基于指标关联的舰载机出动架次率预测方法

doi:10.12305/j.issn.1001-506X.2023.11.17

摘要/Abstract

摘要：

舰载机出动架次率作为衡量航母战斗力的关键指标, 对航母-舰载机系统的安全高效运行十分重要。建立根据实时数据预测当前出动架次率的模型, 将会为航母指挥官的实时调度提供重要参考。首先, 从指标原始数据出发, 基于大数据关联度分析、社区发现及主成分分析法, 确定指标之间的树状关系, 从而建立稀疏深度神经网络。同时, 为了保证更好的训练效果, 选取标准化、L2正则化、Adam优化器作为神经网络的优化算法进行训练。仿真结果表明, 在航母舰载机持续性出动任务下, 所提方法能够实现对舰载机出动架次率的快速、准确、实时预测。

关键词: 舰载机出动架次率, 稀疏深度神经网络, Adam优化器, 数据标准化, 正则化

Abstract:

As a key indicator to measure the combat effectiveness of an aircraft carrier, the carrier aircraft's sortie rate is very important for the safe and efficient operation of the carrier-based aircraft system. Establishing a model that predicts the current sortie rate based on real-time data will provide an important reference for the aircraft carrier commander's real-time scheduling. Firstly, starting from the original data of indicators, based on big data correlation analysis, community discovery, and principal component analysis, the tree-like relationship between indicators is determined, so as to establish a sparse deep neural network. At the same time, in order to ensure better training effect, standardization, L2 regularization, and Adam optimizer are selected as the optimization algorithm of the neural network. The simulation results show that the proposed method can achieve fast, accurate and real-time prediction of the sortie rate of carrier aircraft under the mission of continuous dispatch.

Key words: carrier aircraft's sortie rate, sparse depth neural network, Adam optimizer, date standardization, regularization

中图分类号:

O231.5

邓嘉宁, 李海旭, 安强林, 沙恩来, 王泽, 吴宇. 基于指标关联的舰载机出动架次率预测方法[J]. 系统工程与电子技术, 2023, 45(11): 3507-3515.

Jianing DENG, Haixu LI, Qianglin AN, Enlai SHA, Ze WANG, Yu WU. Prediction method of carrier aircraft's sortie rate based on index correlation[J]. Systems Engineering and Electronics, 2023, 45(11): 3507-3515.

图/表 13

图1

图2

图3

图4

图5

图6

表1

图7

图8

图9

图10

表2

图11

参考文献 33

1	谢君, 廖松, 石章松. 航母作战部署中的舰载机出动规划模型[J]. 系统工程与电子技术, 2020, 42 (1): 128- 132.
	XIE J , LIAO S , SHI Z S . Programming model of flight sortie for an aircraft carrier in transit[J]. Systems Engineering and Electronics, 2020, 42 (1): 128- 132.
2	刘相春, 卢晶, 黄祥钊. 国外航母舰载机出动回收能力指标体系分析[J]. 中国舰船研究, 2011, 6 (4): 1- 7. doi: 10.3969/j.issn.1673-3185.2011.04.001
	LIU X C , LU J , HUANG X Z . Analysis on the index system of sortie generation capacity of embarked aircrafts[J]. Chinese Journal of Ship Research, 2011, 6 (4): 1- 7. doi: 10.3969/j.issn.1673-3185.2011.04.001
3	王玮, 颜世伟. 美国航母舰载机出动回收能力评估方法[J]. 舰船科学技术, 2016, 38 (7): 140- 142.
	WANG W , YAN S W . Analysis on evaluation method of SGR of US aircraft carrier[J]. Ship Science and Technology, 2016, 38 (7): 140- 142.
4	崔荣伟, 韩维, 苏析超, 等. 舰载机甲板机务勤务保障作业调度与资源配置集成优化[J]. 系统工程与电子技术, 2021, 43 (7): 1884- 1893.
	CUI R W , HAN W , SU X C , et al. Integrated optimization of carrier-based aircraft flight deck operations scheduling and resource configuration for pre-flight preparation stage[J]. Systems Engineering and Electronics, 2021, 43 (7): 1884- 1893.
5	WU Y, TAN W Q, SUN L G, et al. A decision-making method for landing routes of aircraft on the carrier[C]//Proc. of the MATEC Web of Conferences, 2016, 75: 05002.
6	WU Y , QU X J . Path planning for taxi of carrier aircraft launching[J]. Science China-Technological Sciences, 2013, 56 (6): 1561- 1570. doi: 10.1007/s11431-013-5222-5
7	梁天骄, 陈晓明, 杨朝旭, 等. 舰载无人机滑行轨迹控制方法[J]. 北京航空航天大学学报, 2021, 47 (2): 289- 296. doi: 10.13700/j.bh.1001-5965.2020.0294
	LIANG T J , CHEN X M , YANG Z X , et al. Trajectory control method for unmanned carrier aircraft taxiing[J]. Journal of Beijing University of Aeronautics and Astronautics, 2021, 47 (2): 289- 296. doi: 10.13700/j.bh.1001-5965.2020.0294
8	彭雅欣, 黄琦, 余明晖, 等. 基于作战环境配置资源的出动架次率计算模型[J]. 水下无人系统学报, 2020, 28 (6): 642-649, 676.
	PENG Y X , HUANG Q , YU M H , et al. Calculation model of SGR based on operational environment configuration resources[J]. Journal of Unmanned Undersea Systems, 2020, 28 (6): 642-649, 676.
9	于步兵, 王卓健, 潘洪升. 基于战时飞机出动架次率的保障设备优化配置[J]. 空军工程大学学报(自然科学版), 2018, 19 (3): 30- 35.
	YU B B , WANG Z J , PAN H S . Optimal allocation of support equipments based on aircraft sortie generation rate in the wartime[J]. Journal of Air Force Engineering University(Natural Science Edition), 2018, 19 (3): 30- 35.
10	郭圣明, 贺筱媛, 吴琳, 等. 基于强制稀疏自编码神经网络的防空作战体系效能回溯分析方法[J]. 中国科学: 信息科学, 2018, 48 (7): 824- 840.
	GUO S M , HE X Y , WU L , et al. Backtracking analysis approach for effectiveness of air defense operation system of systems based on force-sparsed stacked-autoencoding neural networks[J]. Science China: Information Sciences, 2018, 48 (7): 824- 840.
11	YU Y H . Research progress of crop disease image recognition based on wireless network communication and deep learning[J]. Wireless Communications and Mobile Computing, 2021, 7577349.
12	AKGUN D , HIZAL S , CAVUSOGLU U . A new DDoS attacks intrusion detection model based on deep learning for cyber security[J]. Computers & Security, 2022, 102748.
13	VECCHI R , SCARDAPANE S , COMMINIELLO D , et al. Compressing deep-quaternion neural networks with targeted regularisation[J]. CAAI Transactions on Intelligence Technology, 2020, 5 (3): 172- 176. doi: 10.1049/trit.2020.0020
14	ILSANG O , YONGDAI K . Nonconvex sparse regularization for deep neural networks and its optimality[J]. Neural Computation, 2021, 34 (2): 476- 517.
15	TOMOKAZE S , KEN K , YUICHI T . Prediction of hierarchical time series using structured regularization and its application to artificial neural networks[J]. PlosOne, 2020, 15 (11): e0242099. doi: 10.1371/journal.pone.0242099
16	NAKAMURA K , SOATTO S , HONG B W . Stochastic batch size for adaptive regularization in deep network optimization[J]. Pattern Recognition, 2022, 129, 108776.
17	KINGMA D P, BA J. Adam: a method for stochastic optimization[EB/OL]. [2022-06-01]. https://arxiv.org/abs/1412.6980v6.
18	ALOTAIBI S D , YADAV K , ALENDAILYA N , et al. Deep neural network-based intrusion detection system through PCA[J]. Mathematical Problems in Engineering, 2022, 6488571.
19	WU H P , LI L . The BP neural network with adam optimizer for predicting audit opinions of listed companies[J]. IAENG International Journal of Computer Science, 2021, 48 (2): 364- 368.
20	HASHEMI S E , TAVANA M , BAKHSHI M . A new particle swarm optimization algorithm for optimizing big data clustering[J]. SN Computer Science, 2022, 3 (4): 311.
21	SHI Y H, EBERHART R. A modified particle swarm optimizer[C]//Proc. of the IEEE International Conference on Evolutionary Computation, 1998: 69-73.
22	LIU Q , LI J , REN H P , et al. All particles driving particle swarm optimization: superior particles pulling plus inferior particles pushing[J]. Knowledge-Based Systems, 2022, 249, 108849.
23	RESHEF D N , RESHEF Y A , FINUCANE H K , et al. Detecting novel associations in large data sets[J]. Science, 2011, 334 (6062): 1518- 1524.
24	XIE W B , LEE Y L , WANG C , et al. Hierarchical clustering supported by reciprocal nearest neighbors[J]. Information Sciences, 2020, 527, 279- 292.
25	GAYATHRI R G , NAIR J J , KAIMAL M R . Extending full transitive closure to rank removable edges in GN algorithm[J]. Procedia Computer Science, 2016, 93, 995- 1002.
26	HUANG W C , LI L Q , LIU H Y , et al. Defense resource allocation in road dangerous goods transportation network: a self-contained girvan-newman algorithm and mean variance model combined approach[J]. Reliability Engineering & System Safety, 2021, 215, 107899.
27	GAO S , ZHAO H , BAI Z P , et al. Combined use of principal component analysis and artificial neural network approach to improve estimates of PM 2.5 personal exposure: a case study on older adults[J]. Science of the Total Environment, 2020, 726, 138533.
28	WOLD S , ESBENSEN K , GELADI P . Principal component analysis[J]. Chemometrics and Intelligent Laboratory Systems, 1987, 2 (1/3): 37- 52.
29	LI P , ZHANG W L , LU C J , et al. Robust kernel principal component analysis with optimal mean[J]. Neural Networks, 2022, 152, 347- 352.
30	GIRVAN M , NEWMAN M E . Community structure in social and biological networks[J]. Proceedings of the National Academy of Sciences, 2002, 99 (12): 7821- 7826.
31	ANDREA A , FRANCESCO D , FRANCESCO I , et al. A survey on modern trainable activation functions[J]. Neural Networks, 2021, 138, 14- 32.
32	邓嘉宁, 吴宇, 许舒婷, 等. 基于模糊贝叶斯-ANP舰载机出动回收综合评估[J]. 系统工程与电子技术, 2022, 44 (11): 3423- 3432.
	DENG J N , WU Y , XU S T , et al. Comprehensive evaluation of carrier aircraft's dispatch and recovery basedon fuzzy Bayesian-ANP[J]. Systems Engineering and Electronics, 2022, 44 (11): 3423- 3432.
33	DIETZ D C , JENKINS R C . Analysis of aircraft sortie generation with the use of a fork-join queueing network model[J]. Naval Research Logistics, 1997, 44 (2): 153- 164.

指标	x₁	x₂	x₃	x₄	⋯
x₂	0.125 4	-	-	-	⋯
x₃	0.372 8	0.152 3	-	-	⋯
x₄	0.678 5	0.602 5	0.354 9	-	⋯
x₅	0.102 8	0.256 7	0.952 8	0.807 2	⋯
⋮	⋮	⋮	⋮	⋮	⋮

方法	最大误差/%	最小误差/%	隐藏层1节点总数	隐藏层2节点总数	计算时间/s
稀疏深度神经网络	0.660 7	0.286 5	60	4	0.677
非稀疏深度神经网络	1.167 1	0.371 9	60	4	0.447

[1]	刘鸣谦, 徐仲秋, 陈天成, 张冰尘, 吴一戎. 基于L₁ & TV正则化的低过采样Staggered SAR成像方法[J]. 系统工程与电子技术, 2023, 45(9): 2718-2726.
[2]	孙世岩, 张钢, 梁伟阁, 佘博, 田福庆. 基于改进受限玻尔兹曼机的滚动轴承健康因子构建方法[J]. 系统工程与电子技术, 2023, 45(9): 2979-2985.
[3]	仇祝令, 查宇飞, 李振宇, 李禹铭, 张鹏, 朱川. 基于多模型蒸馏的时间正则化相关滤波跟踪算法[J]. 系统工程与电子技术, 2022, 44(8): 2448-2456.
[4]	王彩云, 吴钇达, 王佳宁, 马璐, 赵焕玥. 基于改进的CNN和数据增强的SAR目标识别[J]. 系统工程与电子技术, 2022, 44(8): 2483-2487.
[5]	王帅, 向建军, 彭芳, 唐书娟. 基于新最速下降法的目标跟踪算法[J]. 系统工程与电子技术, 2022, 44(5): 1512-1519.
[6]	刘歌, 芮国胜, 田文飚. 基于双重正则矩阵分解的缺失数据恢复[J]. 系统工程与电子技术, 2021, 43(5): 1191-1197.
[7]	赵迎新, 王长峰, 吴虹, 张铭, 黄英杰, 王乐耕, 刘之洋. 基于负熵最大化的压缩感知信道估计算法[J]. 系统工程与电子技术, 2021, 43(4): 1126-1132.
[8]	刘星, 熊厚情, 赵建印, 朱敏. 基于改进稀疏KELM的在线非平稳动态系统状态预测方法[J]. 系统工程与电子技术, 2020, 42(9): 2022-2032.
[9]	季策, 张晓梦. 基于MS-ROMP信号重构算法的欠定盲分离[J]. 系统工程与电子技术, 2020, 42(4): 756-763.
[10]	徐志林, 魏中浩, 吴辰阳, 张冰尘. 基于l1正则化的多通道滑动聚束SAR成像[J]. 系统工程与电子技术, 2019, 41(2): 304-310.
[11]	叶霞, 杨书杰. 改进混合正则化约束多帧湍流退化图像盲复原方法[J]. 系统工程与电子技术, 2018, 40(9): 2138-2142.
[12]	毕笃彦, 王世平, 刘坤, 何林远. 基于并行映射卷积网络的超分辨率重建算法[J]. 系统工程与电子技术, 2018, 40(8): 1873-1880.
[13]	纪元法, 朱亮亮, 孙希延, 严素清. 差分进化算法结合正则化解算病态方程[J]. 系统工程与电子技术, 2018, 40(7): 1573-1577.
[14]	徐志刚, 李文文, 袁飞祥, 朱红蕾, 许亚美. 基于稀疏表示和多成分字典学习的超分辨率重建[J]. 系统工程与电子技术, 2018, 40(3): 699-703.
[15]	余路, 曲建岭, 高峰, 田沿平, 申江江. 基于过完备字典的缺失振动数据压缩感知重构算法[J]. 系统工程与电子技术, 2017, 39(8): 1871-1877.