基于SVM辨识的涡扇发动机全包线稳态控制方法

刘建勋; 李罡; 吕孟军; 尉询凯

基于SVM辨识的涡扇发动机全包线稳态控制方法

1.
空军第一航空学院航空机械工程系,河南信阳 464000
2.
空军装备研究院航空装备研究所,北京 100076

计量
- 文章访问数: 1519
- HTML浏览量: 2
- PDF量: 552
- 被引次数: 0
出版历程
- 收稿日期: 2011-07-19
- 刊出日期: 2012-07-28

Identification method based on support vector machines for turbofan engine steady state control in full flight envelop and various working conditions

1.
Aeronautic Mechanical Engineering Department, The First Aeronautical College of Air Force,Xinyang Henan 464000,China
2.
Research Institute of Aeronautic Equipment, Air Force Equipment Academe,Beijing 100076,China

摘要

摘要: 针对涡扇发动机全飞行包线范围稳态最优控制器的设计问题,首先根据不同飞行条件下发动机各工作状态的稳态“小偏差”线性模型,采用线性二次型调节器(LQR)分别设计得到相应的发动机最优线性控制器参数,然后将所得到的线性控制器用支持向量机方法进行非线性逼近,得到控制器参数的支持向量机辨识模型,以满足发动机全包线、全状态稳态控制的需要.支持向量机模型的输入为飞行高度、马赫数和稳态转速,输出为线性控制器参数.应用实例表明:该方法在全包线范围内对发动机最优稳态控制器的逼近误差均在2%以内,能较好满足控制精度要求.
- 涡扇 /
- 发动机 /
- 稳态控制 /
- 线性二次型 /
- 支持向量机 /
- 辨识
Abstract: To accomplish steady state optimal control of turbofan engine in full flight envelop and in different working conditions,nonlinear estimation methods based on linear steady state models of turbofan in all operation points were presented.The principle and algorithm realization of support vector machines for nonlinear controller approximation were improved.Then,the method used the improved support vector machines to establish the identification model of many linear optimization controllers designed for turbofan engine in some representative flight conditions.The controller design results for other operation points in the flight envelope can be conveniently educed by the model.For the identification model,the inputs were the steady rotation speed,the flight altitude and the flight Mach number,and the outputs were the parameters of the synthetic controller.The application examples show that the identification errors of the method in the whole flight envelop and various working conditions can meet the control precision need.
- turbofan /
- engine /
- steady state control /
- linear quadratic regulator /
- support vector machines /
- identification

HTML

参考文献(15)

[1]	Wiseman M W.Advanced online control mode selection for gas turbine aircraft engines .Cincinnati,Ohio:University of Cincinnati,1995.
[2]	樊思齐.航空发动机控制(下册)[M].西安:西北工业大学出版社,2008.
[3]	赵海.改进型LQR方法在飞机控制律设计中的应用[J].飞机工程,2006,3(1):63-66. ZHAO Hai.Application of improved LQR method to control law design of an airplane[J].Aircraft Engineering,2006,3(1):63-66.(in Chinese)
[4]	王前宇,孙健国,李秋红.航空发动机三变量鲁棒控制器设计[J].航空动力学报,2009,24(11):2607-2611. WANG Qianyu,SUN Jianguo,LI Qiuhong.Three variables robust controller design for aeroengine[J].Journal of Aerospace Power,2009,24(11):2607-2611.(in Chinese)
[5]	刘建勋,李应红,陈永刚.航空发动机LQR控制的模糊神经网络方法[J].航空动力学报,2004,19(6):838-843. LIU Jianxun,LI Yinghong,CHEN Yonggang.Aeroengine LQR control based on fuzzy-neural network[J].Journal of Aerospace Power,2004,19(6):838-843.(in Chinese)
[6]	郭迎清,章泓,杨云波.利用神经网络设计航空发动机全包线最优控制器[J].航空动力学报,2000,15(3):331-333. GUO Yingqing,ZHANG Hong,YANG Yunbo.The design of aero-engine optimal controller suitable for all flight envelope with neural network approximator[J].Journal of Aerospace Power,2000,15(3):331-333.(in Chinese)
[7]	梁华,李应红,尉询楷.航空发动机的支持向量机自适应PID控制[J].航空动力学报,2007,22(1):137-141. LIANG Hua,LI Yinghong,WEI Xunkai.Support vector machines PID adaptive control in aeroengine[J].Journal of Aerospace Power,2007,22(1):137-141.(in Chinese)
[8]	袁胜发,褚福磊.基于改进型球结构支持向量机的故障诊断方法及其应用[J].推进技术,2006,27(1):1-4. YUAN Shengfa,CHU Fulei.Fault diagnosis based on improved sphere support vector machines[J].Journal of Propulsion Technology,2006,27(1):1-4.(in Chinese)
[9]	刘建勋.涡扇发动机起动过程的学习机模型与动态控制研究 .西安:空军工程大学,2005. LIU Jianxun.Mathematical model of turbofan engine starting based on learning machines and dynamical control research .Xi'an: Airforce Engineering University,2005. (in Chinese)
[10]	WEI Xunkai,LI Yinghong.Comparative study of extreme learning machine and support vector machine[J].LNCS,2006(3971):1089-1095.
[11]	Smola A J,Schölkopf B.A tutorial on support vector regression .Royal Holloway College,University of London,Technical Report NC-TR-98-030,1998.
[12]	Vapnik V N,Chapelle O.Choosing multiple parameters for support vector machines[J].Machine Learning,2002,46(1):124-136.
[13]	Schölkopf B,Smola A J.New support vector algorithms[J].Neural Computation,2000,12(5):1207-1245.
[14]	吕建伟,李军.考虑雷诺数、湿度等影响因素的涡扇发动机小偏差模型[J].航空动力学报,2005,20(1):44-48. LV Jianwei,LI Jun.Reynolds number and humidity effect on the small deviation model of turbofan engine[J].Journal of Aerospace Power,2005,20(1):44-48.(in Chinese)
[15]	杨刚,姚华.一种航空发动机相似多变量控制方法[J].航空动力学报,2006,21(3):588-594. YANG Gang,YAO Hua.Theory of similarity based aeroengine multivariable control method[J]. Journal of Aerospace Powe,2006,21(3):588-594.(in Chinese)