留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于RBFNN自适应混合学习算法的航天测控系统任务可靠性分配

张新贵 武小悦

张新贵, 武小悦. 基于RBFNN自适应混合学习算法的航天测控系统任务可靠性分配[J]. 航空动力学报, 2012, 27(8): 1758-1764.
引用本文: 张新贵, 武小悦. 基于RBFNN自适应混合学习算法的航天测控系统任务可靠性分配[J]. 航空动力学报, 2012, 27(8): 1758-1764.
ZHANG Xin-gui, WU Xiao-yue. Mission reliability allocation of spaceflight TT&C system based on RBFNN adaptive hybrid learning algorithm[J]. Journal of Aerospace Power, 2012, 27(8): 1758-1764.
Citation: ZHANG Xin-gui, WU Xiao-yue. Mission reliability allocation of spaceflight TT&C system based on RBFNN adaptive hybrid learning algorithm[J]. Journal of Aerospace Power, 2012, 27(8): 1758-1764.

基于RBFNN自适应混合学习算法的航天测控系统任务可靠性分配

基金项目: 国家自然科学基金(71071159)

Mission reliability allocation of spaceflight TT&C system based on RBFNN adaptive hybrid learning algorithm

  • 摘要: 为解决执行航天测控任务的各设备存在复杂的时空关联、可视与信息关联等动态约束关系,使得航天测控系统任务可靠性分配建模和分析极其困难,同时模型求解效率低的问题,提出了自适应混合学习算法的径向基神经网络建模方法.算法通过训练样本相关性矩阵的主成分分析确定网络隐含层初始节点数;在此基础上,利用梯度信息衰减因子改进了迭代过程中网络参数的梯度信息计算方式,避免了学习过程早熟的不足,且加快了迭代收敛速度.最后,通过采集航天测控系统输入-输出数据,将自适应混合学习算法应用于参数训练,并给出了具体实现步骤.通过算例仿真,表明算法在解决航天测控系统任务可靠性分配问题时具有较高泛化能力和分配结果稳定等优点.

     

  • [1] 于志坚.航天测控系统工程[M].北京:国防工业出版社,2008.
    [2] Khoshbakht A F,Raoofat M.Optimal allocation of DGs and RCSs to improve distribution network reliability and network energy loss //Proceedings of 2nd IEEE International Conference on Power and Energy (PECon 08).Johor Baharu,Malaysia:IEEE,2008:1586-1592.
    [3] Vidyarthi D P,Tripathi A K.Maximizing reliability of distributed computing system with task allocation using simple genetic algorithm[J].Journal of System Architecture,2001,47(6):549-554.
    [4] Tom P A,Murthy C S R.Algorithms for reliability-oriented module allocation in distributed computing systems[J].Journal Systems Software,1998,40(2):125-138.
    [5] ZHANG Xingui,WU Xiaoyue.A heuristic algorithm for mission reliability allocation of spaceflight TT&C system //The Proceedings of 2011 9th International Conference on RMS.Guiyang,China:IEEE,2011:1208-1213.
    [6] Yalaoui A,Chatelet E,Chu C B.A new fynamic programming method for reliability & redundancy allocation in a parallel-series system[J].IEEE Transactions on Reliability,2005,54(2):254-262.
    [7] Khan M G M,Ahmad N,Rafi L S.Optimal testing resource allocation for modular software based on a software reliability growth model:a dynamic programming approach //Proceeding of International Conference on Computer Science and Software Engineering.Washington,DC,USA:IEEE,2008:759-762.
    [8] LI Minqiang,TIAN Jin,CHEN Fuzan.Improving multiclass pattern recognition with a co-evolutionary RBFNN[J].Pattern Recognition Letters,2008,29(4):392-406.
    [9] LIN Faajeng,TENG Litao,YU Menghsiung.Radial basis function network control with improved particle swarm optimization for induction generator system[J].IEEE Transactions on Power Electronics,2008,23(4):2157-2169.
    [10] Casasent D,CHEN Xuewen.Radial basis function neural networks for nonlinear Fisher discrimination and Neyman-Pearson classification[J].Neural Networks,2003,16(5/6):529-535.
    [11] JIA Mingxing,ZHAO Chunhui,WANG Fuli,et al.A new method for decision on the structure of RBF neural network //Proceeding of International Conference on Computational Intelligence and Security.Guangzhou,China:IEEE,2006:147-150.
    [12] Karayiannis N B.Reformulated radial basis neural networks trained by gradient descent[J].IEEE Transactions on Neural Networks,1999,10(3):657-671.
    [13] XU Shuangwei,WU Xiaoyue,YAN Hua.An efficient and approximate evaluation method for mission reliability of TT&C system //Proceeding of the 7th International Conference on Mathematical Method in Reliability.Beijing,China:Beijing Institute of Technology,2011:687-692.
  • 加载中
计量
  • 文章访问数:  1640
  • HTML浏览量:  2
  • PDF量:  585
  • 被引次数: 0
出版历程
  • 收稿日期:  2012-02-22
  • 刊出日期:  2012-08-28

目录

    /

    返回文章
    返回