Discrete-Time Output Trajectory Tracking for Induction Motor using a Neural Observer

Abstract

This paper presents the design of an adaptive controller based on the block control technique, and a new neural observer for a class of MIMO discrete-time nonlinear systems. The observer is based on a recurrent high-order neural network (RHONN), which estimates the state vectors of the unknown plant dynamics. The learning algorithm for the RHONN is based on an extended Kalman filter (EKF). This paper also includes the respective stability analysis, using the Lyapunov approach, for the whole system, which includes the nonlinear plant, the neural observer trained with the EKF and the block controller. Applicability of the proposed scheme is illustrated via simulation for a discrete-time nonlinear model of an electric induction motor.

References

Page 1

	Year	Citations
Backpropagation through time: what it does and how to do it Paul J. Werbos Proceedings of the IEEE Fault DiagnosisEngineeringMachine LearningNeural Networks (Machine Learning)Intelligent Systems	1990	4.8K
A Learning Algorithm for Continually Running Fully Recurrent Neural Networks Ronald J. Williams, David Zipser Neural Computation Artificial IntelligenceExact FormGradient-following Learning AlgorithmEngineeringMachine Learning	1989	4.4K
Training Multilayer Perceptrons with the Extended Kalman Algorithm Sharad Singhal, Lance Wu Neural Information Processing Systems State EstimationArtificial IntelligenceExtended Kalman AlgorithmIncremental LearningEngineering	1988	319
The Extended Kalman Filter as a Local Asymptotic Observer for Nonlinear Discrete-Time Systems Yongkyu Song, Jessy W. Grizzle State EstimationNonlinear System IdentificationNonlinear Discrete-time SystemsNonlinear ControlLocal Asymptotic Observer	1992	294
Adaptive Neural Network Control for a Class of MIMO Nonlinear Systems With Disturbances in Discrete-Time Shuzhi Sam Ge, J. Zhang, Tae-Hee Lee IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) Nonlinear ControlNonlinear System IdentificationMimo SystemEngineeringAdaptive Neural Network	2004	226
AVOIDING CONTROLLER SINGULARITIES IN ADAPTIVE RECURRENT NEURAL CONTROL Ramón A. Félix, Edgar N. Sánchez, Alexander G. Loukianov IFAC Proceedings Volumes Adaptive ControlNeuroscienceRobot LearningLearning ControlRecurrent Neural Network	2005	35
Inverse optimal nonlinear recurrent high order neural observer Luis J. Ricalde, Edgar N. Sánchez Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Nonlinear ControlState ObserverNeural Network WeightsUnknown PlantIntelligent Control	2006	31
Robust stabilization of a class of uncertain system via block decomposition and VSC Alexander G. Loukianov, B. Castillo–Toledo, Stephen J. Dodds International Journal of Robust and Nonlinear Control EngineeringRobust ControlSliding ManifoldsUncertain SystemMatched Uncertainty	2002	20
Discrete- Time Recurrent Neural Induction Motor Control using Kalman Learning Alma Y. Alanís, Edgar N. Sánchez, A.G. Loukianov The 2006 IEEE International Joint Conference on Neural Network Proceedings Adaptive Tracking ProblemNonlinear ControlControl MethodEngineeringMotor Drive	2006	12

Page 1