Optimal Selection of UAV Launch Parameters Based on SSA-BP Neural Network

doi:10.12141/j.issn.1000-565X.230781

Abstract

Abstract:

Rocket assisted zero length launch is an important form of UAV launch. The selection of launch parameters such as launch angle, booster angle, and booster thrust directly affects the success or failure of UAV launch mission. In the design phase of unmanned aerial vehicle rocket assisted zero length launch, key parameters such as launch angle, booster angle, and booster thrust are selected based on engineering experience. However, this approach faces several challenges, including long iteration cycles for optimal parameter selection, poor design interactivity, and the potential risk of causing instability in the UAV’s flight posture. This study focused on a specific UAV and conducts dynamic and kinematic modeling of its launch phase, constructing a six-degree-of-freedom nonlinear model. A UAV launch trajectory parameterization simulation software was developed using QT/C++ software, and the software’s effectiveness was verified through comparison with real UAV launch test data. At the same time, in order to solve the problem of autonomous optimization of launch parameters, sparrow search algorithm (SSA), particle swarm optimization algorithm (PSO), and genetic algorithm (GA) optimization modules were introduced based on the backpropagation neural network (BP neural network) parameter prediction model. A UAV launch parameter optimization method based on SSA optimized BP neural network was proposed to eliminate the overfitting and local optimal effects of BP neural network in the parameter prediction process. The absolute error (MAE), average percentage error (MAPE), and root mean square error (RMSE) of the parameter prediction results were calculated to comprehensively evaluate the superiority of SSA-BP in predicting launch parameters, and the rationality of the launch parameter selection was verified through launch trajectory verification. The results indicate that the SSA-BP model has the highest prediction accuracy and robustness for launch parameters, and can provide a design basis for the autonomous selection of launch parameters in the engineering design stage of unmanned aerial vehicle launch subsystems.

Key words: UAV launch, sparrow search algorithm, BP neural network, parameter optimization, modeling and simulation

CLC Number:

V553

JIA Huayu, ZHENG Huilong, ZHOU Hong, ZHANG Qian. Optimal Selection of UAV Launch Parameters Based on SSA-BP Neural Network[J]. Journal of South China University of Technology(Natural Science Edition), 2025, 53(4): 90-101.

Figures/Tables 13

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Table 2

Table 1

Table 3

Initial parameterization of the meritocracy module"

算法

参数

数值

SSA算法

初始麻雀种群数量

最大迭代次数

鸟群预警值

发现者占比

反捕食麻雀占比

100

0.8

0.4

0.3

PSO算法

初始种群规模

最大迭代次数

加速常数 $C 1$

加速常数 $C 2$

惯性权重

100

1.5

0.8

GA算法

初始种群规模

最大进化代数

交叉概率

变异概率

染色体编码长度

100

0.7

0.6

Table 3

Fig.7

Fig.8

Fig.9

Fig.10

References 28

1	YIN J， LI W， ZHAO L，et al ． Simulation and analysis of UAV zero-length launch with rocket booster［J］．Advances in Guidance， Navigation and Control，2022，644：3635-3645.
2	YIN J， ZHANG B， ZHAO L，et al ．Simulation and analysis of short rail launch for UAV with rocket booster［C］∥Proceedings of 2020 3rd International Conference on Unmanned Systems （ICUS）．Shanghai：IEEE，2020.
3	LIU B， FANG Z， LI P，et al ．Takeoff analysis and simulation of a small scaled UAV with a rocket booster［J］．Advanced Materials Research， 2011，1286（267）：674-682.
4	PAKE G M， ANVAR A ．A feasibility study of design and development of submersible tube launched UAV-robot［C］∥Proceedings of 2014 13th International Conference on Control， Automation， Robotics & Vision． Singapore：IEEE，2014：1615-1620.
5	ZHU Z， GUO H， MA J ．Aerodynamic layout optimization design of a barrel-launched UAV wing considering control capability of multiple control surfaces［J］．Aerospace Science and Technology， 2019，93：105297/1-12.
6	LIU Q， BAO J， Shao Y， et al ．Dynamic modeling and underwater configuration analysis of fiber optic cable for UUV-launched UAV［J］．Ocean Engineering，2024，303，117774/1-15.
7	ZHOU Q B， RUI X T， WANG G P，et al ．An efficient and modular modeling for launch dynamics of tubed rockets on a moving launcher［J］．Defence Technology， 2021， 17（6）：2011-2026.
8	LU J X， WANG C， WEI Y J， et al ．Experimental and theoretical investigation of the cavity dynamics of underwater launched projectiles［J］．Ocean Engineering，2022，254，111291/1-12.
9	李浩，肖前贵，胡寿松．火箭助推无人机起飞发射段建模与仿真［J］．东南大学学报（自然科学版），2010，40（S1）：136-139.
	LI Hao， XIAO Qiangui， HU Shousong ．Modeling and simulation of UAV launching by rocket booster process［J］．Journal of Southeast University（Natural Science Edition）， 2010， 40（S1）： 136-139 .
10	LIU X L， XIA C N， MA S G ．The modeling and simulation of UAV pneumatic launch system［J］．Applied Mechanics and Materials， 2013， 2306（299）：27-30.
11	GÖKBEL E， GÜELLÜ A， ERSOY S ．Improvement of UAV： design and implementation on launchability［J］．Aircraft Engineering and Aerospace Technology， 2023， 95（5）： 734-740.
12	赵志俊，拜莉莎，孟祥喆．基于试验设计的无人机火箭助推起飞参数敏感性分析与优化［J］．飞行力学，2024，42（1）：89-94.
	ZHAO Zhijun， BAI Lisha， MENG Xiangzhe ．Sensitivity analysis and optimization of UAV rocket booster launch parameters based on DOE［J］．Flight Dynamics， 2024，42（1）：89-94.
13	何丽莎，郑耀，解利军，等．环境风对特定无人机零长发射安全性的影响［J］．哈尔滨工程大学学报， 2019，40（7）：1201-1207．
	HE Lisha， ZHENG Yao， XIE Lijun， et al ．Influence of environmental wind on the safety of a specific UAV zero-length launch［J］．Journal of Harbin Engineering University， 2019，40（7）：1201-1207．
14	贺跃帮，裴海龙，叶祥，等．无人直升机的自适应动态面轨迹跟踪控制［J］．华南理工大学学报（自然科学版），2013，41（5）：1-8.
	HE Yue-bang， PEI Hai-long， YE Xiang， et al ．Trajectory tracking control of unmanned helicopter by using adaptive dynamic surface approach［J］．Journal of South China University of Technology（Natural Science Edition）， 2013，41（5）：1-8.
15	WENG L， LIU Q， XIA M， et al ．Immune network-based swarm intelligence and its application to unmanned aerial vehicle （UAV） swarm coordination［J］．Neurocomputing， 2014， 125（11）：134-141.
16	李林洋，徐天河，王君婷，等．联合匹配场和神经网络的声速时间场构建方法［J］．哈尔滨工程大学学报，2023，44（11）：2044-2053.
	LI Linyang， XU Tianhe， WANG Junting，et al ．A method for constructing sound velocity time field by combining matched field and neural network ［J］．Journal of Harbin Engineering University，2023，44（11）：2044-2053.
17	党婉莹，周乐来，李贻斌，等．模块化机器人最优越野构型神经网络规划方法［J］．兵工学报，2024，45（10）：3674-3685.
	DANG Wanying， ZHOU Lelai， LI Yibin， et al ．Neural network planning method for optimal off-road configuration of　modular robots［J］．Acta Armamentarii，2024，45（10）：3674-3685.
18	张香竹，张立家，宋逸凡，等．基于深度学习的无人机单目视觉避障算法［J］．华南理工大学学报（自然科学版），2022，50（1）：101-108，131.
	ZHANG Xiangzhu， ZHANG Lijia， SONG Yifan，et al ．Obstacle avoidance algorithm for unmanned aerial vehicle vision based on deep learning ［J］．Journal of South China University of Technology （Natural Science Edition）， 2022，50（1）：101-108，131.
19	JIANG W， WANG Z， LI S ．An adaptive RK-UKF projectile impact point prediction method based on strong tracking filter［C］∥Proceedings of 2020 9th Asia-Pacific Conference on Antennas and Propagation （APCAP）．Xiamen：IEEE， 2020.
20	ZHANG X， YAO X， ZHENG Q ．Impact point prediction guidance based on iterative process for dual-spin projectile with fixed canards［J］．Chinese Journal of Aeronautics，2019，32（8）：1967-1981.
21	赵捍东，李志鹏．基于径向基函数神经网络和无迹卡尔曼滤波的弹丸落点预报方法研究［J］．兵工学报，2014，35（7）：965-971.
	ZHAO Han-dong， LI Zhi-peng ．Research on impactpoint prediction method based on radial basis function neural network and unscented Kalman filter ［J］．Acta Armamentarii， 2014，35（7）：965-971.
22	LI Z M， LIN T， MA Y H，et al ．Research on coordinated charging of electric vehicle based on GA-BP power quality prediction［C］∥Proceedings of the 2015 International Conference on Electronics， Electrical Engineering and Information Science．Xiamen： World Scientific Publishing Co Pte Ltd，2016.
23	XUE J， SHEN B ．A novel swarm intelligence optimization approach： sparrow search algorithm［J］．Systems Science & Control Engineering， 2020， 8（1）：22-34.
24	WANG X， LIU J， HOU T，et al ．The SSA-BP-based potential threat prediction for aerial target considering commander emotion［J］．Defence Technology，2022，18（11）：2097-2106.
25	XIN J， CHEN J， LI C，et al ．Deformation characterization of oil and gas pipeline by ACM technique based on SSA-BP neural network model［J］．Measurement，2022，189：110654/1-22.
26	WANG J， SHENG Z， ZHOU B，et al ．Lightning potential forecast over Nanjing with denoised sounding-derived indices based on SSA and CS-BP neural network［J］．Atmospheric Research， 2014， 137（12）： 245-256.
27	张福生，潘学文，路超．基于SSA优化BP神经网络的故障诊断系统研究［J］．中国工程机械学报，2022，20（1）：81-85，90.
	ZHANG Fusheng， PAN Xuewen， LU Chao ．Research on fault diagnosis system based on SSA optimized BP neural network ［J］．Chinese Journal of Construction Machinery， 2022，20（1）：81-85，90.
28	陈亮，郝祎纯，李巧茹，等．改进SSA优化的BP神经网络交通量预测模型［J］．哈尔滨工业大学学报，2024，56（7）：94-101.
	CHEN Liang， HAO Yichun， LI Qiaoru， et al ．Traffic volume forecast model based on BP neural network optimized by improved sparrow search algorithm ［J］．Journal of Harbin Institute of Technology， 2024，56（7）：94-101.

序号	高度/m	速度/（m·s^-1）	迎角/（°）	弹道倾角/（°）	发射角/（°）	助推器夹角/（°）	助推器推力/N
1	61.000	39.883	29.720	39.674	21	18	8 509
2	206.232	176.959	1.173	36.350	19	25	8 316
3	41.735	34.704	30.176	40.603	18	17	8 144
4	76.127	64.912	24.026	23.070	18	21	8 121
5	194.499	160.357	1.024	35.084	22	23	8 805
6	85.868	59.282	24.734	27.582	22	21	8 033
7	55.682	38.776	30.039	41.585	19	17	8 958
8	77.065	46.417	28.369	34.893	24	20	8 010
9	189.873	171.949	0.849	35.879	20	24	8 221
10	199.665	149.531	1.509	35.024	23	24	8 932
11	69.086	48.674	28.569	32.600	20	20	8 248
12	227.347	193.106	1.223	36.611	17	24	8 840
13	38.458	34.039	30.377	41.846	17	16	8 350
14	218.756	191.311	1.145	36.436	18	23	8 905
15	150.330	117.245	1.003	29.923	24	21	8 725
16	52.266	38.367	30.044	41.371	18	17	8 969
17	87.686	53.459	26.935	32.077	24	20	8 275
18	81.288	68.997	23.415	22.675	18	20	8 572
19	178.501	155.609	0.573	34.557	22	23	8 436
20	56.606	44.227	29.313	35.181	17	19	8 641
21	84.202	64.957	22.850	24.263	20	21	8 113
22	181.794	180.563	0.575	35.964	19	23	8 214
23	211.378	200.502	1.020	36.658	17	22	8 849
24	77.934	47.182	28.788	35.885	23	19	8 507
25	84.434	56.961	27.685	30.962	21	19	8 873
26	197.361	180.563	0.829	35.737	20	22	8 857
27	62.621	200.502	29.728	39.951	22	18	8 400
28	212.723	47.182	1.072	36.925	16	23	8 531
29	238.443	56.961	1.281	36.672	16	25	8 935
30	46.227	180.119	30.700	44.747	20	15	8 458

参数名称	数值
质量/kg	230
纵向转动惯量/（kg·m²）	236.5
发动机推力/daN	150
发射段升力系数	0.1
发射段阻力系数	0.015
俯仰力矩系数	0.2

[1]	WANG Qingrong, WANG Junjie, ZHU Changfeng, HAO Fule. Carbon Emission Prediction in Transportation Industry Based on SD-ISSA-DALSTM [J]. Journal of South China University of Technology(Natural Science Edition), 2025, 53(5): 66-81.
[2]	HE Yongming, XING Wanyu, WEI Kun, et al. Lane-Changing Trajectory Planning Strategy for Autonomous Vehicles on Superhighways [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(4): 104-113.
[3]	ZHU Rui, LIU Yu, LIANG Yuying, et al. BP Neural Network Prediction Model for Turbulent Noise Intensity in Gas/Water Medium [J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(12): 119-126.
[4]	NIE Jiamei, HUANG Xiaorong, ZHANG Xiaoliang, et al. Network Synthesis Design Method of Nonlinear Mem-inerter Suspension System [J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(9): 78-89.
[5]	HE Yuanfu, XIA Yimin, LI Shenyuan, et al. Transmission Performance Analysis and Optimization Design of Grasping Module of Steel Arch Looping Mechanism [J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(8): 82-91.
[6]	LAN Fengchong, ZHANG Yue, CHEN Jiqing, et al. Correlation Analysis and Prediction of Pedestrian Casualty Risk in Car-Pedestrian Collision Accident [J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(5): 1-10.
[7]	ZHOU Zhong, DENG Zhuoxiang, CHEN Yun, et al. Strength Prediction of Foam Light Soil Based on GA-BP Neural Network [J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(11): 125-132.
[8]	JI Tianyao WANG Tingshao. Building Energy Consumption Prediction Based on Word Embedding and Convolutional Neural Network [J]. Journal of South China University of Technology(Natural Science Edition), 2021, 49(6): 40-48.
[9]	ZHANG Yirui SU Jian XU Guan. Research on Coupling Effect Experiment and Decoupling Method of 3-D Force Measuring Platform [J]. Journal of South China University of Technology (Natural Science Edition), 2021, 49(5): 135-144.
[10]	YANG Chun, LI Penglin, XIONG Shuai, et al. Analysis of Monitoring Data of a Long-Span Steel Roof Based on BIM and BP Neural Network [J]. Journal of South China University of Technology (Natural Science Edition), 2020, 48(9): 10-19.
[11]	CHEN Songmao CHEN Yulin. Optimization of Fused Deposition Modeling Process Parameters Based on Different Part Dimensions and Assessment Indexes [J]. Journal of South China University of Technology (Natural Science Edition), 2020, 48(8): 130-138.
[12]	WANG Yihong, ZHANG Jianxiong, LAN Guanqi, et al. Artificial Neural Network Prediction Model for Compressive Strength of Compacted Earth Blocks [J]. Journal of South China University of Technology (Natural Science Edition), 2020, 48(7): 115-121.
[13]	ZUO Shuguang LI Duoqiang MAO Yu WU Xudong . Longitudinal Dynamic Analysis and Parameter Optimization of Electric Vehicle Driven by In-wheel Motor [J]. Journal of South China University of Technology (Natural Science Edition), 2018, 46(2): 65-72.
[14]	NIU Haiqing WU Juzhuo GUO Shaofeng. Application of Singular Value Decomposition to Pattern Recognition of Partial Discharge in Cable [J]. Journal of South China University of Technology (Natural Science Edition), 2018, 46(1): 26-32.
[15]	BAO Dan-wen LIU Jian-rong GU Jia-yu . Optimization Model of Airport Bus Line Network Reliability and Algorithm Design [J]. Journal of South China University of Technology (Natural Science Edition), 2017, 45(8): 84-91.