Real-time neural inverse optimal control for position trajectory tracking of an induction motor

This paper describes a neural inverse optimal control approach for a three-phase induction motor position trajectory and flux magnitude tracking. A recurrent high order neural network (RHONN) is used to identify the plant model, trained with an Extended Kalman Filter (EKF) algorithm; the control law minimize a cost functional avoiding to solve the Hamilton Jacobi Bellman (HBJ) equation. The applicability of the approach is illustrated via experimental results. The proposed scheme allows the easy integration of this kind of motors into a system of systems configuration.

[1]  Alexander G. Loukianov,et al.  Discrete-Time High Order Neural Control - Trained with Kaiman Filtering , 2010, Studies in Computational Intelligence.

[2]  Sharad Singhal,et al.  Training Multilayer Perceptrons with the Extende Kalman Algorithm , 1988, NIPS.

[3]  A. Chu,et al.  A novel neural network controller and its efficient DSP implementation for vector controlled induction motor drives , 2002 .

[4]  Alexander G. Loukianov,et al.  Real-Time Discrete Neural Block Control Using Sliding Modes for Electric Induction Motors , 2010, IEEE Transactions on Control Systems Technology.

[5]  P. M. Menghal,et al.  Neural network based dynamic simulation of induction motor drive , 2013, 2013 International Conference on Power, Energy and Control (ICPEC).

[6]  R.A. Freeman,et al.  Optimal nonlinear controllers for feedback linearizable systems , 1995, Proceedings of 1995 American Control Conference - ACC'95.

[7]  E. Ruiz-Velazquez,et al.  Neural inverse optimal control applied to type 1 diabetes mellitus patients , 2012, Analog Integrated Circuits and Signal Processing.

[8]  Alexander G. Loukianov,et al.  Discrete-Time Inverse Optimal Control for Nonlinear Systems , 2013 .

[9]  Alexander G. Loukianov,et al.  Discrete-Time Output Trajectory Tracking for Induction Motor using a Neural Observer , 2007, 2007 IEEE 22nd International Symposium on Intelligent Control.

[10]  Wei Liu,et al.  Adaptive inverse optimal control for a class of nonlinear system , 2011, Proceedings of the 30th Chinese Control Conference.

[11]  Alexander G. Loukianov,et al.  Neural network identification of a double fed induction generator prototype , 2009, 2009 International Joint Conference on Neural Networks.

[12]  Shangtai Jin,et al.  Higher-order model-free adaptive control for a class of discrete-time SISO nonlinear systems , 2011, 2011 Chinese Control and Decision Conference (CCDC).