基于多源域融合代理模型的氢能无人机优化设计

doi:10.7527/S1000-6893.2024.30979

Abstract

Abstract:

This paper addresses the optimization problem of the overall design stage of Hydrogen-powered Unmanned Aerial Vehicles （H-UAVs） in the context of heterogeneous multi-source domains. It explores how to effectively utilize the transfer learning technology to establish a surrogate model and optimize H-UAVs in the presence of heterogeneous samples. To solve the problem of high cost of building a surrogate model due to heterogeneous samples during the evolution of hydrogen-powered UAVs， a framework for establishing a Multi-Source domain Fusion （DG-MSF） surrogate model is proposed based on Data Generation. The geodesic flow kernel method is used to map the heterogeneous source and target domains to a high-dimensional space to determine the relationship between multi-source domains. The marginal distribution-based data generation method is used to effectively integrate source domain information. A multi-layer perceptron neural network is built as a surrogate model， and is trained and fine-tuned through pre-training and fine-tuning methods to achieve efficient prediction of performance of H-UAVs. Finally， the optimization design of the H-UAV is carried out. The analysis results show that the proposed method can effectively utilize multi-source domain data to improve the efficiency of model training and prediction accuracy and the overall performance of H-UAVs， providing powerful technical support for the development of H-UAVs.

Key words: hydrogen-powered unmanned aerial vehicle (H-UAV), transfer learning, surrogate model, multi-objective optimization, multi-source domain, pre-training fine-tuning

CLC Number:

V221⁺.6

Rongzu LI, Li LIU, Dun YANG. Optimal design of hydrogen-powered UAV based on multi-source domain fusion surrogate model[J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(9): 630979.

Figures/Tables 23

Fig.1

Fig.2

Fig.3

Table 1

Range of overall design parameters of UAV

序号	设计参数	$X u$	$X l$
1	$L w i n g$ /mm	3 200	5 000
2	$C w i n g$ /mm	300	460
3	$t r o o t$ /mm	2	12
4	$t t i p$ /mm	0.4	10
5	$L s t r u t$ /mm	1 000	3 000
6	$C s t r u t$ /mm	80	200
7	$t s t r u t$ /mm	2	4
8	$V H$ /L	2.6	10
9	$L H$ /mm	200	375

Table 1

Fig.4

Table 2

Characteristic spatial relationship of different UAVs layout

设计变量	布局A	布局B	布局C
$L w i n g$	√	√	√
$C w i n g$	√		√
$t r o o t$	√	√	√
$t t i p$	√	√	√
$L s t r u t$		√	√
$C s t r u t$		√	√
$t s t r u t$		√	√
$V H$			√
$L H$			√

Table 2

Fig.5

Fig.6

Fig.7

Table 3

Fig.8

Fig.9

Fig.10

Fig.11

Fig.12

Table 4

Fig.13

Fig.14

Fig.15

Fig.16

Table 5

Variables for prototype and candidate design

设计变量	原型机	方案D	方案E	方案F
$L w i n g$ /mm	4 600	4 787.04	4 802.79	4 990.82
$C w i n g$ /mm	423	457.75	459.17	459.18
$t r o o t$ /mm	2.03	5.05	5.03	4.63
$t t i p$ /mm	1.23	1.03	1.02	0.94
$L s t r u t$ /mm	1 375	1 983.73	1 985.04	2 897.97
$C s t r u t$ /mm	120	118.57	111.47	118.65
$t s t r u t$ /mm	3.21	2.36	2.46	2.35
$V H$ /L	6.8	5.0	10.00	10.00
$L H$ /mm	200	374.11	374.11	238.99

Table 5

Table 6

Table 7

References 24

1	刘莉，曹潇，张晓辉，等. 轻小型太阳能/氢能无人机发展综述［J］. 航空学报， 2020， 41（3）： 623474.
	LIU L， CAO X， ZHANG X H， et al. Review of development of light and small scale solar/hydrogen powered unmanned aerial vehicles［J］. Acta Aeronautica et Astronautica Sinica， 2020， 41（3）： 623474 （in Chinese）.
2	TAN C Q， SUN F C， KONG T， et al. A survey on deep transfer learning［C］∥Artificial Neural Networks and Machine Learning-ICANN 2018. Cham： Springer International Publishing， 2018： 270-279.
3	强碧瑶，史恺宁，任学军，等. 基于实例迁移学习的跨工况刀具剩余寿命预测［J］. 航空学报， 2024， 45（13）： 629038.
	QIANG B Y， SHI K N， REN J X， et al. Instance transfer for tool remaining useful life prediction cross working conditions［J］. Acta Aeronautica et Astronautica Sinica，2024， 45（13）： 629038 （in Chinese）.
4	廖奕校. 基于多源域知识迁移的旋转机械智能故障诊断方法研究［D］. 广州：华南理工大学， 2022.
	LIAO Y X. Research on intelligent fault diagnosis method of rotating machinery based on multi-source domain knowledge transfer［D］. Guangzhou： South China University of Technology， 2022 （in Chinese）.
5	GUPTA L， EDELEN A， NEVEU N， et al. Improving surrogate model accuracy for the LCLS-II injector frontend using convolutional neural networks and transfer learning［J］. Machine Learning： Science and Technology， 2021， 2（4）： 045025.
6	TIAN K， LI Z C， ZHANG J X， et al. Transfer learning based variable-fidelity surrogate model for shell buckling prediction［J］. Composite Structures， 2021， 273： 114285.
7	PENG L， WU H， GAO M， et al. TLT： Recurrent fine-tuning transfer learning for water quality long-term prediction［J］. Water Research， 2022， 225： 119171.
8	SEO W， PARK S W， KIM N， et al. A personalized blood glucose level prediction model with a fine-tuning strategy： A proof-of-concept study［J］. Computer Methods and Programs in Biomedicine， 2021， 211： 106424.
9	NASIR M U， GHAZAL T M， KHAN M A， et al. Breast cancer prediction empowered with fine-tuning［J］. Computational Intelligence and Neuroscience， 2022， 2022（1）： 5918686.
10	YANG D， LIU L， BAI W C， et al. Conceptual design and configurations selection of S/H-UAVs based on Q-rung dual hesitant double layer FQFD［J］. Chinese Journal of Aeronautics， 2024， 37（9）： 193-205.
11	LIU L， BAI W C， YANG D. Flight endurance increasing technology of new energy UAV based on a strut-braced wing［J］. International Journal of Aerospace Engineering， 2022， 2022（1）： 4868037.
12	蔚光辉. 绿色能源小型电动无人机总体设计［D］. 北京：北京理工大学， 2018.
	YU G H. Overall design of small electric UAV with green energy［D］. Beijing： Beijing Institute of Technology， 2018 （in Chinese）.
13	GE W F， YU Y Z. Borrowing treasures from the wealthy： Deep transfer learning through selective joint fine-tuning［C］∥2017 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2017： 10-19.
14	PAN S J， TSANG I W， KWOK J T， et al. Domain adaptation via transfer component analysis［J］. IEEE Transactions on Neural Networks， 2011， 22（2）： 199-210.
15	LI W， DUAN L X， XU D， et al. Learning with augmented features for supervised and semi-supervised heterogeneous domain adaptation［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2014， 36（6）： 1134-1148.
16	BAO R X， SUN Y M， GAO Y H， et al. A recent survey of heterogeneous transfer learning［EB/OL］. arXiv preprint： 2310.08459， 2023. .
17	GONG B Q， SHI Y， SHA F， et al. Geodesic flow kernel for unsupervised domain adaptation［C］∥2012 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE Press， 2012： 2066-2073.
18	BORGWARDT K M， GRETTON A， RASCH M J， et al. Integrating structured biological data by kernel maximum mean discrepancy［J］. Bioinformatics， 2006， 22（14）： e49-57.
19	GRETTON A， SRIPERUMBUDUR B， SEJDINOVIC D， et al. Optimal kernel choice for large-scale two-sample tests［C］∥Proceedings of the 26th International Conference on Neural Information Processing Systems-Volume 1. New York： ACM， 2012： 1205-1213.
20	RUMELHART D E， HINTON G E， WILLIAMS R J. Learning representations by back-propagating errors［J］. Nature， 1986， 323（6088）： 533-536.
21	HINTON G. Deep belief networks［J］. Scholarpedia， 2009， 4（5）： 5947.
22	SCABINI L F S， BRUNO O M. Structure and performance of fully connected neural networks： Emerging complex network properties［J］. Physica A： Statistical Mechanics and Its Applications， 2023， 615： 128585.
23	DEB K， JAIN H. An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach， Part II： Handling Constraints and Extending to an Adaptive Approach［J］. IEEE Transactions on Evolutionary Computation， 2014， 18（4）： 602-622.
24	LI K， DEB K， ZHANG Q F， et al. An evolutionary many-objective optimization algorithm based on dominance and decomposition［J］. IEEE Transactions on Evolutionary Computation， 2015， 19（5）： 694-716.

层	参数尺寸	激活函数	是否添加Dropout
I0	9
D1	15	ReLU
D2	30	ReLU
D3	18	ReLU
D4	6	ReLU	是（0.1）
O5	3	ReLU
R6

参数	预训练	微调
最大迭代次数	2 000	7 000
初始学习率	0.001	0.000 1
最小批大小	4	4
学习率乘法纪元数	800	900
学习率乘法因子	0.6	0.975

指标	原型机	方案D	方案E	方案F
升阻比	20.66	23.809	23.800	23.546
起飞质量/kg	21.519	21.372	21.373	21.194
航时/h	11.359	12.007	22.068	22.496

输出	升阻比	起飞质量/kg	航时/h
误差/%	0.87	1.50	0.19
优化	23.546	21.194	22.496
实际	23.343	20.881	22.453

[1]	Weiwei CAI, Guohua WU, Hengwei LI, Qian YIN. Multi-objective scheduling optimization method for relay satellites considering user preferences [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(8): 331074-331074.
[2]	Yunwen FENG, Da TENG, Cheng LU, Rui WANG, Junyu CHEN. Integrated mechanism and generative adversarial surrogate modeling for aircraft systems reliability evaluation [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(7): 230948-230948.
[3]	Yifan WANG, Xiyun GUO, Shiyuan JIA, Gang CHEN, Mo REN. Configuration optimization method of three-branch robot for truss holding [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(7): 431033-431033.
[4]	Kaishang LI, Haoqi FAN, Runzi WANG, Xiancheng ZHANG, Shantung TU. Life design method of high-temperature equipment based on dual-scale damage theory [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(5): 531706-531706.
[5]	Yang JIAO, Yuting LU, Ba XU, Jian OUYANG. Transfer prediction of satellite traffic based on spatiotemporal correlation [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(4): 330938-330938.
[6]	Yuxin CUI, Zhong LU, Jia ZHOU. Development assurance level assignment based on multi-objective artificial hummingbird algorithm [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(4): 330946-330946.
[7]	Lulu JIANG, Xin PAN, Wei JIANG, Rui FENG, Gang CHEN. Optimization shape design of capsule-supersonic parachute system based on fusion surrogate strategy [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(1): 630471-630471.
[8]	Zichao LIU, Jiang WANG, Peng WANG, Defu LIN, Zhichuan HE. Time-constrained multi-missile cooperative guidance law [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(S1): 730607-730607.
[9]	Zhuangzhuang CUI, Xin YUAN, Guoqing ZHAO, Simeng JING, Qijun ZHAO. Influence of control strategy on forward flight performance of coaxial rigid rotor high⁃speed helicopters [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(9): 529256-529256.
[10]	Jiaqi LIU, Rongqian CHEN, Jinhua LOU, Xu HAN, Hao WU, Yancheng YOU. Aerodynamic shape optimization of high-speed helicopter rotor airfoil based on deep learning [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(9): 529828-529828.
[11]	Shusheng CHEN, Cong FENG, Zhaokang ZHANG, Ke ZHAO, Xinyang ZHANG, Zhenghong GAO. Aerodynamic design of wide-speed-range waverider-wing configuration based on global & gradient optimization method [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(6): 629596-629596.
[12]	Yuhan LI, Baoyu YANG, Yinong WU, Qiang ZHANG, Xiao TANG. Research on parameters correction method for thermal model of satellite optomechanical load [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(6): 628814-628814.
[13]	Jiang CUI, Fan ZHOU, Yongfan CHEN, Li YU, Zhuoran ZHANG. A technique for aerospace generator rectifier fault diagnosis based on GAMF-CNN [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(24): 330398-330398.
[14]	Wei WANG, Weigang AN, Bifeng SONG, Wenqing YANG. Dynamic soaring performance of albatross-inspired morphing wing [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(24): 630576-630576.
[15]	Chengjun SHAN, Tianyu GONG, Lizhe YI, Haohui YANG, Yaosong LONG. High-efficiency and high-reliability sonic boom/aerodynamic multidisciplinary optimization method for supersonic civil aircraft [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(24): 630573-630573.

Optimal design of hydrogen-powered UAV based on multi-source domain fusion surrogate model

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 23

References 24

Related Articles 15

Recommended Articles

Metrics

Comments