航空发动机的智能神经网络自适应控制研究

赵俊; 陈建军; 王灵刚

航空发动机的智能神经网络自适应控制研究

1.
西安电子科技大学机电工程学院, 西安 710071
2.
中航一集团电光设备研究所, 洛阳 471009

基金项目: 国家863项目(2006AA04Z402);陕西省自然科学基金(2005A09)

计量
- 文章访问数: 1508
- HTML浏览量: 76
- PDF量: 638
- 被引次数: 0
出版历程
- 收稿日期: 2007-09-21
- 修回日期: 2008-03-12
- 刊出日期: 2008-10-28

New intelligent neural network adaptive control scheme research for aeroengine

1.
School of Electromechanical Engineering, Xidian University, Xi′an 710071, China
2.
Institute of Electro-Optical Equipment of Aviation Industry Corporation I, Luoyang 471009, China

摘要

摘要: 针对结构复杂、模型不确定、强非线性的航空发动机对象,提出一种综合模糊推理、神经网络自适应和PID简单控制各自优点的控制方案.在改进模糊PID控制器的基础上,进行了新型智能型神经网络控制器的设计,并提出离线混沌蚁群优化与在线误差反传调整相结合的优化方法.应用具有良好泛化能力的最小二乘支持向量机进行系统辨识,对某型航空发动机进行了设计点处的线性和非线性模型控制仿真.结果表明:控制系统具有满意的动、静态性能和较好的鲁棒性,验证了该方案的可行性和有效性.
- 航空发动机 /
- 智能神经网络 /
- 模糊PID控制 /
- 混沌蚁群优化 /
- 误差反传算法 /
- 最小二乘支持向量机
Abstract: In view of complicated,undetermined and strongly nonlinear aeroengine object,a novel control scheme integrating the merits of fuzzy inference,neural network adaptation and simple proportional-integral-derivative(PID) method was presented.Based on the improved fuzzy-PID controller,a novel intelligent neural network controller was designed.The parameters of the controller were optimized by the mixed learning method integrating offline chaotic ant colony optimization and online error back propagation(BP) algorithm.By applying least square support vector machine for system identification,with its fine nonlinear mapping ability,Simulation results at the design point show that the control system has good robustness and better performance than conventional control methods.The feasibility and validity of the control scheme are proved.
- aeroengine /
- intelligent neural network /
- fuzzy-pid control /
- chaotic ant colony optimization /
- error back propagation algorithm /
- least square support vector machine

HTML

参考文献(9)

[1]	袁春飞,孙健国,姚华.航空发动机模型参考模糊自学习控制[J].南京航空航天大学学报,2004,36(2):155-158.YUAN Chunfei.SUN Jianguo,YA0 Hua.Fuzzy model reference learning control of aero-engine[J].Journal of Nanjing University of Aeronautics and Astronautics,2004,36(2):155-158.(in Chinese)
[2]	董劲,黄金泉.航空发动机多变量模糊PID控制[J].航空动力学报,2003,18(4):538-541.DONG Jin.HUANG Jinquan.Muhivariable fuzzy-PID control for aeroengineI-J1.Journal of Aerospace Power,2003,18(4);538-541.(in Chinese)
[3]	苏伟生,李弱,孙健国,等.基于遗传算法的航空发动机PI控制器参数优化方法[J].航空动力学报,2005,20(6):1078-1082.SU Weisheng,LI Yue,SUN Jianguo,et al.Optimization methodology of PI controller parameters for aeroengines based on genetic algorithm[J].Journal of Aerospace Power,2005,20(6):1078-1082.(in Chinese)
[4]	侯胜利,吴云,刘建勋,等.基于混沌变量的航空发动机模糊神经网络控制[J].航空动力学报,2005,20(3):494-498.HOU Shengli,WU Yun,I.IU Jianxun,et al.Chaos based fuzzy neural networks control for aeroengines[J].Journal of Aerospace Power,2005,20(3):494-498.(in Chinese)
[5]	郭迎清.航空发动机神经网络自适应控制研究[J1.航空动力学报,2001,16(1):83-86.GUO Yingqing.A new neural network adaptive eontrol scheme research[J]].Journal of Aerospace Power,2001,16(1):83-86.(in Chinese)
[6]	Dorigo M,Maniezzo V,Colorni A.Antsystem:Optimization by a colony of cooperating agents[J]].IEEE Trans on Systems Man and Cybernetics,Part B,1996,26(1):29-41.
[7]	李祥飞,邹恩,邹莉华,等.前馈神经网络的混沌学习方法研究[J].小型微型计算机系统,2004,25(2):233-236.LI Xiangfei,ZOU En,ZOU Lihua,et al.Chaos optimization design for feed-forward neural networks[J].Mini-micro Systems,2004,25(Z):233-236.(in Chinese)
[8]	Vapnik V,Golowich S,Smola A.Support vector method for function approximation,regression estimation and signat processing[C]//Proceedings of the lOth Annual Conference on Neural Information Processing Systems.Cambridge:MA,USA:MIT Press,1997:281-287.
[9]	郑水波,韩正之,唐厚君,等.最小二乘支持向量机在汽车动态系统辨识中的应用[J].上海交通大学学报,2005,39(3):392-395.ZHENG Shuibo,HAN Zhengzhi,TANG Houjun,et al.Application of LS-SVMs in theautomobile dynamical systern identmcation[J].Journal of Shanghai Jiaotong University,2005,39(3):392-395.(in Chinese)