed in this candidate. The proposed optimization framework efficiently realizes high-performance orifice plates with less computational resources.
Similar content being viewed by others
References
Bates SJ, Sienz J, Langley DS (2003) Formulation of the audze-eglais uniform latin hypercube design of experiments. Adv Eng Softw 34(8):493–506
Corbera S, Olazagoitia JL, Lozano JA (2016) Multi-objective global optimization of a butterfly valve using genetic algorithms. ISA Trans. 63:401–412
Costin WJ, Allen CB (2013) Numerical study of radial basis function interpolation for data transfer across discontinuous mesh interfaces. Int J Numer Methods Fluids 72(10):1076–1095
Fatahi Nafchi R, Yaghoobi P, Reaisi Vanani H et al (2021) Eco-hydrologic stability zonation of dams and power plants using the combined models of smce and cequalw2. Appl Water Sci 11(7):109
Frazier PI (2018) A tutorial on bayesian optimization. Mach Learn. https://doi.org/10.48550/arXiv.1807.02811
Gan R, Li B, Tang T et al (2022) Noise optimization of multi-stage orifice plates based on rbf neural network response surface and adaptive nsga-ii. Ann Nucl Energy 178(109):372
Lei L, Gang Y, Jing G (2022) Physics-guided neural network for underwater glider flight modeling. Appl Ocean Res 121(103):082
Lei L, Gang Y, Jing G et al (2022) Gliding hydrodynamic modeling and identification of underwater glider based on differential evolution algorithm. Ocean Eng 244(110):250
Lei L, Tang T, Gang Y et al (2022) Hierarchical neural network-based hydrological perception model for underwater glider. Ocean Eng 260(112):101
Liefvendahl M, Stocki R (2006) A study on algorithms for optimization of Latin hypercubes. J Stat Plan Inference 136(9):3231–3247
Nafchi RF, Samadi-Boroujeni H, Vanani HR et al (2021) Laboratory investigation on erosion threshold shear stress of cohesive sediment in Karkheh dam. Environ Earth Sci 80:1–15
Osman H, Elsayed K, Sedrak M (2019) Shape optimization of an orifice meter using the Adjoint method and surrogate based optimization. Flow Meas Instrum 70(101):652
Pałys L, Mrzygłód MW (2021) Using metamodeling and fluid-structure interaction analysis in multi-objective optimization of a butterfly valve. Comput Assist Methods Eng Sci 28(1):17–38
Seeger M (2004) Gaussian processes for machine learning. Int J Neural Syst 14(02):69–106
Shayannejad M, Ghobadi M, Ostad-Ali-Askari K (2022) Modeling of surface flow and infiltration during surface irrigation advance based on numerical solution of saint-venant equations using preissmann’s scheme. Pure Appl Geophys 179(3):1103–1113
Soleimani S, Eckels S (2022) Multi-objective optimization of 3d micro-fins using NSGA-II. Int J Heat Mass Trans 197(123):315
Tang T, Gao L, Li B et al (2019) Cavitation optimization of a throttle orifice plate based on three-dimensional genetic algorithm and topology optimization. Struct Multidiscip Optim 60(3):1227–1244
Tang T, Yang G, Zhang D et al (2020) A hydrodynamic prediction model of throttle orifice plate using space filling and adaptive sampling method. Struct Multidiscip Optim 62(3):1563–1578
Viana FA, Venter G, Balabanov V (2010) An algorithm for fast optimal Latin hypercube design of experiments. Int J Num Methods Eng 82(2):135–156
Wang C, Yang M, Wang Y et al (2022) Design and optimization of cylindrical hull with non-uniform arch ribs for underwater gliders based on approximate model and experiments. Ocean Eng 259(111):831
Zhang Y, Lai J, He C et al (2022) Cavitation optimization of single-orifice plate using cfd method and neighborhood cultivation genetic algorithm. Nuclear Eng Technol 54(5):1835–1844
Funding
This work was supported by the Open Research Fund Program of Hubei Provincial Key Laboratory of Chemical Equipment Intensification and Intrinsic Safety under Grant [no. 2020KA02]; the Science Foundation of Wuhan Institute of Technology under Grant [no. K2021014].
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
No potential conflict of interest was reported by the authors.
Replication of results
The Python code of the proposed algorithm is unavailable due to the confidential issue. The source data are available upon request to the corresponding author.
Additional information
Responsible Editor: Hongyi Xu.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Tang, T., Lei, L., Xiao, L. et al. Flow characteristic optimization of a multi-stage orifice plate using surrogate-based modeling and Bayesian optimization. Struct Multidisc Optim 66, 188 (2023). https://doi.org/10.1007/s00158-023-03647-0
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s00158-023-03647-0