Optimization of flapping hydrofoil propulsion performance based on combined neural network and CFD

SONG Zhenyu; ZHU Jianyang; DONG Lu

doi:10.7638/kqdlxxb-2023.0053

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Optimization of flapping hydrofoil propulsion performance based on combined neural network and CFD

更新时间：2026-05-28

- Optimization of flapping hydrofoil propulsion performance based on combined neural network and CFD
- Vol. 42, Issue 5, Pages: 53-63(2024)
- 作者机构：
  
  武汉科技大学冶金装备及其控制教育部重点实验室,武汉,430081
- 作者简介：
- 基金信息：
- DOI：10.7638/kqdlxxb-2023.0053
  CLC： V211.41
- Published：2024
- 稿件说明：
移动端阅览
宋振宇, 朱建阳, 董璐. 基于神经网络与CFD相结合的扑翼推进性能优化[J]. 空气动力学学报, 2024, 42(5): 53−63.

SONG Zhenyu, ZHU Jianyang, DONG Lu. Optimization of flapping hydrofoil propulsion performance based on combined neural network and CFD[J]. 2024, 42(5): 53-63.
宋振宇, 朱建阳, 董璐. 基于神经网络与CFD相结合的扑翼推进性能优化[J]. 空气动力学学报, 2024, 42(5): 53−63. DOI： 10.7638/kqdlxxb-2023.0053

SONG Zhenyu, ZHU Jianyang, DONG Lu. Optimization of flapping hydrofoil propulsion performance based on combined neural network and CFD[J]. 2024, 42(5): 53-63. DOI： 10.7638/kqdlxxb-2023.0053.

摘要

为了提升现有水下扑翼式机器人的推进性能，采用田口实验、神经网络和计算流体力学（Computational Fluid Dynamics

CFD）相结合的方法，系统研究展弦比、升沉幅值、俯仰幅值和扑动频率变化对三维NACA 0012扑翼推进性能的影响。首先采用田口实验确定CFD仿真的参数组合，接着进行CFD仿真并为神经网络优化提供数据集，然后训练神经网络并用训练好的神经网络模型对CFD结果进行预测和验证，最后分析优化后的参数组合获得最优推进性能的机理。研究结果表明：展弦比、升沉幅值、俯仰幅值和扑动频率变化能显著影响扑翼的推进性能，其中扑动频率的影响最大，展弦比的影响最小，神经网络优化后的扑翼最大推进效率可达55.43%。进一步对不同参数组合扑翼周围流场结构分析发现，最优参数组合扑翼表面可以形成稳定的涡流，且涡流在扑动过程中可以长时间附着在扑翼表面，这是最优参数组合扑翼具有更好推进性能的内在原因。

Abstract

In order to improve the propulsion performance of existing underwater hydrofoil robots

the Taguchi experiments

neural networks and CFD are combined to systematically study the effects of aspect ratio

heaving amplitude

pitching amplitude and flapping frequency on the propulsion performance of a three-dimensional NACA 0012 hydrofoil. First

the parameter combinations for CFD simulation are determined by the Taguchi method. Next

CFD simulations are performed and the results are used as the training set of the neural network. Then

the neural network is trained and used to predict the CFD result. Finally

the mechanism for the optimal propulsion performance at the optimized parameter combinations is analyzed. The results show that the aspect ratio

heaving amplitude

pitching amplitude

and flapping frequency can significantly affect the propulsion performance of the hydrofoil

among which

the flapping frequency (aspect ratio) has the greatest (least) influence on the propulsion performance. The maximum propulsion efficiency of the hydrofoil can reach 55.43% after the optimization of the neural network. Further analysis of the flow field structure around the hydrofoil with different parameters reveals that

under the optimal parameters there forms a stable vortex on the hydrofoil surface

which can stay on the hydrofoil surface for a long time during the flapping process. This is the intrinsic reason for the better propulsion performance at the optimal parameters.

关键词

Keywords

references

THAWEEWAT N, PHOEMSAPTHAWEE S, JUNTASARO V . Semi-active flapping foil for marine propulsion[J ] . Ocean Engineering, 2018 , 147 : 556 − 564 .

LIU Z, QU H L, SHI H D . Numerical study on hydrodynamic performance of a fully passive flow- driven pitching hydrofoil[J ] . Ocean Engineering, 2019 , 177 : 70 − 84 .

BELIBASSAKIS K A, FILIPPAS E S . Ship propulsion in waves by actively controlled flapping foils[J ] . Applied Ocean Research, 2015 , 52 : 1 − 11 .

FILIPPAS E S, GEROSTATHIS T P, BELIBASSAKIS K A . Semi-activated oscillating hydrofoil as a nearshore biomimetic energy system in waves and currents[J ] . Ocean Engineering, 2018 , 154 ( APR.15 ): 396 − 415 .

CHAO L M, CAO Y H, PAN G A . A review of underwater bio-mimetic propulsion: Cruise and fast-start[J ] . Fluid Dynamics Research, 2017 , 49 ( 4 ): 044501 .

LICHT S, POLIDORO V, FLORES M, et al . Design and projected performance of a flapping foil AUV[J ] . IEEE Journal of Oceanic Engineering, 2004 , 29 ( 3 ): 786 − 794 .

TANGORRA J L, DAVIDSON S N, HUNTER I W, et al . The development of a biologically inspired propulsor for unmanned underwater vehicles[J ] . IEEE Journal of Oceanic Engineering, 2007 , 32 ( 3 ): 533 − 550 .

WANG T M, YANG X B, LIANG J H . A survey on bionic autonomous underwater vehicles propelled by median and/or paired fin mode[J ] . Robot, 2013 , 35 ( 3 ): 352 − 362,384 (in Chinese).

WU X, ZHANG X T, TIAN X L, et al . A review on fluid dynamics of flapping foils[J ] . Ocean Engineering, 2020 , 195 : 106712 .

MEI L, ZHOU J W, YU D, et al . Parametric analysis for underwater flapping foil propulsor[J ] . Water, 2021 , 13 ( 15 ): 2103 .

POLITIS G K, TSARSITALIDIS V T . Flapping wing propulsor design: An approach based on systematic 3D-BEM simulations[J ] . Ocean Engineering, 2014 , 84 : 98 − 123 .

READ D A, HOVER F S, TRIANTAFYLLOU M S . Forces on oscillating foils for propulsion and maneuvering[J ] . Journal of Fluids and Structures, 2003 , 17 ( 1 ): 163 − 183 .

SCHOUVEILER L, HOVER F S, TRIANTAFYLLOU M S. Performance of flapping foil propulsion[J]. Journal of Fluids and Structures, 2005, 20(7): 949-959.

LI Y Z, LIU T Y, WANG Y Q, et al . Deep learning based real-time energy extraction system modeling for flapping foil[J ] . Energy, 2022 , 246 : 123390 .

WANG Z X, CHANG X, HOU L X, et al . Optimal matching of flapping hydrofoil propulsion performance considering interact ion effects of motion parameters[J ] . Journal of Marine Science and Engineering, 2022 , 10 ( 7 ): 853 .

BAKHTIARI M, GHASSEMI H . CFD data based neural network functions for predicting hydrodynamic performance of a low-pitch marine cycloidal propeller[J ] . Applied Ocean Research, 2020 , 94 : 101981 .

LI J D, LI Q L, HAO H, et al . Prediction of BLEVE blast loading using CFD and artificial neural network[J ] . Process Safety and Environmental Protection, 2021 , 149 : 711 − 723 .

CHANG K Y . The optimal design for PEMFC modeling based on Taguchi method and genetic algorithm neural networks[J ] . International Journal of Hydrogen Energy, 2011 , 36 ( 21 ): 13683 − 13694 .

ALIZADEH A, OMRANI H . An integrated multi response Taguchi- neural network- robust data envelopment analysis model for CO 2 laser cutting[J ] . Measurement, 2019 , 131 : 69 − 78 .

Lin H L, Chou C P . Optimisation of the GTA welding process using the Taguchi method and a neural network[J ] . Science and Technology of Welding and Joining, 2006 , 11 ( 1 ): 120 − 126 .

CHEN W H, WANG J S, CHANG M H, et al. Optimization of a vertical axis wind turbine with a deflector under unsteady wind conditions via Taguchi and neural network applications[J]. Energy Conversion and Management, 2022, 254.

ED-DȊN FERTAHI S, BOUHAL T, RAJAD O, et al . CFD performance enhancement of a low cut-in speed current vertical tidal turbine through the nested hybridization of Savonius and Darrieus[J ] . Energy Conversion and Management, 2018 , 169 : 266 − 278 .

LI C, GUAN Y L, FENG Y G, et al . Comparison of influencing factors and level optimization for heating through deep-buried pipe based on Taguchi method[J ] . Geothermics, 2021 , 91 : 102045 .

ZHU J Y, ZHU M K, ZHANG T, et al. Improvement of the power extraction performance of a semi-active flapping airfoil by employing two-sided symmetric slot airfoil[J]. Energy, 2021, 227: 120458.

WU X, ZHU J Y, XIE P . Study on the energy capture efficiency of flapping airfoil power generator using semiactive dual‐layer airfoils[J ] . Energy Science Engineering, 2023 , 11 ( 2 ): 745 − 761 .

DONG L, XIE P, ZHU J Y, et al . Study on the power extraction performance of a flapping airfoil power generator using jet flow method[J ] . Journal of the Brazilian Society of Mechanical Sciences and Engineering, 2023 , 45 ( 2 ): 1 − 11 .

PENG H Y, HAN Z D, LIU H J, et al . Assessment and optimization of the power performance of twin vertical axis wind turbines via numerical simulations[J ] . Renewable Energy, 2020 , 147 : 43 − 54 .

HORNIK K, STINCHCOMBE M, WHITE H . Multilayer feedforward networks are universal approximators[J ] . Neural Networks, 1989 , 2 ( 5 ): 359 − 366 .

ZHANG L M. Models and applications of artificial neural networks[M]. Shanghai: Fudan Press, 1993(in Chinese).

PENG L S, ZHENG M Z, PAN T Y, et al . Effects of tandem-wing interactions on aerodynamics of hovering dragonflies[J ] . Acta Aeronautica et Astronautica Sinica, 2021 , 42 ( 7 ): 124571 (in Chinese).

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Impact of key area optimization on the aerodynamic characteristics of a high-speed train in crosswind

Static aerodynamic characteristics of symmetrical wind turbine airfoils considering the influence of near-ocean underlying surface

Numerical simulation of liquid film cooling on hypersonic oblique plate

Performance of various SST models in predicting typical separated flows

Active control of supersonic jet based on multiple microjets

Related Author

Jiang Jiyun

Liu Tanghong

Wang Xinran

Gao Hongrui

Wang Lei

Jia Xiaofeng

Huang Wen

Hu Chuanxin

Related Institution

中南大学交通运输工程学院，轨道交通安全教育部重点实验室

中南大学轨道交通安全关键技术国际合作联合实验室

中南大学轨道交通列车安全保障技术国家地方联合工程研究中心

中车长春轨道客车股份有限公司

School of urban construction, Wuhan University of Science and Technology, Wuhan

AI问答

⁰