基于RBF网络辨识的涡扇发动机双变量神经网络PID解耦控制

杨华; 郭迎清

基于RBF网络辨识的涡扇发动机双变量神经网络PID解耦控制

杨华,
郭迎清

西北工业大学动力与能源学院, 西安 710072

计量
- 文章访问数: 1448
- HTML浏览量: 4
- PDF量: 398
- 被引次数: 0
出版历程
- 收稿日期: 2006-07-24
- 修回日期: 2006-10-07
- 刊出日期: 2007-08-28

Double variable PID decoupling control of turbofan engine based on RBF neural network identification

School of Power and Energy, Northwestern Polytechnical University, Xi'an 710072, China

摘要

摘要: 根据神经网络与PID算法相结合的思想, 针对涡扇发动机双变量控制中变量之间的耦合问题, 提出基于径向基函数神经网络(RBF)辨识的发动机双变量神经网络PID解耦控制, 并给出控制系统的控制结构及原理.仿真结果表明, 该方法控制精度高、跟踪性能强、鲁棒性良好, 能够有效地减小各回路之间的耦合影响, 并保证控制系统具有良好的稳态和动态性能, 适合航空发动机控制.
- 航空、航天推进系统 /
- 涡扇发动机 /
- 双变量控制 /
- 径向基函数神经网络(RBF) /
- 解耦
Abstract: According to the concept of combining the neural network and PID in solving the problem of coupling in turbofan engine double-variable control system, double variable PID decoupling control method for turbofan engine based on RBF neural network identification was presented in this paper.The structure of engine decoupling control system, as well as its decoupling principle was given.Simulation of the control system was performed and excellent tracking performance and robustness were obtained.The simulation results show that the method can effectively reduce the coupling influence of each control loop and assure satisfactory transient performance, thus it is suitable for the aero-engine control.
- aerospace propulsion system /
- turbofan engine control /
- double variable control /
- radial basis function(RBF)neural network /
- decoupling

HTML

参考文献(10)

[1]	Narendra K S,Neural networks for control theory and practice[J].IEEE,1996,84(10):1385-1406.
[2]	Rokhsaz K,Steck J E,Shue S P,Longitudinal flight control decoupling using artificial neural network[R].AIAA-94-0274,1994.
[3]	KrishnaKumar K,Kulkarni N,Inverse adaptive neuro-control of a turbo-fan engine[R].AIAA-99-3994,1999.
[4]	黄金泉,蔡红武,孙健国.航空发动机多变量三层神经网络控制[J].航空动力学报,1999,14(2):191-194.HUANG Jinquan,CAI Hongwu,SUN Jianguo,Multivariable control for aeroengine with 3-layer neural network[J].Journal of Aerospace Power,1999,14(2):191-194.
[5]	蒋衍君,黄金泉.航空发动机自适应神经网络PID控制[J].航空动力学报,2000,15(3):334-336.JIANG Yanjun,HUANG Jinquan,Adaptive neural network PID control for an aeroengine[J].Journal of Aerospace Power,2000,15(3):334-336.
[6]	郭迎清,章泓,杨云波,等.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,et al.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.
[7]	蒋陵平,左渝钰,傅强.航空发动机模糊神经网络控制研究[J].微计算机信息(测控自动化),2005,21(12-1):74-75.JIANG Lingping,ZUO Yuyu,FU Qiang,Study on FuzzyNeural Networks Control of Aero-engine[J].Control and Automation,2005,21 (12-1):74-75.
[8]	刘建勋,李应红,陈永刚,等.航空发动机递归神经网络分路式解耦控制[J].航空动力学报,2005,20(2):287-292.LIU Jianxun,LI Yinghong,CHEN Yonggang,et al.Aeroengine separate decoupling control based on recursive neural networks[J].Journal of Aerospace Power,2005,20 (2):287-292.
[9]	刘延峰,郭迎清.基于新型神经网络的航空发动机多变量控制[J].航空发动机,2005,31(1):34-36.LIU Yanfeng,GUO Yingqing.Aircraft engine double variable controller based on a new neural network[J].Aeroengine,2005,31(1):34-36.
[10]	刘金琨.先进PID控制MATLAB仿真[M].2版.北京:电子工业出版社,2004:171-172.