Feedback linearization control of nonlinear uncertain systems using single hidden layer neural networks

2014 ◽  
Author(s):  
Mohammed Belkhiri ◽  
Hamou Ait Abbas ◽  
Boubakeur Zegnini
Keyword(s):  
Neural Networks ◽  
Feedback Linearization ◽  
Uncertain Systems ◽  
Feedback Linearization Control ◽  
Nonlinear Uncertain Systems ◽  
Hidden Layer

Adaptive Feedback Linearization Control of SISO Nonlinear Processes Using a Self-Generating Neural Network-Based Approach

2011 ◽  
Vol 6 (1) ◽  
Author(s):  
Karim Salahshoor ◽  
Amin Sabet Kamalabady
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Adaptive Control ◽  
Feedback Linearization ◽  
Learning Algorithm ◽  
Rbf Neural Networks ◽  
Adaptive Feedback ◽  
Control Scheme ◽  
Feedback Linearization Control ◽  
Adaptive Control Scheme

This paper presents a new adaptive control scheme based on feedback linearization technique for single-input, single-output (SISO) processes with nonlinear time-varying dynamic characteristics. The proposed scheme utilizes a modified growing and pruning radial basis function (MGAP-RBF) neural network (NN) to adaptively identify two self-generating RBF neural networks for online realization of a well-known affine model structure. An extended Kalman filter (EKF) learning algorithm is developed for parameter adaptation of the MGAP-RBF neural networks. The MGAP-RBF growing and pruning criteria have been endeavored to enhance its performance for online dynamic model identification purposes. A stability analysis has been provided to ensure the asymptotic convergence of the proposed adaptive control scheme using Lyapunov criterion. Capabilities of the adaptive feedback linearization control scheme is evaluated on two nonlinear CSTR benchmark processes, demonstrating good performances for both set-point tracking and disturbance rejection objectives.

Position Control of a Manipulator Robotic Arm Considering Flexible Joints Driven by a DC Motor and a Controlled Torque by a MR-Brake

2016 ◽  
Author(s):  
Jeferson J. Lima ◽  
Rodrigo T. Rocha ◽  
Frederic C. Janzen ◽  
Angelo M. Tusset ◽  
Dailhane G. Bassinello ◽  
...  
Keyword(s):  
Neural Networks ◽  
Feedback Control ◽  
Feedback Linearization ◽  
Position Control ◽  
Dc Motor ◽  
The State ◽  
Robotic Arm ◽  
Flexible Joints ◽  
State Dependent ◽  
Feedback Linearization Control

This paper presents a two-degree-of-freedom robotic arm design with flexible joints driven by a DC Motor and controlled by a Magnetorheological (MR) Brake, considering a feedback control. The MR Brake is used to provide adjustable constraints in motion of the manipulator and compensate overshoot by interactions between the robot’s links and flexible joints of the motor drive mechanism. The torque of the MR Brake is obtained by the Radial Basis Function Neural Networks (RBFNN), which is a widely used class of neural networks for prediction or approximation of function. The RBFNN provides the nonlinear curve of hysteresis of MR brake to use torque. Two controllers were proposed to control the manipulator. The first one is obtained by feedback linearization control with the objective to remove the non-dependent terms of the state space equation. The second one is the feedback control obtained using the State-Dependent Riccati Equation (SDRE) with the objective of controlling the position of the manipulator and the torque applied on the MR brake. The numerical simulation results showed that the proposed control using both signal feedback linearization control and a feedback control signal by a DC Motor and MR Brake is effective to control the flexible joint manipulators.

Sign in / Sign up

Export Citation Format

Share Document