基于NSGA-Ⅲ-SAM算法的冲压发动机喷管性能预测

doi:10.7527/S1000-6893.2024.30910

Abstract

Abstract:

The exhaust characteristics of a nozzle directly affect the overall performance of the scramjet engine. It is crucial to effectively predict the nozzle performance to prevent drastic changes for the stable operation of the engine. Numerical simulations of three-dimensional asymmetric nozzles under different flight conditions were conducted to build a dataset for predicting nozzle performance at various Mach numbers and nozzle pressure ratios. Considering the limitations of traditional multi-objective optimization algorithms， a Non-dominated Sorting Genetic Algorithm-Ⅲ-Simulated Annealing Mutation （NSGA-Ⅲ-SAM） was proposed to extract the optimal wall pressure measurement points for the nozzle. By using the optimal pressure characteristic data as input and the axial thrust coefficient， pitching moment coefficient， and lift coefficient as outputs， a nozzle performance parameter prediction model based on the One Dimension-Convolutional Neural Network （1D-CNN） was established and validated by the data of over-expanded states at the Mach numbers from 4.5 to 6.0. The results show that the optimal pressure positions extracted by the NSGA-Ⅲ-SAM algorithm enable the model to have high-precision and rapid prediction performance， with the overall average absolute error of all performance parameters being within 0.5%， the maximum absolute error not exceeding 0.8%， and the average prediction time being only about 0.6 ms. The proposed prediction model and method provide a reliable technical foundation for monitoring nozzle performance and adjusting exhaust conditions.

Key words: performance prediction, three-dimensional asymmetric nozzle, NSGA-Ⅲ-SAM algorithm, wall-optimized pressure measurement point, 1D-CNN model

CLC Number:

V219

Ke MIN, Zejun CAI, Jiale ZHANG, Chengxiang ZHU. Scramjet nozzle performance prediction based on NSGA-Ⅲ-SAM algorithm[J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(14): 130910.

Figures/Tables 21

Fig.1

Fig.2

Fig.3

Table 1

Fig.4

Fig.5

Fig.6

Fig.7

Table 2

Parameter initialization settings for NSGA-Ⅲ-SAM algorithm

参数	初始化值	参数	初始化值
种群规模 $N p$	91	参考点数 $N d$	91
迭代次数 $n m a x$	200	初始温度 $T 0$	1
交叉率 $p c$	0.9	终止温度 $T f$	0.95
变异率 $p m$	0.05	退火速率 $λ$	0.95

Table 2

Fig.8

Fig.9

Fig.10

Fig.11

Table 3

Results for Pareto frontier optimal individual

算法	最优个体（特征组合）	目标函数（均方误差）
NSGA-Ⅲ算法	$4, 7, 15, 18, 28,30, 42, 45, 46, 49$	［0.287 8%， 0.304 0%， 0.320 5%］^T
NSGA-Ⅲ-SAM算法	$6, 8, 9, 20, 43, 47$	［0.264 2%， 0.247 2%， 0.257 2%］^T

Table 3

Fig.12

Table 4

1D-CNN network structure parameters

序号	网络层类型	核尺寸	通道数	步长	填充操作	输出尺寸
1	上采样层					$50 × 1$
2	卷积层1	$3 × 1$	16	3	是	$50 × 16 × 1$
3	池化层1	$2 × 1$		2	否	$25 × 16 × 1$
4	卷积层2	$3 × 1$	32	3	是	$25 × 32 × 1$
5	池化层2	$2 × 1$		2	否	$12 × 32 × 1$
6	全连接层1					$64 × 1$
7	全连接层2					$3 × 1$

Table 4

Fig.13

Fig.14

Fig.15

Table 5

Metrics statistics of model predictions for test working points

测试工况	平均绝对误差 $ζ / %$			最大绝对误差 $ζ m a x / %$
测试工况	$C T$	$C m$	$C L$	$C T$	$C m$	$C L$
Ma=4.5， NPR=67.83	0.444 8	0.687 2	0.061 0	0.451 2	0.771 3	0.190 9
Ma=5.0， NPR=131.52	0.177 1	0.573 9	0.552 9	0.196 9	0.752 8	0.626 7
Ma=5.5， NPR=240.67	0.077 7	0.633 4	0.626 6	0.105 5	0.712 8	0.682 2
Ma=6.0， NPR=41.09	0.064 9	0.105 0	0.051 6	0.124 4	0.205 9	0.091 5
Ma=4.5~6.0整体	0.191 1	0.499 8	0.323 1	0.451 2	0.771 3	0.682 2

Table 5

Fig.16

References 27

[1]	林鹏，庄福建，曲林锋，等．高超声速飞机尾喷管设计－制造与验证技术发展综述［J］. 航空学报， 2022， 43（6）： 52-62.
	LIN P， ZHUANG F J， QU L F， et al. Technological development in hypersonic nozzle design， manufacture and validation： A review‍［J］. Acta Aeronautica et Astronautica Sinica， 2022， 43（6）： 52-62 （in Chinese）.
[2]	徐惊雷. 超燃冲压及TBCC组合循环发动机尾喷管设计方法研究进展［J］. 推进技术， 2018， 39（10）： 2236-2251.
	XU J L. Research progress of nozzle design method for scramjet and turbine based combined cycle［J］. Journal of Propulsion Technology， 2018， 39（10）： 2236-2251 （in Chinese）.
[3]	LV Z， XU J L， SONG G T， et al. Review on the aerodynamic issues of the exhaust system for scramjet and turbine based combined cycle engine［J］. Progress in Aerospace Sciences， 2023， 143： 1-35.
[4]	LI J P， SONG W Y， XING Y， et al. Influences of geometric parameters upon nozzle performances in scramjets［J］. Chinese Journal of Aeronautics， 2008， 21（6）： 506-511.
[5]	于洋. RBCC单边膨胀喷管过膨胀流动分离现象及机理研究［D］. 南京：南京航空航天大学， 2017.
	YU Y. Study on over-expansion flow separation phenomenon and mechanism of RBCC unilateral expansion nozzle［D］. Nanjing： Nanjing University of Aeronautics and Astronautics， 2017 （in Chinese）.
[6]	HIRAIWA T， TOMIOKA S， UEDA S， et al. Performance variation of scramjet nozzle at various nozzle pressure ratios［J］. Journal of Propulsion and Power， 1995， 11（3）： 403-408.
[7]	晏至辉，刘卫东. 超燃冲压发动机尾喷管数值分析［J］. 导弹与航天运载技术， 2006（5）： 50-52.
	YAN Z H， LIU W D. Numericla simulation to scramjet nozzle’s performance under different external flow condition and nozzle pressure ratio［J］. Missiles and Space Vehicles， 2006（5）： 50-52 （in Chinese）.
[8]	文科，李旭昌，马岑睿，等. 不同入口马赫数对超燃冲压发动机尾喷管的性能影响研究［J］. 火箭推进， 2011， 37（3）： 18-21.
	WEN K， LI X C， MA C R， et al. Influence of nozzle inlet Mach number on performance of scramjet nozzle［J］. Journal of Rocket Propulsion， 2011， 37（3）： 18-21 （in Chinese）.
[9]	文科，李旭昌，马岑睿，等. 超燃冲压发动机尾喷管性能数值模拟研究［J］. 弹箭与制导学报， 2011， 31（5）： 125-128.
	WEN K， LI X C， MA C R， et al. Numerical simulation research on nozzle performance of scramjet［J］. Journal of Projectiles， Rockets， Missiles and Guidance， 2011， 31（5）： 125-128 （in Chinese）.
[10]	全志斌，徐惊雷，李斌，等. 超燃冲压发动机尾喷管非均匀进口的冷流试验与数值模拟［J］. 航空学报， 2013， 34（10）： 2308-2315.
	QUAN Z B， XU J L， LI B， et al. Cold flow experiment and numerical simulation on nonuniform entrance flow of scramjet nozzle［J］. Acta Aeronautica et Astronautica Sinica， 2013， 34（10）： 2308-2315 （in Chinese）.
[11]	LV Z， XU J L， YU K K， et al. Experimental and numerical investigations of a scramjet nozzle at various operations［J］. Aerospace Science and Technology， 2020， 96： 105536.
[12]	SUN Y F， DUAN C X， LI R F， et al. Combined effects of inlet airflow temperature and upper expansion angle on the performance of scramjet nozzle［J］. Aircraft Engineering and Aerospace Technology， 2022， 94（7）： 1037-1046.
[13]	贺旭照，秦思，卫锋，等. 吸气式高超声速飞行器非均匀尾喷流试验［J］. 航空学报， 2017， 38（3）： 120199.
	HE X Z， QIN S， WEI F， et al. Test of non-uniform nozzle plume for air-breathing hypersonic vehicle‍［J］. Acta Aeronautica et Astronautica Sinica， 2017， 38（3）： 120199 （in Chinese）.
[14]	YU D R， CHANG J T， BAO W， et al. Optimal classification criterions of hypersonic inlet start/unstart［J］. Journal of Propulsion and Power， 2007， 23（2）： 310-316.
[15]	CHANG J， YU D， BAO W， et al. A CFD assessment of classifications for hypersonic inlet start/unstart phenomena［J］. The Aeronautical Journal， 2009， 113（1142）： 263-271.
[16]	DEB K， PRATAP A， AGARWAL S， et al. A fast and elitist multi-objective genetic algorithm： NSGA-Ⅱ‍‍［J］. IEEE Transactions on Evolutionary Computation， 2002， 6（2）： 182-197.
[17]	DEB K， JAIN H. An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach， part Ⅰ： solving problems with box constraints［J］. IEEE Transactions on Evolutionary Computation， 2014， 18（4）： 577-601.
[18]	ZHANG Q F， LI H. MOEA/D： a multiobjective evolutionary algorithm based on decomposition‍［J］. IEEE Transactions on Evolutionary Computation， 2007， 11（6）： 712-731.
[19]	王青，谷良贤，龚春林. 超燃冲压发动机可调喷管多目标优化设计［J］. 推进技术， 2013， 34（3）： 294-299.
	WANG Q， GU L X， GONG C L. Multi-objective optimization design of adjustable tail nozzle for scramjet engine［J］. Journal of propulsion technology， 2013， 34（3）： 294-299 （in Chinese）.
[20]	石波，盛刚，黄雪刚，等. 吸气式发动机可调喷管调节片结构优化设计［J］. 火箭推进， 2021， 47（3）： 52-59.
	SHI B， SHENG G， HUANG X G， et al. Structural optimization design for variable nozzle flap of airbreathing engines‍［J］. Journal of Rocket Propulsion， 2021， 47（3）： 52-59 （in Chinese）.
[21]	杨洪涛，游广飞，徐亮，等. 超声速风洞喷管冷却结构的多目标优化设计［J］. 航空动力学报， 2023， 38（5）： 1047-1057.
	YANG H T， YOU G F， XU L， et al. Multi-objective optimization design of nozzle cooling structure for supersonic wind tunnel［J］. Journal of Aerospace Dynamics， 2023， 38（5）： 1047-1057 （in Chinese）.
[22]	WANG Z H， SUN X， CHEN S. Multi-objective parameters optimization design of self-excited oscillation pulsed atomizing nozzle［J］. Journal of the Brazilian Society of Mechanical Sciences and Engineering， 2019， 41（11）： 510.
[23]	SHENG X， YOU Y X， WU Y， et al. Multi-objective optimization of the geometric parameters of a pressure-swirl nozzle［J］. Journal of the Chinese Institute of Engineers， 2022， 45（8）： 713-723.
[24]	ZHAO Y， ZHENG S J. Nozzle dimension design for aircraft engine infrared signature and thrust active control using MOEA/D‍［J］. Proceedings of the Institution of Mechanical Engineers， Part G： Journal of Aerospace Engineering， 2020， 234（15）： 2133-2138.
[25]	BUFI E A， CINNELLA P. Robust optimization of supersonic ORC nozzle guide vanes［J］. Journal of Physics： Conference Series， 2017， 821： 012014.
[26]	SPAID F， KEENER E. Experimental results for a hypersonic nozzle/afterbody flow field‍［C］‍∥10th Aerospace Sciences Meeting. Reston： AIAA， 1972.
[27]	ZHAO X C. Simulated annealing algorithm with adaptive neighborhood‍［J］. Applied Soft Computing， 2011， 11（2）： 1827-1836.

Scramjet nozzle performance prediction based on NSGA-Ⅲ-SAM algorithm

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 21

References 27

Related Articles 3

Recommended Articles

Metrics

Comments

马赫数	高度/km	落压比
4.5	24	67.8， 7.78， 77.7， 87.6， 97.5， 117.33
5.0	26	131.5， 136.05， 140.59， 149.66，158.7， 176.87
5.5	27	240.67， 245.0， 249.37， 258.08，266.78， 284.19
6.0	28	413.09， 416.61， 420.1， 427.16， 434.20， 448.26

[1]	Jinhua LOU, Rongqian CHEN, Jiaqi LIU, Yue BAO, Hao WU, Yancheng YOU. Aircraft aerodynamic performance prediction and inverse design based on a gated diffusion model [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(10): 631183-631183.
[2]	YANG Xiaofei, JIANG Yongsong, PAN Ruochi, MENG Dejun. 2D performance prediction approach for multi-stage axial compressors [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2020, 41(3): 123515-123515.
[3]	JIN Xin, XIAO Wenbo, YE Guomin, XIA Qinggan, WU Huaming, ZHANG Wenlong, TU Jiliang, HE Yinshui. Effect of flight state parameters of solar aircraft on photovoltaic module performance [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2020, 41(10): 223851-223851.