Prelaunch rolling suppression for maritime rockets using RF-AdaBoost

doi:10.23919/JSEE.2026.000048

Abstract

Abstract:

Prelaunch rolling of maritime rockets threatens the reliability of launch in rough sea conditions. In order to suppress the prelaunch rolling, this study introduces advanced smart prediction designed especially for maritime rockets. The suggested approach introduces a hybrid model that combines random forest (RF) and Adaptive boosting （AdaBoost） methods to describe the coupling mechanism of factors affecting rocket rolling and to suppress the rolling. This combination improves forecast accuracy. Thereafter, the dimensionality reduced response surfaces are used to visually present the coupling between rocket rolling and influencing factors, which reveals the prelaunch rolling mechanism. When angle between the launch device and the ship’s bow is within 80°?100°, the dynamic friction coefficient between adapters and guideways is 0.4, and the dynamic friction coefficient between the rocket and launchpad is within 0?0.15 or 0.5?0.7, the prelaunch rolling of rocket during one motion cycle of the ship is less than 0.065°, originally 0.27°, reduced by 75.93%, effectively suppressing the prelaunch rolling. This study improves the prelaunch stability of maritime rockets in rough sea conditions and establishes a mapping relationship between the factors affecting rocket rolling and the structure of the sea launch system, guiding the optimization of future sea launch systems.

Key words: prelaunch rolling, maritime rocket, maritime dynamic platform, rolling suppression, random forest (RF)-AdaBoost

Deng WANG, Wenhao XIAO, Jianshuai SHAO, Yi JIANG. Prelaunch rolling suppression for maritime rockets using RF-AdaBoost[J]. Journal of Systems Engineering and Electronics, 2026, 37(1): 197-210.

Figures/Tables 20

Fig 1

Fig 2

Fig 3

Fig 4

Fig 5

Fig 6

Table 1

Table 2

Table 3

Fig 7

Fig 8

Fig 9

Fig 10

Fig 11

Fig 12

Fig 13

Table 4

Fig 14

Fig 15

Fig 16

References 40

1	ILCEY S D. Spacecraft launching technique and systems. Proc. of the International Conference on Electrical, Electronics, and Optimization Techniques, 2016: 4514–4517.
2	SONG Z Y, XIE Z F, QIU L M, et al Prospects of sea launches for Chinese cryogenic liquid-fueled medium-lift launch vehicles. Chinese Journal of Aeronautics, 2021, 34 (1): 424- 437. doi: 10.1016/j.cja.2020.06.018
3	XIAO N, XIAO L T, ZHANG F L, et al. An architecture of cross-domain support system for multiple space command and control platforms. Proc. of the IEEE Aerospace Conference, 2021. DOI 10.1109/AERO50100.2021.9438270.
4	CARNEAL L C R, CHANG R. Sea-launched TacSats for responsive space (STaRS). Proc. of the 7th Responsive Space Conference, 2009: AIAA-RS7-2009-1007.
5	TUTUREA D, RAJABI F. Ocean launch facility concept design. Proc. of the Advanced Marine Vehicles Conference, 1989: 536−547.
6	ZHONG Z, JIANG Y, LI Y Y, et al. Dynamic simulation analysis of shipborne missile launching under high-wave-level environment. Proc. of the International Conference on Advanced Materials Design and Mechanics, 2012: 380–385.
7	ZENG W, JIANG Y Launching dynamics simulation of ship-board rocket gun. Advanced Materials Research, 2012, 625 (12): 140- 145. doi: 10.4028/www.scientific.net/amr.625.140
8	KONYUKHOV S N Applied mechanics problems accompanying spacecraft launches from a floating platform and their resolution. International Applied Mechanics, 2004, 40 (2): 115- 139. doi: 10.1023/b:inam.0000028591.66544.e4
9	WANG D, XIAO W H, SHAO J S, et al. Rolling mechanism of launch vehicle during the prelaunch phase in sea launch. Aerospace, 2024, 11(5): 399.
10	LEE J J Legal analysis of sea launch license: national security and environmental concerns. Space Policy, 2008, 24 (2): 104- 112. doi: 10.1016/j.spacepol.2008.02.002
11	FINGER G, MOORE S, GULLIVER B Implementing operationally responsive launch sites. Proc. of the SpaceOps 2010 Conference, 2010. doi: 10.2514/6.2010-2236
12	DONG Y P, QU M H, SU C Q, et al. Dynamic simulation of shipborne vertical launching system under high wave level. Proc. of the International Conference on Advanced Manufacturing, Computation and Optimization, 2019: 422−427.
13	LIU X B, WANG Y Y, LIU X H. Review of marine satellite launch platform and related study at JUST. Proc. of the International Conference on Marine Equipment & Technology and Sustainable Development, 2023: 579–590.
14	XU W J, XU G, NIU G C, et al. The study of the motion of the satellite launching platform with different shape of pontoons. Proc. of the International Conference on Marine Equipment & Technology and Sustainable Development, 2023: 303–315.
15	PANG F Z, QIN Y X, TANG Y, et al Experimental study on impact response of seaborne rocket launch platform. Ocean Engineering, 2023, 280 (14): 114623. doi: 10.1016/j.oceaneng.2023.114623
16	WANG D, SHAO J S, CHEN M, et al Sea launch adapter response in rough sea conditions considering strain rate effects. Journal of Physics: Conference Series, 2023, 2508 (1): 012027. doi: 10.1088/1742-6596/2508/1/012027
17	SU Y F, LU X X, LE G G, et al Numerical simulations of seawater spraying on launch platform during CZ-8X offshore launching. Advances in Space Research, 2023, 72 (9): 3631- 3644. doi: 10.1016/j.asr.2023.07.021
18	MU R J, ZHANG T F, LI S P. A rapid self-alignment strategy for a launch vehicle on an offshore launching platform. Sensors-Basel, 2022, 23(1): 339: 1−21.
19	XIONG Z X, ZHU C Y, YANG Y, et al XFEM-based study of fatigue crack propagation in rocket deflector troughs under coupled high-temperature and impact conditions. Journal of Marine Science and Engineering, 2024, 12 (2): 207. doi: 10.3390/jmse12020207
20	GONG Q T, LIU Z P, HU X, et al Robust anti-disturbance fault-tolerant control of ship-board platforms with multiplicative actuator faults and unknown disturbances. Ocean Engineering, 2023, 286, 115552. doi: 10.1016/j.oceaneng.2023.115552
21	TIN K H The random subspace method for constructing decision forests. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1998, 20 (8): 832- 844. doi: 10.1109/34.709601
22	ELSHEIKH A H Applications of machine learning in friction stir welding: prediction of joint properties, real-time control and tool failure diagnosis. Engineering Applications of Artificial Intelligence, 2023, 121 (5): 105961. doi: 10.1016/j.engappai.2023.105961
23	HU J C, SZYMCZAK S A review on longitudinal data analysis with random forest. Briefings in Bioinformatics, 2023, 24 (2): bbad002. doi: 10.1093/bib/bbad002
24	ADNAN R M, SADEGHIFAR T, ALIZAMIR M, et al Short-term probabilistic prediction of significant wave height using bayesian model averaging: case study of Chabahar Port, Iran. Ocean Engineering, 2023, 272 (1): 113887. doi: 10.1016/j.oceaneng.2023.113887
25	WANG Y H, CHEN W, SONG J, et al. Open set radar HRRP recognition based on random forest and extreme value theory. Proc. of the International Conference on Radar, 2018: 27−31.
26	FREUND Y, SHAPIRE R E. Experiments with a new boosting algorithm. Proc. of the International Conference on Machine Learning, 1996: 6–15.
27	WU C M, WANG X D, ZHENG C Y. Classifying HRRP by AdaBoost SVM. Proc. of the 9th International Conference on Signal Processing, 2008: 1582–1585.
28	ZHANG F, WANG Y C, NI J, et al SAR target small sample recognition based on CNN cascaded features and AdaBoost rotation forest. IEEE Geoscience and Remote Sensing Letters, 2020, 17 (6): 1008- 1012. doi: 10.1109/LGRS.2019.2939156
29	AMIN M N, IFTIKHAR B, KHAN K, et al Prediction model for rice husk ash concrete using AI approach: boosting and bagging algorithms. Structures, 2023, 50 (4): 745- 757. doi: 10.1016/j.istruc.2023.02.080
30	EKANAYAKE I U, MEDDAGE D P P, RATHNAYAKE U A novel approach to explain the black-box nature of machine learning in compressive strength predictions of concrete using Shapley additive explanations (SHAP). Case Studies in Construction Materials, 2022, 16 (6): e01059. doi: 10.1016/j.cscm.2022.e01059
31	AHMAD A, AHMAD W, ASLAM F, et al Compressive strength prediction of fly ash-based geopolymer concrete via advanced machine learning techniques. Case Studies in Construction Materials, 2022, 16 (5): e00840. doi: 10.1016/j.cscm.2021.e00840
32	WEI M M, LU H X, YANG H H Research on boold species identification algorithm based on RF-AdaBoost model. Chemical Journal of Chinese Universities, 2020, 41 (1): 94- 101.
33	LAN C F, SONG B W, ZHANG L, et al State prediction of hydro-turbine based on WOA-RF-Adaboost. Energy Reports, 2022, 8 (11): 13129- 13137. doi: 10.1016/j.egyr.2022.09.142
34	WANG X R, ZHANG C, QIANG Z P, et al A new forest growing stock volume estimation model based on AdaBoost and random forest model. Forests, 2024, 15 (2): 260. doi: 10.3390/f15020260
35	ZHANG W, LIU J J, LIU W, et al Smart dragon 3 launch vehicle system. Aerospace China, 2022, 23 (4): 3- 10.
36	ZHANG E H LM-11 performs a sea-launch mission successfully. Aerospace China, 2020, 21 (3): 57.
37	SHANG H, LIU B, MENG X, et al LM-11SL: a sea-launched carrier rocket for small satellites and its launch service. Aerospace China, 2018, 19 (2): 22- 29.
38	APOSTOL A, CONSTANTINESCU D M Influence of speed of testing and temperature on the behaviour of polyurethane foams. The Romanian Journal of Technical Sciences. Applied Mechanics, 2012, 1 (57): 27- 61.
39	APOSTOL D A, CONSTANTINESCU D M Temperature and speed of testing influence on the densification and recovery of polyurethane foams. Mechanics of Time-Dependent Materials, 2013, 17 (1): 111- 136. doi: 10.1007/s11043-012-9179-8
40	CONSTANTINESCU D M, APOSTOL D A Performance and efficiency of polyurethane foams under the influence of temperature and strain rate variation. Mechanics of Time-Dependent Materials, 2020, 29, 3016- 3029.

Parameter	Value	Moment of inertia	Value
Length/m	30.888	I_xx/(kg·m²)	5010 550
Mass/kg	120 000	I_yy/(kg·m²)	5010 550
Distance from the center of mass to the nose cone tip/m	21.043	I_zz/(kg·m²)	101 123

Parameter	Strain rate/s
Parameter	0.0028	0.0756	0.7003	8.4034	28.0112	504.2016
y₀	−0.06979	−0.26674	−0.36169	−0.79306	−1.1871	−79.81828
ε_c	0.06119	0.06432	0.06731	0.06944	0.06935	0.07146
ω	0.05669	0.09666	0.09877	0.12105	0.1056	0.14048
A	4.87821	5.59774	6.25682	7.42643	7.98074	91.01336
A₁	1.14704	1.79238	1.81942	1.96374	1.28445	0.35962
A₂	−0.72626	−1.05261	−2.08598	−1.29507	−0.55306	−0.45419
A₃	0.78345	3.6199	3.13786	3.51804	1.00361	0.22962

Parameter	Strain rate/s
Parameter	0.0028	0.0756	0.7003	8.4034	28.0112	504.2016
σ_p	4.26440	5.02810	5.09074	5.83828	7.51987	8.22078
B₁	2.03×10⁻⁴	0.00158	1.94×10⁻⁴	0.00308	0.01466	0.0023
t₁	−0.07285	−0.09469	−0.07255	−0.10200	−0.1374	−0.09815
B₂	0.11500	1.58×10⁻³	0.06000	3.08×10⁻³	0.01494	0.0023
t₂	−0.23198	−0.09469	−0.19158	−0.10185	−0.13740	−0.09815

Data set	R²/%	R	RMSE	MSE	MAE	RPD/%
Training set	91.6909	0.9625	0.0169	0.0003	0.0123	10.6831
Testing set	90.7057	0.9563	0.0155	0.0002	0.0124	10.3968