基于支持向量机的坦克驾驶模拟训练结果分析

doi:10.3969/j.issn.1000-1093.2019.09.021

摘要/Abstract

摘要： 利用坦克驾驶模拟器进行模拟训练是提高装备操作技能的重要方法。针对以往模拟训练忽视训练数据采集分析和提高训练质量的问题，提出采用支持向量机（SVM）对坦克驾驶模拟训练结果进行分析的方法。为了解决SVM参数选取难的问题，提出一种自适应粒子群优化(APSO)算法对SVM参数进行优化选择，设计动态权重参数并赋予相关惯性，实现粒子动态自适应。引入多位置查询机制和极值点信息以维持不同粒子平衡点的多样性，通过迭代选择与优化目标函数实现对参数的自动寻优。基于APSO算法的支持向量机(SVM-APSO)应用到某型坦克驾驶模拟器的训练结果分析中，结果表明SVM-APSO能克服多维影响因素对训练成绩分类带来的不利影响，实验结果在精度和时间上都有明显优势，验证了SVM-APSO在坦克驾驶模拟训练结果分析中应用的可行性与有效性。

关键词: 坦克, 支持向量机, 驾驶模拟器, 模拟训练, 结果分析, 粒子群优化算法

Abstract: Training by tank driving simulator is an important way of improving equipment skill. A method of training effect analysis of tank driving simulator based on support vector machine (SVM) is proposed for the problems resulted from ignoring the collection and analysis of training data and the increase in training quality. In order to solve the issue of choosing SVM parameters,an adaptive particle swarm optimization (APSO) algorithm is adopted to determine the SVM parameters. Dynamic weight parameters are designed and the related inertance is entrusted for realizing the self-adaption of particle. The multi-location inquiry mechanism and the information from extreme point are used to keep the balance dot diversity of different particles.The SVM parameters can be automatically optimized by iterating and optimizing the object function. After the SVM based on particle swarm algorithm is used for the training effect analysis of tank driving simulator, the adverse effect of multidimensional factors on training score can be overcome. The experimental results show that SVM can be feasible and effective in the training effect analysis of tank driving simulator. Key

Key words: tank, supportvectormachine, drivingsimulator, simulationtraining, resultanalysis, particleswarmalgorithm

中图分类号:

邓青，薛青，罗佳. 基于支持向量机的坦克驾驶模拟训练结果分析[J]. 兵工学报, 2019, 40(9): 1953-1960.

DENG Qing, XUE Qing, LUO Jia. Analysis of Tank Driving Simulation Training Results Based on Support Vector Machine[J]. Acta Armamentarii, 2019, 40(9): 1953-1960.

参考文献

［1］胡剑文,常青,冯晓文,等.作战仿真实验:理论、平台与应用［M］.北京:国防工业出版社，2016.
HU J W, CHANG Q, FENG X W, et al. Combat simulation experiment: theory, platform and application［M］. Beijing: National Defense Industry Press, 2016.(in Chinese)

［2］余辉,屈喜龙,谢京力. 基于支持向量机的电力云故障诊断方法研究［J］. 湖南工程学院学报(自然科学版),2017,27(4):39-42.
YU H, QU X L, XIE J L. Research on fault diagnosis method of power cloud based on support vector machine［J］. Journal of Hunan Institute of Engineering (Natural Science Edition), 2017, 27(4): 39-42. (in Chinese)
［3］蔡冬松,靖继鹏. 基于最小二乘支持向量机的数据挖掘应用研究［J］. 情报科学, 2005，23 (12)：1877-1880.
CAI D S, JING J P. Data mining based on least squares support vector machine［J］. Information Science, 2005，23 (12)：1877-1880. (in Chinese)

［4］张琨,曹宏鑫,刘凤玉. 一种基于SVM的网络入侵检测模型［J］. 南京理工大学学报, 2007,31(4): 403-408.
ZHANG K, CAO H X, LIU F Y. SVM-based network intrusion detection model［J］. Journal of Nanjing University of Science and Technology, 2007,31(4): 403-408. (in Chinese)
［5］张彪,闫晓鹏,栗苹,等. 基于支持向量机的无线电引信抗扫频式干扰研究［J］. 兵工学报,2016,37(4): 635-640.
ZHANG B, YAN X P, LI P, et al. Research on anti-frequency sweeping jamming of radio fuze based on support vector machine［J］.Acta Armamentarii, 2016,37(4): 635-640. (in Chinese)
［6］杨小明, 崔雪, 周斌. 基于粒子群优化支持向量机的短期负荷预测［J］. 武汉大学学报(工学版), 2018,51(8):715-720.
YANG X M,CUI X, ZHOU B. Research of short tern load forecasting based on particle swarm optimization SVM［J］. Engineering Journal of Wuhan University, 2018,51(8):715-720. (in Chinese)
［7］吕明珠, 苏晓明, 陈长征,等. Fisher准则下的粒子群支持向量机在轴承故障诊断中的应用［J］. 机械与电子, 2018,36(7): 49-54.
L M Z, SU X M, CHEN C Z,et al. Application of particle swarm support vector machine based on Fisher criterion in bearing fault diagnosis［J］. Machinery & Electronics,2018,36(7):49-54. (in Chinese)
［8］张树团, 张晓斌, 雷涛，等. 基于粒子群算法和支持向量机的故障诊断研究［J］. 计算机测量与控制, 2008,16 (11): 1573- 1574.
ZHANG S T, ZHANG X B, LEI T, et al. Research on fault diagnosis based on PSO and SVM［J］. Computer Measurement & Control, 2008,16 (11): 1573-1574. (in Chinese)

［9］ CHAPELLE O, VAPNIK V, MUKHERJEE S. Choosing multiple parameters for support vector machines［J］. Machine Learning,2002,46(1): 131-159.

［10］ AHMED F, SIYAL M Y. A secure and robust wavelet-based hashing scheme for image authentication［C］∥Proceedings of the 13th International Multimedia Modeling Conference. Singapore: Nanyang Technological University, 2007: 51-62.
［11］颜根廷,李传江,马广富. 基于混合遗传算法的支持向量机参数选择［J］. 哈尔滨工业大学学报, 2008,40(5):688-691.
YAN G T, LI C J, MA G F. Parameter selection for support vector machine based on hybrid genetic algorithm［J］. Journal of Harbin Institute of Technology, 2008,40(5):688-691. (in Chinese)
［12］ HU T, QIU Y P, CUI H J,et al. Numerical discretization-based kernel type estimation methods for ordinary differential equation models［J］.Acta Mathematica Sinica, 2015,31(8):1233-1254.
［13］赵羲,苏昊月,石中玉,等. 南极海冰密集度多源数据的交叉检验［J］. 武汉大学学报(信息科学版), 2015,40(11):1460- 1466.
ZHAO X, SU H Y, SHI Z Y, et al. Intercomparison of multi-sources sea ice concentration data in Antarctic［J］. Geomatics and Information Science of Wuhan University, 2015,40(11):1460-1466. (in Chinese)

第40卷第9期
2019 年9月兵工学报ACTA
ARMAMENTARIIVol.40No.9Sep. 2019

[1]	郭志明，王迪，庞婷，李娟，赵丹，杨建新. 面向装备体系联合检验的指数分布定时截尾方案优化研究[J]. 兵工学报, 2022, 43(S1): 203-207.
[2]	李良钰，苏铁熊，马富康，吴小军，徐春龙. 基于集合经验模态分解-支持向量机的高压共轨系统故障诊断方法[J]. 兵工学报, 2022, 43(5): 992-1001.
[3]	段浩，陈晖，翟兆阳，韩雨，马凡华，崔亚辉. 基于支持向量机的氢混天然气发动机性能预测[J]. 兵工学报, 2022, 43(5): 1002-1011.
[4]	杨建新，兰小平，冯亚东，杨一铭，郭志明. 基于改进樽海鞘群和最小二乘支持向量机算法的新型弹药质量评估方法[J]. 兵工学报, 2022, 43(5): 1012-1022.
[5]	陈军，张岳，陈晓威，佟龑. 基于模糊灰色认知图的复杂战场智能态势感知建模方法[J]. 兵工学报, 2022, 43(5): 1093-1106.
[6]	许晓东，唐圣金，谢建，于传强，王凤飞，韩洋洋. 随机退化应力作用下设备剩余寿命预测方法[J]. 兵工学报, 2022, 43(3): 712-719.
[7]	李军宁，王倩，韩卡，陈武阁. 坦克炮发射角对炮塔座圈动力学行为及其润滑性能的影响[J]. 兵工学报, 2021, 42(9): 1819-1828.
[8]	冯海潮，王羽羽，刘伟，曾永兴，吴克南. 基于三维建模的坦克假目标示假性能仿真技术[J]. 兵工学报, 2021, 42(9): 1998-2003.
[9]	马润波，董丽虹，王海斗. 基于支持向量机的热喷涂层接触疲劳寿命预测[J]. 兵工学报, 2021, 42(12): 2743-2752.
[10]	宋承天，焦永晖，刘向，赵宏宇. 基于电容与磁复合的装甲目标近程探测方法[J]. 兵工学报, 2021, 42(11): 2310-2320.
[11]	雷震烁，刘松涛，温镇铭，葛杨. 复杂电磁环境下末制导雷达工作状态实时判别方法[J]. 兵工学报, 2021, 42(1): 83-90.
[12]	戴文君，常天庆，褚凯轩，张雷，郭理彬. 基于时空卷积特征记忆模型的坦克火控系统视频目标检测方法[J]. 兵工学报, 2020, 41(9): 1708-1718.
[13]	王成，吴岩，杨廷飞. 利用改进单分类支持向量机提升舰船尾流目标的检测准确率[J]. 兵工学报, 2020, 41(9): 1887-1893.
[14]	吕国俊，曹建军，郑奇斌，常宸，翁年凤，彭琮. 基于多目标蚁群优化的单类支持向量机相似重复记录检测[J]. 兵工学报, 2020, 41(2): 324-331.
[15]	邓青, 薛青, 高恒, 翟凯. 基于双向概念格的坦克驾驶模拟训练关联规则挖掘[J]. 兵工学报, 2020, 41(12): 2397-2407.