Robust model predictive control of nonlinear systems with unmodeled dynamics and bounded uncertainties based on neural networks

Zheng Yan, Jun Wang

Результат исследований: Вклад в журналСтатьярецензирование

119 Цитирования (Scopus)

Аннотация

This paper presents a neural network approach to robust model predictive control (MPC) for constrained discrete-time nonlinear systems with unmodeled dynamics affected by bounded uncertainties. The exact nonlinear model of underlying process is not precisely known, but a partially known nominal model is available. This partially known nonlinear model is first decomposed to an affine term plus an unknown high-order term via Jacobian linearization. The linearization residue combined with unmodeled dynamics is then modeled using an extreme learning machine via supervised learning. The minimax methodology is exploited to deal with bounded uncertainties. The minimax optimization problem is reformulated as a convex minimization problem and is iteratively solved by a two-layer recurrent neural network. The proposed neurodynamic approach to nonlinear MPC improves the computational efficiency and sheds a light for real-time implementability of MPC technology. Simulation results are provided to substantiate the effectiveness and characteristics of the proposed approach.

Язык оригиналаАнглийский
Номер статьи6582522
Страницы (с-по)457-469
Число страниц13
ЖурналIEEE Transactions on Neural Networks and Learning Systems
Том25
Номер выпуска3
DOI
СостояниеОпубликовано - мар. 2014
Опубликовано для внешнего пользованияДа

Fingerprint

Подробные сведения о темах исследования «Robust model predictive control of nonlinear systems with unmodeled dynamics and bounded uncertainties based on neural networks». Вместе они формируют уникальный семантический отпечаток (fingerprint).

Цитировать