Multilayer recurrent neural networks for real-time robust pole assignment

Sanqing Hu, Jun Wang

Результат исследований: Глава в книге, отчете, сборнике статейМатериалы для конференциирецензирование

Аннотация

Robust pole assignment is an effective design method for linear control systems subject to parameter perturbation. In this paper, two multilayer recurrent neural networks are presented for robust pole assignment. One of them is called state-independent annealing neural network (SIANN) and the other is called state-dependent annealing neural network (SDANN). The proposed recurrent neural networks are composed of three layers and are shown to be capable of synthesizing linear control systems via robust pole assignment in real time. The SDANN is proven to converge for any design parameters. Moreover, the neural network converges exponentially to an optimal solution of the robust pole assignment problem and the perturbed closed-loop control system based on the neural network is globally exponentially stable with appropriate design parameters. These desirable properties make it possible to apply the neural network to slowly time-varying linear control systems. Simulation results are shown to illustrate the effectiveness, advantages, and operating characteristics of the proposed approach.

Язык оригиналаАнглийский
Название основной публикацииICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing
Подзаголовок основной публикацииComputational Intelligence for the E-Age
РедакторыJagath C. Rajapakse, Soo-Young Lee, Lipo Wang, Kunihiko Fukushima, Xin Yao
ИздательInstitute of Electrical and Electronics Engineers Inc.
Страницы1104-1108
Число страниц5
ISBN (электронное издание)9810475241, 9789810475246
DOI
СостояниеОпубликовано - 2002
Опубликовано для внешнего пользованияДа
Событие9th International Conference on Neural Information Processing, ICONIP 2002 - Singapore, Сингапур
Продолжительность: 18 нояб. 200222 нояб. 2002

Серия публикаций

НазваниеICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age
Том3

Конференция

Конференция9th International Conference on Neural Information Processing, ICONIP 2002
Страна/TерриторияСингапур
ГородSingapore
Период18/11/0222/11/02

Fingerprint

Подробные сведения о темах исследования «Multilayer recurrent neural networks for real-time robust pole assignment». Вместе они формируют уникальный семантический отпечаток (fingerprint).

Цитировать