Real-time implementation of neural optimal control and state estimation for a linear induction motor

被引：9
作者：
Lopez, Victor G. [1 ]
Alanis, Alma Y. [2 ]
Sanchez, Edgar N. [1 ]
Rivera, Jorge [2 ]
机构：
[1] CINVESTAV, Unidad Guadalajara, Guadalajara 45091, Jalisco, Mexico
[2] Univ Guadalajara, CUCEI, Zapopan 45080, Jalisco, Mexico
来源：
NEUROCOMPUTING | 2015年 / 152卷
关键词：
Neural optimal control; Recurrent neural networks; Neural observers; Linear induction motor; Real-time implementation; Control Lyapunov function;
D O I：
10.1016/j.neucom.2014.10.031
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
A reduced order state estimator based on recurrent high-order neural networks (RHONN) trained using an extended Kalman filter (EKF) is designed for the magnetic fluxes of a linear induction motor (LIM). The proposed state estimator does not need the mathematical model of the plant. This state estimator is employed to obtain the unmeasurable state variables of the LIM in order to use a state feedback nonlinear controller. A neural inverse optimal control is implemented to achieve trajectory tracking for a position reference. Real-time implementation results on a LIM prototype illustrate the applicability of the proposed scheme. (C) 2014 Elsevier B.V. All rights reserved.
引用
收藏
页码：403 / 412
页数：10
相关论文
共 42 条
[1]  
Alanis A. Y., 2011, IEEE T NEURAL NETW, V22
[2]  
Alanis A. Y., 2011, 2011 IEEE S COMP INT
[3]  
Alanis A. Y., 2006, P C DEC CONTR 2006 S
[4]  
[Anonymous], 2004, Kalman filtering and neural networks
[5]  
[Anonymous], 2008, DISCRETE TIME HIGH O
[6]  
Bellman R. E., 1957, Dynamic programming. Princeton landmarks in mathematics
[7]  
Feemster M., 2001, IEEE T CONTROL SYST, V9
[8]  
Freeman R. A., 1996, Robust Nonlinear Control Design
[9]  
Gadoue S. M., 2009, IEEE T IND ELECT, V56
[10]  
Hairik H.A., 2009, IRAQ J ELECT ELECT E, V5
12345