Optimization of a Lobed Mixer with BP Neural Network and Genetic Algorithm

SONG Yukuan, LEI Zhijun, LU Xin-Gen, XU Gang, ZHU Junqiang

热科学学报 ›› 2023, Vol. 32 ›› Issue (1) : 387-400.

PDF(7606 KB)
English

Journal of Thermal Science

热科学学报
PDF(7606 KB)
热科学学报 ›› 2023, Vol. 32 ›› Issue (1) : 387-400. DOI: 10.1007/s11630-022-1766-7  CSTR: 32141.14.JTS-022-1766-7
气动

Optimization of a Lobed Mixer with BP Neural Network and Genetic Algorithm

  • SONG Yukuan1,2, LEI Zhijun1,2*, LU Xin-Gen1,2, XU Gang1,2, ZHU Junqiang1,2
作者信息 +

Optimization of a Lobed Mixer with BP Neural Network and Genetic Algorithm

  • SONG Yukuan1,2, LEI Zhijun1,2*, LU Xin-Gen1,2, XU Gang1,2, ZHU Junqiang1,2
Author information +
文章历史 +

摘要

基于BP神经网络和遗传算法，建立了波瓣混合器多目标优化的顺序近似优化框架（SAO）：以波瓣波长与高度之比（η）和上升角（α）为设计参数，以混合效率、推力和总压力损失为优化目标。波瓣混合器的数值计算采用CFX商用求解器，并以SST湍流模型进行湍流封闭。波瓣混合器计算域采用四面体非结构化网格，其中具有560万个节点的网格即可获得精确的全局结果。根据波瓣混合器的响应面近似模型，应避免同时增加或减少α和η；相反，α应减小，而η应适当增加，有利于实现增加推力和减少损失的目标，而代价是混合效率略有降低。与归一化方法相比，具有更好全局优化精度的非归一化方法更适合于求解波瓣混合器的多目标优化问题，其最优解（α=8.54°，η=1.165）是本文研究的波瓣混合器优化问题的最优解。与基准波瓣混合器相比，最优解的α、β（下降角）和H（波瓣高度）分别减少0.14°、1.34°和3.97 mm，η增加0.074；其混合效率降低了4.46%，但推力增加了2.29%，总压力损失降低了0.64%。在优化的波瓣混合器的下游，流向涡的径向尺度和峰值涡度随着波瓣高度的减小而减小，从而降低了混合效率。对于优化的波瓣混合器，其混合效率低是降低总压力损失的主要因素，但几何曲率的改善也有利于降低其轮廓损失。在本研究范围内，最优波瓣混合器混合效率ε=74.14%，此时可最大化其输出推力，而不会过度增加掺混损失。

Abstract

A Sequential Approximate Optimization framework (SAO) for the multi-objective optimization of lobed mixer is established by using the BP neural network and Genetic Algorithm: the ratio of lobe wavelength to height (η) and the rise angle (α) are selected as the design parameters, and the mixing efficiency, thrust and total pressure loss are the optimization objectives. The CFX commercial solver coupled with the SST turbulence model is employed to simulate the flow field of lobed mixer. A tetrahedral unstructured grid with 5.6 million cells can achieve the similar global results. Based on the response surface approximation model of the lobed mixer, it is necessary to avoid increasing or decreasing α and η at the same time. Instead, the α should be reduced while the η is appropriately increased, which is conducive to achieving the goal of increasing thrust and reducing losses at the expense of a small decrease in the mixing efficiency. Compared with the normalized method, the non-normalized method with better global optimization accuracy is more suitable for solving the multi-objective optimization problem of the lobed mixer, and its optimal solution (α=8.54°, η=1.165) is the optimal solution of the lobed mixer optimization problem studied in this paper. Compared with the reference lobed mixer, the α, β (the fall angle) and H (lobe height) of the optimal solution are reduced by 0.14°, 1.34° and 3.97 mm, respectively, and the η is increased by 0.074; its mixing efficiency is decreased by 4.46%, but the thrust is increased by 2.29% and the total pressure loss is decreased by 0.64%. Downstream of the optimized lobed mixer, the radial scale and peak vorticity of the streamwise voritices decrease with the decreasing lobe height, thereby reducing the mixing efficiency. For the optimized lobed mixer, its low mixing efficiency is the main factor for the decrease of the total pressure loss, but the improvement of the geometric curvature is also conducive to reducing its profile loss. Within the scope of this study, the lobed mixer has an optimal mixing efficiency (ε=74.14%) that maximizes its thrust without excessively increasing the mixing loss.

关键词

lobed mixer / optimization / BP neural network / genetic algorithm, jet mixing

Key words

lobed mixer / optimization / BP neural network / genetic algorithm, jet mixing

引用本文

EndNote

Ris (Procite)

Bibtex

导出引用
SONG Yukuan, LEI Zhijun, LU Xin-Gen, XU Gang, ZHU Junqiang. Optimization of a Lobed Mixer with BP Neural Network and Genetic Algorithm[J]. 热科学学报, 2023, 32(1): 387-400 https://doi.org/10.1007/s11630-022-1766-7
SONG Yukuan, LEI Zhijun, LU Xin-Gen, XU Gang, ZHU Junqiang. Optimization of a Lobed Mixer with BP Neural Network and Genetic Algorithm[J]. Journal of Thermal Science, 2023, 32(1): 387-400 https://doi.org/10.1007/s11630-022-1766-7

参考文献

[1] Birch S., Paynter G., Spalding D., et al., An experimental and numerical study of the 3-D mixing flows of a turbofan engine exhaust system. American Institute of Aeronautics and Astronautics (AIAA), 1977. DOI: 10.2514/6.1977-204.
[2] Presz J.R.W., Mixer/ejector noise suppressors. American Institute of Aeronautics and Astronautics (AIAA), 1991. 
DOI: 10.2514/6.1991-2243.
[3] Power G., McClure M., Vinh D., Advanced IR suppressor design using a combined CFD/test approach. American Institute of Aeronautics and Astronautics (AIAA), 1994. 
DOI: 10.2514/6.1994-3215.
[4] Frost T.H., Practical bypass mixing systems for fan jet aero engines. Aeronautical Quarterly, 1966, 17: 141–160.
[5] Werle M., Presz J.R.W., Paterson R., Flow structure in a periodic axial vortex array. American Institute of Aeronautics and Astronautics (AIAA), 1987. DOI: 10.2514/6.1987-610.
[6] Eckerle W.A., Sheibani H., Awad J., Experimental measurement of the vortex development downstream of a lobed forced mixer. Journal of Engineering for Gas Turbines and Power, 1992, 114: 63–71.
[7] McCormick D.C., Bennett J.C., Vortical and turbulent structure of a lobed mixer free shear layer. AIAA Journal, 1994, 32: 1852–1859.
[8] Elliott J.K., Manning T.A., Qiu Y.J., et al., Computational and experimental studies of flow in multi-lobed forced mixers. AIAA/ASME/SAE/ASEE 28th Joint Propulsion Conference and Exhibit, 1992. American Institute of Aeronautics and Astronautics Inc, AIAA, 1992. 
DOI: 10.2514/6.1992-3568.
[9] Belovich V.M., Samimy M., Mixing processes in a coaxial geometry with a central lobed mixer-nozzle. AIAA Journal, 1997, 35: 838–841.
[10] Lei Z.J., Experimental study on the mixing mechanism of lobed mixer with inlet swirl in model turbofan engines. 2011, Chinese Academy of Sciences, China. (in Chinese) 
[11] O’Sullivan M.N., Krasnodebski J.K., Waitz I.A., et al., Computational study of viscous effects on lobed mixer flow features and performance. Journal of Propulsion and Power, 1996, 12: 449–456.
[12] Sheoran Y., Hoover R., Schuster W., et al., Forced mixer nozzle optimization. NASA Report, 1999, Report No. NASA/CR-1999-209160.
[13] Abolfadl M.A., Metwally M.A., El-Messiry A.M., et al., Experimental investigation of lobed mixer performance. Journal of Propulsion and Power, 2001, 17: 1109–1116.
[14] Kozlowski H., Larkin M., Energy efficient engine exhaust mixer model technology. NASA Report, 1981, Report No NASA-CR-165459.
[15] Chai M., Lei Z.J., Lu X.G., et al., Research on jet mixing mechanism of a new de-swirling lobed mixer. Journal of Propulsion Technology, 2018, 39(9): 1965–1973. 
[16] Xie Y., Yi C., Influence of micro-lobed burner on the non-premixed combustion of methane and oxygen. Journal of Thermal Science and Engineering Applications, 2020, 12(1): 011011. 
DOI: 10.1115/1.4043913.
[17] Fang X.X., Shen C.B., Sun M.B., et al., Turbulent structures and mixing enhancement with lobed mixers in a supersonic mixing layer. Physics of Fluids, 2020, 32(4): 041701. DOI: 10.1063/5.0005156.
[18] Huang W., Du Z.B., Yan L., et al., Supersonic mixing in air breathing propulsion systems for hypersonic flights. Progress in Aerospace Sciences, 2019, 109: 100545.
[19] Zhang D.D., Tan J.G., Li H., et al., Fine flow structure and mixing characteristic in supersonic flow induced by a lobed mixer. Acta Physica Sinica, 2017, 66(10): 104702. DOI: 10.7498/aps.66.104702.
[20] Sheng Z.Q., Yao Y., Xu Y.H., Suggestions on investigations of lobed jet mixing. Aerospace Science and Technology, 2019, 86: 415–429. 
[21] Wang Q., Zhao Q., Rotor blade aerodynamic shape optimization based on high-efficient optimization method. Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering, 2020, 234: 375–387.
[22] Lai Y.Y., Jiang X., Detailed explanation of the theory of parameter optimization with Isight. 3rd ed. Beijing: Beihang University Press, 2012. (in Chinese)
[23] Yang C., Aoyama T., Chae S., et al., Blade planform optimization to reduce HSI noise of helicopter in hover. Proceedings of the 64th American Helicopter Society forum, Montreal, Canada, Annual Forum Proceedings- AHS International, 2008, pp. 2218–2232.
[24] Kim J.H., Choi J.H., Husain A., et al., Multi-objective optimization of a centrifugal compressor impeller through evolutionary algorithms. Proceedings of the Institution of Mechanical Engineers, Part A: Journal of Power and Energy, 2010, 224: 711–721.
[25] Islek A.A., Optimization of micro compressor blades using CFD analysis and artificial intelligence. Proceedings of ASME, 2003, Paper No: FEDSM2003-45751.
[26] Xie Y., Yan C.C., Ruan D.F., et al., Research on approximation model of lobed mixing exhaust system based on response surface methodology. Journal of Propulsion Technology, 2016, 37: 1037–1048.
[27] Zhang Z.P., Aerodynamic design and performance analysis of lobed ejector in wind turbines. 2015, Harbin Institute of Technology, China. (in Chinese)
[28] Xie Y., Liu Y.H., A modified thermal mixing efficiency and its application to lobed mixer nozzle for aero-engines. Heat Transfer Research, 2011, 42: 317–335.
[29] Chai M., Investigation on the design and flow mechanisms of the de-swirling lobed mixer. 2018, Chinese Academy of Sciences, China. (in Chinese)
[30] Cheng R., Gen M., An adaptive superplane approach for multiple object optimization problems. Report, Ashikaga Institute of Technology, Ashikaga City, Tochigi, Japan, 1998.
[31] Wu Z.P., Study on sequential approximate optimization and its application. 2010, National University of Defense Technology, China. (in Chinese)
[32] Nakayama H., Arakawa M., Sasaki R., Simulation-based optimization using computational intelligence. Optimization and Engineering, 2002, 3: 201–214.
[33] Pan C.C., Zhang J.Z., Shan Y., et al., Flow separation control of lobed ejector/forced mixer by ventilation. Journal of Aerospace Power, 2013, 28(2): 331–337.

基金

This research was funded by the National Science and Technology Major Project (Grant No. J2019-II-0007-0027).

版权

Science Press, Institute of Engineering Thermophysics, CAS and Springer-Verlag GmbH Germany, part of Springer Nature 2022
PDF(7606 KB)

45

Accesses

0

Citation

Detail
段落导航
相关文章

微信公众号

主办单位：中国科学院工程热物理研究所　 出版单位：科学出版社

版权所有© 2023 热科学学报

/

〈 〉