基于RVM回归误差补偿的航空发动机分布式控制系统多步预测控制

王磊; 谢寿生; 苗卓广; 任立通; 余坚

基于RVM回归误差补偿的航空发动机分布式控制系统多步预测控制

1.
空军工程大学航空航天工程学院, 西安 710038
2.
中国人民解放军93704部队, 北京 101100

计量
- 文章访问数: 1624
- HTML浏览量: 118
- PDF量: 845
- 被引次数: 0
出版历程
- 收稿日期: 2012-11-03
- 刊出日期: 2013-06-28

Multi-step predictive control for aero-engine distributed control system based on RVM regression error compensation

1.
Aeronautics and Astronautics Engineering Institute, Air Force Engineering University, Xi'an 710038, China
2.
Unit 93704 of Chinese People's Liberation Army, Beijing 101100, China

摘要

摘要: 针对具有随机有界双侧时延的航空发动机分布式控制系统,提出了一种基于多步预测和关联向量机(RVM)回归误差补偿的控制方案.首先建立航空发动机分布式控制系统(DCS)的神经网络非线性自回归滑动平均(NARMA)模型,利用当前的系统输出和控制量对N步之后的系统输出进行预测;其次用改进的RVM回归多步预测算法估计NARMA模型的的预测误差,并对预测结果进行误差补偿;最后利用补偿之后的预测值和设定值对控制参数进行滚动优化,设计系统的神经网络逆控制器实现系统的自适应控制.仿真结果证明该控制策略能够避免随机有界双侧时延对控制系统的影响,实现对设定值的稳定跟踪,且控制器具有较好的实时性和鲁棒性.低压转子转速阶跃响应的稳态绝对误差小于0.04%,响应时间小于0.3s.
- 航空发动机 /
- 分布式控制系统 /
- 非线性自回归滑动平均(NARMA)模型 /
- 多步预测控制 /
- 误差时间序列 /
- 关联向量机(RVM)
Abstract: A multi-step predictive control method based on relevance vector machine(RVM) regression error compensation was put forward to control aero-engine distributed control system(DCS) with stochastic and bounded time-delay.The neural network nonlinear auto regressive moving average(NARMA) model of the aero-engine DCS was established to predict the future output.An improved multi-step prognostic algorithm based on RVM regression was presented to estimate prognostic error series which were compensated for the NARMA model.Finally,a neural network inverse controller was designed,and rolling optimization of the parameters was conducted by prognostic output and the expectations.Simulation results illustrate the control strategy avoids the effect of stochastic and bounded time-delay on the control system.The controller has favorable dynamic tracking and robust performance.The absolute steady error of low-pressure rotor speed step response is less than 0.04%,and the response time is less than 0.3 s.
- aero-engine /
- distributed control system /
- nonlinear auto regressive moving average(NARMA) model /
- multi-step predictive control /
- time series error /
- relevance vector machine (RVM)

HTML

参考文献(16)

[1]	彭靖波,谢寿生,武卫,等.航空发动机分布式控制系统指数稳定性分析[J].航空动力学报,2009,24(10):2362-2367. PENG Jingbo,XIE Shousheng,WU Wei,et al.Stability analyzation of aero-engine distributed control system[J].Journal of Aerospace Power,2009,24(10):2362-2367.(in Chinese)
[2]	朱其新,胡寿松.网络控制系统的分析与建模[J].信息与控制,2003,32(1):5-8. ZHU Qixin,HU Shousong.Analysis and modeling of network control systems[J].Information and Control,2003,32(1):5-8.(in Chinese)
[3]	刘涛,王岩.基于时延估计组合模型的NCS控制方法研究[J].计算机工程与应用,2010,46(30):78-81. LIU Tao,WANG Yan.Study on control method of NCS based on time delay estimation combined model[J] Computer Engineering and Applications,2010,46(30):78-81.(in Chinese)
[4]	潘海鹏,吕勇松.时滞系统的模糊神经网络补偿控制[J].浙江大学学报:工学版,2010,44(7):1343-1347. PAN Haipeng,LV Yongsong.Fuzzy neural network control method with compensation for time-delay system[J].Journal of Zhejiang University:Engineering Science,2010,44(7):1343-1347.(in Chinese)
[5]	王瑞敏,费树岷,柴琳.网络控制系统的预测补偿[J].控制理论与应用,2011,28(10):1473-1479. WANG Ruimin,FEI Shumin,CHAI Lin.Predictive compensation for networked control systems[J].Control Theory & Applications,2011,28(10):1473-1479.(in Chinese)
[6]	付伟,杨先一,冯伟,等.网络控制系统时延的预测控制补偿方法[J].系统工程与电子技术,2011,33(9):2066-2071. FU Wei,YANG Xianyi,FENG Wei,et al.Predictive control compensation for time delay in networked control systems[J].Systems Engineering and Electronics,2011,33(9):2066-2071.(in Chinese)
[7]	魏东,刘熙,张龙.神经网络非线性多步预测逆控制方法研究[J].计算机应用研究,2012,29(1):211-214. WEI Dong,LIU Xi,ZHANG Long.Multi-step predictive inverse control based on neural networks[J].Application Research of Computers,2012,29(1):211-214.(in Chinese)
[8]	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[J].航空动力学报,2008,23(10):1913-1920. ZHAO Jun,CHEN Jianjun,WANG Linggang.New intelligent neural network adaptive control scheme research for aeroengine[J].Journal of Aerospace Power,2008,23(10):1913-1920.(in Chinese)
[9]	宗晓萍,冯贺平.基于神经网络的时滞系统预测控制[J].控制理论与应用,2005,24(12):6-8. ZONG Xiaoping,FENG Heping.Neural network based predictive control for time delay systems[J].Control Theory and Application,2005,24(12):6-8.(in Chinese)
[10]	蔡开龙.航空推进系统分布式综合控制研究与试验[D].西安:空军工程大学,2008. CAI Kailong.Research of the aeronautic propulsion distributed control system[D].Xi'an:Air Force Engineering University,2008.(in Chinese)
[11]	Chen L,Narendra K S.Identification and control of a nonlinear discrete-time system based on its linearization:a unified framework[J].Transactions on Neural Networks,2004,15(3):663-673.
[12]	Cabrera J B D.Nonlinear ARMA models and the general tracking problem for discrete-time dynamical systems[D].New Haven,Connecticut,US:Yale University,1997.
[13]	魏震,李长虹,谢剑英.网络控制系统在线时延估计控制[J].控制与决策,2003,18(5):545-549. WEI Zhen,LI Changhong,XIE Jianying.Online delay-evaluation control for networked control systems[J].Control and Decision,2003,18(5):545-549.(in Chinese)
[14]	陈秋霞,俞立,黄骅.基于RVM的非线性预测控制及在聚丙烯牌号切换中的应用[J].控制与决策,2010,25(8):1241-1245. CHEN Qiuxia,YU Li,HUANG Hua.Application of RVM-based nonlinear predictive control to polypropylene grade transition[J].Control and Decision,2010,25(8):1241-1245.(in Chinese)
[15]	Candela J Q,Girard A,Larsen J,et al.Propagation of uncertainty in Bayesian kernel models-application to multiple-step ahead forecasting[C]//Proceedings of IEEE International Conference on Acoustics,Speech,and Signal Processing.Lyngby,Danmark:IEEE,2003:701-704.
[16]	张磊,李行善,于劲松,等.基于关联向量机回归的故障预测算法[J].系统工程与电子技术,2010,32(7):1540-1543. ZHANG Lei,LI Xingshan,YU Jinsong,et al.Fault prognostic algorithm based on relevance vector machine regression[J].Systems Engineering and Electronics,2010,32(7):1540-1543.(in Chinese)