Welcome to the InfoSci Platform
Reference Hub10
Neural Networks Predictive Controller Using an Adaptive Control Rate

Neural Networks Predictive Controller Using an Adaptive Control Rate

Ahmed Mnasser, Faouzi Bouani, Mekki Ksouri
Copyright: © 2014 |Volume: 3 |Issue: 3 |Pages: 21
ISSN: 2160-9772|EISSN: 2160-9799|EISBN13: 9781466656413|DOI: 10.4018/ijsda.2014070106
Cite Article Cite Article

MLA

Mnasser, Ahmed, et al. "Neural Networks Predictive Controller Using an Adaptive Control Rate." IJSDA vol.3, no.3 2014: pp.127-147. http://doi.org/10.4018/ijsda.2014070106

APA

Mnasser, A., Bouani, F., & Ksouri, M. (2014). Neural Networks Predictive Controller Using an Adaptive Control Rate. International Journal of System Dynamics Applications (IJSDA), 3(3), 127-147. http://doi.org/10.4018/ijsda.2014070106

Chicago

Mnasser, Ahmed, Faouzi Bouani, and Mekki Ksouri. "Neural Networks Predictive Controller Using an Adaptive Control Rate," International Journal of System Dynamics Applications (IJSDA) 3, no.3: 127-147. http://doi.org/10.4018/ijsda.2014070106

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

A model predictive control design for nonlinear systems based on artificial neural networks is discussed. The Feedforward neural networks are used to describe the unknown nonlinear dynamics of the real system. The backpropagation algorithm is used, offline, to train the neural networks model. The optimal control actions are computed by solving a nonconvex optimization problem with the gradient method. In gradient method, the steepest descent is a sensible factor for convergence. Then, an adaptive variable control rate based on Lyapunov function candidate and asymptotic convergence of the predictive controller are proposed. The stability of the closed loop system based on the neural model is proved. In order to demonstrate the robustness of the proposed predictive controller under set-point and load disturbance, a simulation example is considered. A comparison of the control performance achieved with a Levenberg-Marquardt method is also provided to illustrate the effectiveness of the proposed controller.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.