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

一种研究逆向卸荷膜片式减压器稳定性的BP神经网络改进算法

刘文英 王拥军 王宝山 陈阳

刘文英, 王拥军, 王宝山, 陈阳. 一种研究逆向卸荷膜片式减压器稳定性的BP神经网络改进算法[J]. 航空动力学报, 2017, 32(5): 1241-1249. doi: 10.13224/j.cnki.jasp.2017.05.026
引用本文: 刘文英, 王拥军, 王宝山, 陈阳. 一种研究逆向卸荷膜片式减压器稳定性的BP神经网络改进算法[J]. 航空动力学报, 2017, 32(5): 1241-1249. doi: 10.13224/j.cnki.jasp.2017.05.026
An improved BP neural network algorithm for researching on stability of reverse unloading diaphragm pressure reducing regulator[J]. Journal of Aerospace Power, 2017, 32(5): 1241-1249. doi: 10.13224/j.cnki.jasp.2017.05.026
Citation: An improved BP neural network algorithm for researching on stability of reverse unloading diaphragm pressure reducing regulator[J]. Journal of Aerospace Power, 2017, 32(5): 1241-1249. doi: 10.13224/j.cnki.jasp.2017.05.026

一种研究逆向卸荷膜片式减压器稳定性的BP神经网络改进算法

doi: 10.13224/j.cnki.jasp.2017.05.026
基金项目: 国家自然科学基金(11371044, 11101023)

An improved BP neural network algorithm for researching on stability of reverse unloading diaphragm pressure reducing regulator

  • 摘要: 为更好地研究多结构参数耦合变化下减压器PPR(pressure reducing regulator)的稳定性,使用BFGS (Broyden-Fletcher-Goldfarb-Shanno)拟牛顿法替换梯度下降法,实现了基于Wolfe条件的一维线搜索变步长BP(back propagation)算法.结果表明:改进的BP算法使迭代次数减少了1~2个数量级,且易于收敛到最小点.该算法用于逆向卸荷膜片式减压器时,能适应2~3个结构参数的耦合,可预测大于106个数据点的数据集.多结构参数同时变化时,更容易找到使得减压器稳定的结构参数组合.更重要的是这些结构参数同时变化时减压器的稳定性比仅其中一个参数变化时更好.

     

  • [1] Shahani A R,Esmaili H,Aryaei A,et al.Dynamic simulation of high pressure regulator[J].Journal of Computational and Applied Research in Mechanical Engineering,2011,1(1):17-28.
    [2] Rami E G,Jean-Jacques B,Pascal G,et al.Stability study and modelling of a pressure regulating station[J].International Journal of Pressure Vessels and Piping,2005,82(1):51-60.
    [3] Zafer N,Luecke G R.Stability of gas pressure regulators[J].Applied Mathematical Modelling,2008,32(1):61-82.
    [4] 陈阳,蔡国飙,张振鹏,等.双组元统一推进系统减压器稳性仿真[J].北京航空航天大学学报,2010,36(10):1135-1139.CHEN Yang,CAI Guobiao,ZHANG Zhenpeng,et al.Numerical simulation on dynamic stability of pressure reducing regulator in integral bipropellant propulsion system[J].Journal of Beijing University of Aeronautics and Astronautics,2010,36(10):1135-1139.(in Chinese)
    [5] 陈阳,高芳,张黎辉,等.减压器动态仿真的有限体积模型[J].推进技术,2006,27(1):9-14.CHEN Yang,GAO Fang,ZHANG Lihui,et al.Finite volume model for numerical simulation on dynamic process of pressure reducing regulator[J].Journal of Propulsion Technology,2006,27(1):9-14.(in Chinese)
    [6] Prescott S L,Ulanicki B.Dynamic modeling of pressure reducing valves[J].Journal of Hydraulic Engineering,2003,129(10):804-812.
    [7] Afshari H H,Zanj A,Novinzadeh A B.Dynamic analysis of a nonlinear pressure regulator using bondgraph simulation technique[J].Simulation Modelling Practice and Theory,2010,18(2):240-252.
    [8] 陈经禄,王拥军,陈阳.使用BP神经网络模型研究逆向卸荷膜片式减压器的稳定性能[J].航空动力学报,2013,28(9):2112-2120.CHEN Jinglu,WANG Yongjun,CHEN Yang.Research on stability of reverse unloading diaphragm pressure reducing regulator using BP neural network model[J].Journal of Aerospace Power,2013,28(9):2112-2120.(in Chinese)
    [9] 陈阳,高芳,张振鹏,等.气动薄膜调节阀控制系统工作过程的动态仿真[J].火箭推进,2006,32(6):28-34.CHEN Yang,GAO Fang,ZHANG Zhenpeng,et al.Dynamic simulation of working process for control system of a pneumatic diaphragm control valve[J].Journal of Rocket Propulsion,2006,32(6):28-34.(in Chinese)
    [10] Bodén M.A guide to recurrent neural networks and backpropagation[J].Electrical Engineering,2001(2):1-10.
    [11] Kumars S.Neural networks[M].Beijing:Tsinghua University Press,2006.
    [12] 袁亚湘.非线性优化计算方法[M].北京:科学出版社,2010.
    [13] 刘红英,夏勇,周水生.数学规划基础[M].北京:北京航空航天大学出版社,2012.
    [14] Han J,Kamber M,Pei J.Data mining:concepts and techniques[M].2nd ed.San Francisco:Morgan Kaufmann Publisher,2006.
    [15] Didandeh A,Mirbakhsh N,Amiri A,et al.A variable step size approach to speed-up the convergence of error back-propagation algorithm[J].Neural Processing Letters,2011,33(2):201-214.
    [16] Silva F M,Almeida L B.Acceleration techniques for the backpropagation algorithm[M].Berlin:Springer Berlin Heidelberg,1990.
    [17] Jacobs R A.Increased rates of convergence through learning rate adaptation[J].Neural Networks,1988,1(4):295-307.
  • 加载中
计量
  • 文章访问数:  762
  • HTML浏览量:  1
  • PDF量:  5
  • 被引次数: 0
出版历程
  • 收稿日期:  2015-08-09
  • 刊出日期:  2017-05-28

目录

    /

    返回文章
    返回