航空发动机约简遗传规划起动非线性动态模型

尉询楷; 李应红

航空发动机约简遗传规划起动非线性动态模型

空军工程大学工程学院, 陕西西安 710038

基金项目: 空军工程大学工程学院优秀博士论文创新基金(BC0501);国防预研基金(4132030103)资助

计量
- 文章访问数: 1931
- HTML浏览量: 277
- PDF量: 416
- 被引次数: 0
出版历程
- 收稿日期: 2005-09-15
- 修回日期: 2006-05-31
- 刊出日期: 2006-08-28

Aero-engine nonlinear dynamic starting model based on parsimonious genetic programming

School of Engineering, Air Force Engineering University, Xi'an 710038, China

摘要

摘要: 提出了一种新的用于航空发动机最优化起动过程数据驱动动态建模的约简遗传规划(PGP)算法。这种模型采用遗传规划产生航空发动机辨识模型的输入输出非线性模型集,并以二叉树结构表征函数项,运用正交最小二乘算法(OLS)估计二叉树分支对于模型精度的贡献并据此去除复杂、冗余的函数项,从而加快遗传规划的收敛速度,最后通过GP进化可获得简单、可靠、准确的线参数非线性线参数动态模型。实际发动机起动过程建模应用案例证明,这种思路对于具有非线性输入输出关系特征的数据可以产生鲁棒性好、解析性强的线参数非线性模型。
- 航空、航天推进系统 /
- 航空发动机 /
- 起动 /
- 约简遗传规划 /
- 正交最小二乘 /
- 非线性动态模型
Abstract: A novel Parsimonious Genetic Programming(PGP) algorithm for aero-engine starting process optimum data-driven nonlinear dynamic modeling was proposed.First, the method used the traditional GP to generate nonlinear input-output models that were represented in a binary tree structure.Then,Orthogonal Least Squares algorithm(OLS) was applied to estimate the contribution of the tree branches to the accuracy of the model.On this basis,the complex redundant subtrees can be eliminated and the GP's convergence speed is enhanced.Finally,the simple,reliable and accurate linear-in-parameters nonlinear dynamic model can be obtained via GP evolution.Applications to real aeroengine starting process modeling validate that the proposed method can generate more robust and interpretable models.
- aerospace propulsion system /
- aero-engine /
- starting /
- Parsimonious Genetic Programming(PGP) /
- Orthogonal Least Squares algorithm(OLS) /
- nonlinear dynamic model

HTML

参考文献(12)

[1]	刘小勇,樊思齐.采用BP网络辨识航空发动机数学模型[J],航空动力学报,1996,11(2):153-156.Liu X Y,Fan S Q.Aeorengine model identification with back-propagation neural networks[J].Journal of Aerospace Power,1996,11(2):153-156.
[2]	姜涛,李应红.基于动态RBF网络的发动机起动过程模型辨识[J].航空动力学报,2002,17(3):381-384.Jiang T,Li Y H.A dynamic identification model of aeroengine starting progress based on the RBF network[J].Journal of Aerospace Power,2002,17(3):381-384.
[3]	李应红,刘建勋.基于支持向量机的航空发动机起动性能估算研究[J].航空学报,2005,26(1):32-35.Li Y H,Liu J X.Turbofan engine starting characteristics estimation based on Support Vector Machines[J].Acta Aeronautica et Astronautica Sinica,2005,26(1):32-35.
[4]	尉询楷,李应红,王剑影,等.基于支持向量机的航空发动机辨识模型[J].航空动力学报,2004,19(5):684-688.Wei X K,Li Y H,Wang J Y,et al.A novel aero-engine identification model based on Support Vector Machines[J].Journal of Aerospace Power,2004,19(5):684-688.
[5]	Stephan Winkler,Michael Affenzeller,Stefan Wagner.New methods for the identification of nonlinear model structures based upon Genetic Programming techniques[Z].http://citeseer.ist.psu.edu/634350.html,2005.
[6]	宋志平,程礼,魏瑞轩.航空发动机的一种Volterra级数非线性动态模型[J].航空动力学报,2004,19(4):577-580.Song Z P,Cheng L,Wei R X.A volterra progression model of nonlinearity dynamic respondence of aero-engine[J].Journal of Aerospace Power,2004,19(4):577-580.
[7]	Pearson R,Ogunnaike B.Nonlinear process identification[A].In Henson M A,Seborg D E ed.Nonlinear process control[C].Prentice-Hall:Englewood Cliffs,NJ,1997:10-38.
[8]	Hernandez E,Arkun Y.Control of nonlinear systems using polynomial ARMA models[J].AICHE Journal,1993,39(3):446-460.
[9]	Feil B,Abonyi J,Szeifert F.Model order selection of nonlinear input-output models using a clustering based approach[J].Journal of Process Control,2004,14(6):593-602.
[10]	Pearson R.Selecting nonlinear model structures for computer control[J].Journal of Process Control,2003,13(1):1-26.
[11]	Koza J.Genetic programming:on the programming of computers by means of natural selection[M].MIT Press:Cambridge,1992.
[12]	Chen S,Billings S,Luo W.Orthogonal least squares methods and their application to nonlinear system identification[J].International Journal of Control,1989,50:1873-1896.