基于深度学习的螺旋桨水动力性能快速预报方法

doi:10.16183/j.cnki.jsjtu.2022.331

摘要/Abstract

摘要：

为实现螺旋桨水动力性能的快速、精确预报,基于改进的残差连接神经网络建立了一套螺旋桨水动力性能预报模型.残差连接方式大幅提高了模型深度,结合Inception结构从不同尺度同时提取数据特征,利用深度可分离式卷积减少模型参数,基于螺旋桨几何参数和模型试验结果构建训练深度神经网络所需的样本空间;提出一种改进的群体天牛须算法对模型的初始权重与阈值进行优化,进一步提高其预报精度.研究结果表明:改进的群体天牛须算法显著提高预报模型的精度并解决了过拟合问题,预报结果与试验值吻合良好,对数据集外螺旋桨的预测性能与CFD法基本一致.模型的普适性极佳且计算周期极短、效率高,满足实时、准确预报螺旋桨敞水性能的要求.

关键词: 螺旋桨, 水动力性能, 残差神经网络, Inception结构, 改进的群体天牛须搜索算法

Abstract:

In order to achieve rapid and accurate prediction of the hydrodynamic performance of propellers, a set of propeller hydrodynamic performance prediction model was established based on the improved residual connection network. The residual connection method greatly improves the depth of the model. In combination with the Inception structure to simultaneously extract data features from different scales, the depthwise separable convolution reduces the model parameters. The sample space for training the deep neural network is built based on the propeller geometric parameters and model test results. An improved beetle swarm antennae search algorithm is proposed to optimize the initial weights and thresholds of the model to further improve the prediction accuracy of the model. The research results indicate that the improved beetles swarm antennae algorithm significantly improves the accuracy of the model and solves the problem of overfitting of it. The prediction results of the model are in good agreement with the experimental values, and its prediction performance for the propellers which are not in the dataset is basically the same as that of the CFD method. The model has an excellent universality and its calculation period is extremely short, which can meet the requirements of real-time and accurate prediction of propeller open water performance.

Key words: propeller, hydrodynamic performance, residual neural network, Inception structure, the improved beetle swarm antennae search algorithm

中图分类号:

U664.33

高楠, 胡安康, 侯立勋, 常欣. 基于深度学习的螺旋桨水动力性能快速预报方法[J]. 上海交通大学学报, 2024, 58(2): 188-200.

GAO Nan, HU Ankang, HOU Lixun, CHANG Xin. An Rapid Prediction Method for Propeller Hydrodynamic Performance Based on Deep Learning[J]. Journal of Shanghai Jiao Tong University, 2024, 58(2): 188-200.

图/表 19

图1

图2

图3

图4

表1

表2

表3

测试函数及其取值区间

测试函数	公式	搜索维度	取值区间
f₁	$f (x) = ∑ i = 1 n \| x i + 1 \|$	30	[-100, 100]
f₂	$f (x) = ∑ i = 1 n [100 (x i + 1 - x i 2) 2 + (x i - 1) 2]$	30	[-30, 30]
f₃	$f (x) = ∑ i = 1 n \| x i \| + ∏ i = 1 n \| x i \|$	30	[-10, 10]
f₄	$f (x) = ∑ i = 1 n \| x i + 0.5 \| 2$	30	[-100, 100]
f₅	$f (x) = ∑ i = 1 n [x i 2 - 10 c o s (2 π x i) + 10]$	30	[-5.12, 5.12]
f₆	$f (x) = ∑ i = 1 n \| x i s i n x i + 0.1 x i \|$	30	[-10, 10]
f₇	$f (x) = 418.9829 n - ∑ i = 1 n x i s i n \| x i \|$	30	[-500, 500]
f₈	$f (x) = ∑ i = 1 n i x i 4 + r a n d o m [0,1]$	30	[-1.28, 1.28]

表3

图5

图6

图7

图8

图9

图10

表4

表5

图11

图12

图13

图14

参考文献 36

[1]	CHOI S P, LEE J U, PARK J B. Application of deep reinforcement learning to predict shaft deformation considering hull deformation of medium-sized oil/chemical tanker[J]. Journal of Marine Science and Engineering, 2021, 9(7): 1-29. doi: 10.3390/jmse9010001 URL
[2]	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. doi: 10.1016/j.apor.2019.101981 URL
[3]	SHORA M M, GHASSEMI H, NOWRUZI H. Using computational fluid dynamic and artificial neural networks to predict the performance and cavitation volume of a propeller under different geometrical and physical characteristics[J]. Journal of Marine Engineering & Technology Proceedings of the Institute of Marine Engineering Science & Technology, 2018, 17(2): 59-84.
[4]	王超, 韩康, 孙聪, 等. 船用螺旋桨优化设计与参数分析[J]. 华中科技大学学报(自然科学版), 2020, 48(4): 97-102.
	WANG Chao, HAN Kang, SUN Cong, et al. Marine propeller optimization design and parameter analysis[J]. Journal of Huazhong University of Technology (Natural Science Edition), 2020, 48(4): 97-102.
[5]	XUE Y, YANG C J, DONG X Q, et al. Design of marine propellers with prescribed and optimal spanwise circulation distributions based on genetic algorithms and neural network[J]. Applied Ocean Research, 2022, 127: 103318. doi: 10.1016/j.apor.2022.103318 URL
[6]	THOMAS M, LIONEL F, LAURENT D P, et al. Propeller noise detection with deep learning[C]// International Conference on Acoustics Speech and Signal Processing ICASSP. Barcelona, Spain:IEEE, 2020: 306-310.
[7]	WANG Y J, WANG K Q, MOUSTAFA A M. NoiseNet: A neural network to predict marine propellers’ underwater radiated noise[J]. Ocean Engineering, 2021, 236: 109542. doi: 10.1016/j.oceaneng.2021.109542 URL
[8]	MIGLIANTI L, CIPOLLINI F, ONETO L, et al. Predicting the cavitating marine propeller noise at design stage: A deep learning based approach[J]. Ocean Engineering, 2020, 209: 107481. doi: 10.1016/j.oceaneng.2020.107481 URL
[9]	王宪磊. 基于CFD的大侧斜螺旋桨性能研究[D]. 大连: 大连海事大学, 2020.
	WANG Xianlei. Research on the performance of high skew propeller based on CFD[D]. Dalian: Dalian Maritime University, 2020.
[10]	LONG Y, HAN C Z, JI B, et al. Verification and validation of large eddy simulations of turbulent cavitating flow around two marine propellers with emphasis on the skew angle effects[J]. Applied Ocean Research, 2020, 101: 102167. doi: 10.1016/j.apor.2020.102167 URL
[11]	王文全, 马开放, 王诗洋, 等. 螺旋桨适伴流理论设计及参数优化设计[J]. 应用科技, 2019, 46(5): 1-9.
	WANG Wenquan, MA Kaifang, WANG Shiyang, et al. Wake-adapted theory design and parameter optimization design of propeller[J]. Applied Science and Technology, 2019, 46(5): 1-9.
[12]	朱显玲, 齐江辉, 陈艳霞. 斜流中七叶侧斜螺旋桨水动力及空泡性能研究[J]. 推进技术, 2022, 43(8): 425-433.
	ZHU Xianling, QI Jianghui, CHEN Yanxia. Hydrodynamic performance and cavitation characteristics of seven blade propeller with skew in oblique flow[J]. Journal of Propulsion Technology, 2022, 43(8): 425-433.
[13]	杨晓. 水动力模型驱动下的智能船舶仿真平台研究[D]. 大连: 大连海事大学, 2020.
	YANG Xiao. Research on simulation platform of intelligent ship driven by hydrodynamic model[D]. Dalian: Dalian Maritime University, 2020.
[14]	YANG X, YIN Y, LIAN J J. Numerical study on the hydrodynamic performance of the semi-spade rudder and propeller[J]. Advances in Mechanical Engineering, 2019, 11(1): 1-18.
[15]	汤世昕, 沈育静, 陈纪康, 等. 改进螺旋桨敞水性能预报的泰勒展开边界元法[J]. 哈尔滨工程大学学报, 2022, 43(7): 928-935.
	TANG Shixin, SHEN Yujing, CHEN Jikang, et al. Taylor expansion boundary element method for propeller steady hydrodynamic performance prediction[J]. Journal of Harbin Engineering University, 2022, 43(7): 928-935.
[16]	BISHOUP B A, BROCKETT T, DONG S T. Report of the propulsor committee. 18th ITTC[C]// International Towing Tank Conference. Kobe, Japan: Japan Shipbuilding Association, 1987: 104-105.
[17]	黄永生. 高速水下航行体对转螺旋桨设计方法研究[D]. 上海: 上海交通大学, 2020.
	HUANG Yongsheng. Study on design methods for contra-rotating propellers of high speed underwater vehicles[D]. Shanghai: Shanghai Jiao Tong University, 2020.
[18]	DJAHIDA B, OMAR I. Numerical simulation of the cavitating flow around marine co-rotating tandem propellers[J]. Brodogradnja, 2019, 70(1): 43-57.
[19]	赵旻晟, 赵伟文, 万德成. E779A螺旋桨斜流工况下的空泡数值模拟[J]. 中国造船, 2021, 62(3): 94-102.
	ZHAO Minsheng, ZHAO Weiwen, WAN Decheng. Numerical simulation of cavitation under oblique flow condition of E779A propeller[J]. Shipbuilding of China, 2021, 62(3): 94-102.
[20]	EBRAHIMI A, SEIF M S, NOURI BORUJERDI A. Hydro-acoustic and hydrodynamic optimization of a marine propeller using genetic algorithm, boundary element method, and FW-H equations[J]. Journal of Marine Science and Engineering. 2019, 7(9): 321-1-18. doi: 10.3390/jmse7090321 URL
[21]	张利军. 螺旋桨性能预报的速度势面元法研究[D]. 大连: 大连理工大学, 2006.
	ZHANG Lijun. Investigation of a potential based surface panel method for prediction of propeller performances[D]. Dalian: Dalian University of Technology, 2006.
[22]	PAN Y C, ZHANG H X, ZHOU Q D. Numerical simulation of unsteady propeller force for a submarine in straight ahead sailing and steady diving maneuver[J]. International Journal of Naval Architecture and Ocean Engineering, 2019, 11(2): 899-913. doi: 10.1016/j.ijnaoe.2019.04.002 URL
[23]	ZHANG X T, HONG Y, LIU W B, et al. Improving the propulsion performance of composite propellers under off-design conditions[J]. Applied Ocean Research, 2020, 100: 102164 doi: 10.1016/j.apor.2020.102164 URL
[24]	TONG X D, CHEN H Y, CHEN Y, et al. Influence of skew angle on the random vibration response of propeller-shafting system induced by turbulent inflow[J]. Ocean Engineering, 2022, 244: 110350. doi: 10.1016/j.oceaneng.2021.110350 URL
[25]	王琪, 杨晨俊. 基于涡格法的任意环量分布螺旋桨数值设计方法[J]. 中国造船, 2018, 59(2): 90-102.
	WANG Qi, YANG Chenjun. Numerical design method of arbitrary circulation distribution of propeller based on vortex lattice method[J]. Shipbuilding of China, 2018, 59(2): 90-102.
[26]	陈志明, 袁剑平, 严谨, 等. 基于MRF方法和滑移网格的螺旋桨水动力性能研究[J]. 船舶工程, 2020, 42(Sup.1): 157-162.
	CHEN Zhiming, YUAN Jianping, YAN Jin, et al. Study on hydrodynamic performance of propeller based on MRF model and sliding mesh[J]. Ship Engineering, 2020, 42(Sup.1): 157-162.
[27]	胡俊明, 李铁骊, 林焰, 等. 基于RANS法的B系列对转螺旋桨敞水性能数值模拟[J]. 大连理工大学学报, 2017, 57(2): 148-156.
	HU Junming, LI Tieli, LIN Yan, et al. Numerical simulation of open water performance of B series contra-rotating propellers based on RANS method[J]. Journal of Dalian University of Technology, 2017, 57(2): 148-156.
[28]	胡健, 李聪慧, 张维鹏, 等. 基于CFD的桨舵水动力干扰研究[J]. 应用科技, 2017, 44(3): 5-11.
	HU Jian, LI Conghui, ZHANG Weipeng, et al. Investigation of hydrodynamic interaction between propeller and rudder based on computation fluid dynamics[J]. Applied Science and Technology, 2017, 44(3): 5-11.
[29]	王超. 螺旋桨水动力性能、空泡及噪声性能的数值预报研究[D]. 哈尔滨: 哈尔滨工程大学, 2010.
	WANG Chao. The research on performance of propeller’s hydrodynamics, cavitation and noise[D]. Harbin: Harbin Engineering University, 2010.
[30]	胡洋, 胡健, 刘亚彬. 斜流中螺旋桨的水动力性能研究[J]. 武汉理工大学学报(交通科学与工程版), 2019, 43(2): 262-268.
	HU Yang, HU Jian, LIU Yabin. Research on hydrodynamic performance of propeller in oblique flow[J]. Journal of Wuhan University of Technology (Transportation Science & Engineering), 2019, 43(2): 262-268.
[31]	ZHOU X M, PAN H C, TIAN X Q, et al. Comparative analysis of hydrodynamic performance of propeller under different turbulence models[C]// 3rd International Conference on Fluid Mechanics and Industrial Applications. Taiyuan, China: IOP Publishing Ltd., 2019: 1300-1-11.
[32]	宁鹏. 基于速度势面元法的三维水翼与螺旋桨水动力性能预报[D]. 杭州: 浙江大学, 2017.
	NING Peng. Prediction of hydrodynamic performance on three-dimensional hydrofoil and propeller using potential panel method[D]. Hangzhou: Zhejiang University, 2017.
[33]	王有江. 螺旋桨水动力性能及流场分析的面元-涡粒子耦合算法研究[D]. 西安: 西北工业大学, 2017.
	WANG Youjiang. Study on the boundary element-vortex particle couple method for the simulation of marine propeller flow[D]. Xi’an: Northwestern Polytechnical University, 2017.
[34]	王超, 黄胜, 常欣, 等. 基于滑移网格与RNG k-ε湍流模型的桨舵干扰性能研究[J]. 船舶力学, 2011, 15(7): 715-721.
	WANG Chao, HUANG Sheng, CHANG Xin, et al. Research on the hydrodynamics performance of propeller-rudder interaction based on sliding mesh and RNG k-ε model[J]. Journal of Ship Mechanics, 2011, 15(7): 715-721.
[35]	SONG S, DEMIREL Y K, ATLAR M. Propeller performance penalty of biofouling: CFD prediction[J]. Journal of Offshore Mechanics and Arctic Engineering, 2020, 142(6): 1-22.
[36]	NADERY A, GHASSEMI H, CHYBOWSKI L. The effect of the PSS configuration on the hydrodynamic performance of the KP505 propeller behind the KCS[J]. Ocean Engineering, 2021, 234: 109310. doi: 10.1016/j.oceaneng.2021.109310 URL

参数	特征集
桨叶片数,Z	FS1
桨直径,D/m	FS1
毂径比,d/D	FS1
盘面比,D_r	FS1
无因次半径,r/R	FS2
螺距比,P/D	FS2
各桨叶剖面的无因次弦长,b/D	FS2
各桨叶剖面的最大厚度比,t_m/b	FS2
各桨叶剖面的拱度比,f_m/b	FS2
桨叶侧斜角,S/(°)	FS2
桨叶纵倾角,r_a/(°)	FS2
推力系数,K_T	OPS
转矩系数,K_Q	OPS
进速系数,J	FS1

型号	Z	D/m	D_r	P/D₍₀_.₇_R₎	S/(°)	r_a/(°)
HSP	5	0.220	0.700	0.944	45.00	-3.03
P4119	3	0.305	0.600	1.084	0.00	0.00
MAU5-65	5	0.250	0.650	1.000	50.00	10.00
KP458	4	0.204	0.431	0.721	13.15	0.00
DTRC 4118	3	0.305	0.600	1.077	0.00	0.00
E779A	4	0.240	0.550	1.100	0.00	4.05
P4381	5	0.305	0.725	1.210	0.00	0.00
KP068	5	0.250	0.725	1.210	0.00	0.00
KP069	5	0.250	0.725	1.191	31.58	0.00
KP070	5	0.250	0.725	1.184	63.10	0.00
B4-55	4	0.240	0.550	1.000	0.00	0.00
B4-40	4	0.300	0.400	1.300	0.00	15.00
P4382	5	0.305	0.725	1.200	36.00	5.38
DTRC 4497	5	0.240	0.700	1.200	36.00	0.00
DTRC 4383	5	0.305	0.725	1.098	72.00	10.15
VP1304	5	0.250	0.779	1.635	18.84	-7.50
DTRC4384	5	0.305	0.725	1.199	108.00	14.46
DTRC4679	3	0.607	0.755	1.572	51.00	0.00

模型	E_train	E_test
IDRN	0.004 85	0.005 95
DRN	0.061 6	0.080 1
DCNN	0.114 2	0.164 1

型号	Z	D/m	D_r	d/D	P/D₍₀_.₇_R₎	S₍₀_.₇_R₎/(°)	r_a/(°)	b/D₍₀_.₇_R₎	t_m/b₍₀_.₇_R₎	f_m/b₍₀_.₇_R₎
KP505	5	0.25	0.80	0.18	0.996 7	32	0.00	0.359 0	0.014 92	0.014 039
B4-70	4	0.3418	0.7	0.2	1.0	1.38	9.21	0.375 2	0.033 07	0.015 602