Performance optimisation of learning feed forward control

Wubbe J.R. Velthuis, Theo J.A. de Vries, Job van Amerongen

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    10 Downloads (Pure)

    Abstract

    The performance of sub-optimal feedback controllers can be improved in several ways. In this paper a learning control strategy is considered. The learning control system consists of the feedback and a feed forward controller. The feed forward controller is implemented as a neural network that is trained during control in order to minimise the tracking error. The type of neural network is a single layer network, in which B-spline basis functions are used to store the input-output mapping. The distribution of the Bsplines on the domain of the input(s) is of influence on the performance of the learning controller. Until recently, the basis functions were distributed by rule of thumb. In this paper fuzzy clustering techniques are used to obtain the distribution in a systematic way. In experiments the learning controller has been used to control a linear motor.
    Also when the B-splines are chosen by rule of thumb, the learning controller was able to improve the performance of the feedback controller considerably. The tracking error could be reduced further by determining the distribution of the basis functions using fuzzy clustering.
    Original languageEnglish
    Title of host publicationArtificial intelligence in real-time control 1997 (AIRTC'97)
    Subtitle of host publicationa proceedings volume from the IFAC symposium, Kuala Lumpur, Malaysia, 22-25 September 1997
    EditorsHerbert E. Rauch
    Place of PublicationOxford
    PublisherPergamon Press
    Pages391-396
    Number of pages6
    ISBN (Print)9780080429274
    Publication statusPublished - 22 Sep 1997
    EventIFAC Symposium on Artificial Intelligence in Real-Time Control, AIRTC 1997 - Kuala Lumpur, Malaysia
    Duration: 22 Sep 199725 Sep 1997

    Conference

    ConferenceIFAC Symposium on Artificial Intelligence in Real-Time Control, AIRTC 1997
    Abbreviated titleAIRTC
    CountryMalaysia
    CityKuala Lumpur
    Period22/09/9725/09/97

    Keywords

    • Intelligent control
    • Neural control
    • Adaptation
    • B-spline networks
    • Fuzzy clustering

    Fingerprint Dive into the research topics of 'Performance optimisation of learning feed forward control'. Together they form a unique fingerprint.

    Cite this