航空学报 > 2013, Vol. 34 Issue (2): 343-351   doi: 10.7527/S1000-6893.2013.0039

基于启发式自适应离散差分进化算法的多UCAV协同干扰空战决策

薛羽1, 庄毅1, 张友益2, 倪思如1, 赵学健3   

  1. 1. 南京航空航天大学 计算机科学与技术学院, 江苏 南京 210016;
    2. 中船重工集团公司 第723研究所, 江苏 扬州 225001;
    3. 南京邮电大学 物联网学院, 江苏 南京 210046
  • 收稿日期:2012-02-22 修回日期:2012-04-16 出版日期:2013-02-25 发布日期:2012-05-17
  • 通讯作者: 庄毅 E-mail:zhuangyi@nuaa.edu.cn
  • 作者简介:薛羽,男,博士研究生。主要研究方向:智能计算、电子对抗、物联网。Tel:025-84890790,E-mail:xueyu_123@nuaa.edu.cn;庄毅,女,教授,博士生导师。主要研究方向:分布计算。Tel:025-84896779,E-mail:zhuangyi@nuaa.edu.cn
  • 基金资助:

    江苏省普通高校研究生科研创新计划(CXLX11_0203);航空科学基金(2010ZC13012);国防基础研究基金(Q072006C002-1)

Multiple UCAV Cooperative Jamming Air Combat Decision Making Based on Heuristic Self-adaptive Discrete Differential Evolution Algorithm

XUE Yu1, ZHUANG Yi1, ZHANG Youyi2, NI Siru1, ZHAO Xuejian3   

  1. 1. School of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China;
    2. No.723 Institute, China Shipbuilding Industry Corporation, Yangzhou 225001, China;
    3. College of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing 210046, China
  • Received:2012-02-22 Revised:2012-04-16 Online:2013-02-25 Published:2012-05-17
  • Contact: 10.7527/S1000-6893.2013.0039 E-mail:zhuangyi@nuaa.edu.cn
  • Supported by:

    Funding of Jiangsu Innovation Program for Graduate Education (CXLX11_0203); Aeronautical Science Foundation of China (2010ZC13012); National Defense Foundation of China (Q072006C002-1)

摘要:

研究了多无人作战飞机(UCAV)协同干扰空战决策(MUCJAD)问题,在干扰效能评估指标量化方法的基础上为该问题建立了优化模型。为有效求解该模型,提出一种启发式自适应离散差分进化(H-SDDE)算法。在H-SDDE算法中,设计了包含4种候选解产生策略的候选策略池,引入了候选解产生策略及其参数的自适应学习过程。此外,结合实际问题为算法设计了基于威胁度的扩展型整数编码方案、基于威胁度的启发式个体调整操作、基于约束满足的个体修复操作。在12个测试实例上进行了仿真验证,结果表明,H-SDDE算法与其他同类算法相比在求解质量和求解速度上具有明显优势,能够更好地发挥多UCAV协同干扰整体效果。

关键词: 无人机, 协同干扰, 决策, 启发式算法, 自适应, 优化, 差分进化

Abstract:

This paper presents a multiple unmanned combat air vehicle (UCAV) cooperative jamming air combat decision-making (MUCJAD) problem. An optimal model is constructed for the MUCJAD on the metric methods of the jamming effect evaluating indexes. In order to solve the model effectively, a heuristic self-adaptive discrete differential evolution (H-SDDE) algorithm is proposed in which, a strategy candidate pool which including four candidate solution generating strategies is designed and two self-adaptive learning processes are introduced for candidate solution generating strategy and its parameters. Furthermore, a threat degree based extensional integer coding scheme, a heuristic individual adjust operator and a constraints satisfaction based individual repair process are designed according to the real-word application. Simulation experiments are conducted on twelve test instances. The results indicate that the H-SDDE algorithm is better than other algorithms in terms of convergence speed and solution quality. The H-SDDE algorithm can enhance the effect of multiple UCAV cooperative jamming.

Key words: unmanned aerial vehicles, cooperative jamming, decision making, heuristic algorithm, self-adaption, optimization, differential evolution

中图分类号: