Neural Generalized Predictive Control of a non-linear Process

Paul Haase Sørensen, Peter Magnus Nørgård, Ole Ravn, Niels Kjølstad Poulsen

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    Abstract

    The use of neural network in non-linear control is made difficult by the fact the stability and robustness is not guaranteed and that the implementation in real time is non-trivial. In this paper we introduce a predictive controller based on a neural network model which has promising stability qualities. The controller is a non-linear version of the well-known generalized predictive controller developed in linear control theory. It involves minimization of a cost function which in the present case has to be done numerically. Therefore, we develop the numerical algorithms necessary in substantial detail and discuss the implementation difficulties. The neural generalized predictive controller is tested on a pneumatic servo sys-tem.
    Original languageEnglish
    Title of host publicationProceedings of the SCI' 98
    Place of Publicationflorida
    Publication date1998
    Publication statusPublished - 1998
    EventWorld Multiconference on Systemics, Cybernetics and Informatics 1998 - Orlando, United States
    Duration: 12 Jul 199816 Jul 1998

    Conference

    ConferenceWorld Multiconference on Systemics, Cybernetics and Informatics 1998
    CountryUnited States
    CityOrlando
    Period12/07/199816/07/1998
    OtherJointly with 4th International Conference on Information Systems, Analysis and Synthesis ISAS' 98

    Cite this