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

    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

    Fingerprint

    Feedforward control
    Controllers
    Fuzzy clustering
    Feedback
    Splines
    Neural networks
    Network layers
    Linear motors
    Control systems

    Keywords

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

    Cite this

    Velthuis, W. J. R., de Vries, T. J. A., & van Amerongen, J. (1997). Performance optimisation of learning feed forward control. In H. E. Rauch (Ed.), Artificial intelligence in real-time control 1997 (AIRTC'97): a proceedings volume from the IFAC symposium, Kuala Lumpur, Malaysia, 22-25 September 1997 (pp. 391-396). Oxford: Pergamon Press.
    Velthuis, Wubbe J.R. ; de Vries, Theo J.A. ; van Amerongen, Job. / Performance optimisation of learning feed forward control. Artificial intelligence in real-time control 1997 (AIRTC'97): a proceedings volume from the IFAC symposium, Kuala Lumpur, Malaysia, 22-25 September 1997. editor / Herbert E. Rauch. Oxford : Pergamon Press, 1997. pp. 391-396
    @inproceedings{9882634e51c041eaa7d97c81e8e9c2f5,
    title = "Performance optimisation of learning feed forward control",
    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.",
    keywords = "Intelligent control, Neural control, Adaptation, B-spline networks, Fuzzy clustering",
    author = "Velthuis, {Wubbe J.R.} and {de Vries}, {Theo J.A.} and {van Amerongen}, Job",
    year = "1997",
    month = "9",
    day = "22",
    language = "English",
    isbn = "9780080429274",
    pages = "391--396",
    editor = "Rauch, {Herbert E.}",
    booktitle = "Artificial intelligence in real-time control 1997 (AIRTC'97)",
    publisher = "Pergamon Press",
    address = "United Kingdom",

    }

    Velthuis, WJR, de Vries, TJA & van Amerongen, J 1997, Performance optimisation of learning feed forward control. in HE Rauch (ed.), Artificial intelligence in real-time control 1997 (AIRTC'97): a proceedings volume from the IFAC symposium, Kuala Lumpur, Malaysia, 22-25 September 1997. Pergamon Press, Oxford, pp. 391-396, IFAC Symposium on Artificial Intelligence in Real-Time Control, AIRTC 1997, Kuala Lumpur, Malaysia, 22/09/97.

    Performance optimisation of learning feed forward control. / Velthuis, Wubbe J.R.; de Vries, Theo J.A.; van Amerongen, Job.

    Artificial intelligence in real-time control 1997 (AIRTC'97): a proceedings volume from the IFAC symposium, Kuala Lumpur, Malaysia, 22-25 September 1997. ed. / Herbert E. Rauch. Oxford : Pergamon Press, 1997. p. 391-396.

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

    TY - GEN

    T1 - Performance optimisation of learning feed forward control

    AU - Velthuis, Wubbe J.R.

    AU - de Vries, Theo J.A.

    AU - van Amerongen, Job

    PY - 1997/9/22

    Y1 - 1997/9/22

    N2 - 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.

    AB - 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.

    KW - Intelligent control

    KW - Neural control

    KW - Adaptation

    KW - B-spline networks

    KW - Fuzzy clustering

    M3 - Conference contribution

    SN - 9780080429274

    SP - 391

    EP - 396

    BT - Artificial intelligence in real-time control 1997 (AIRTC'97)

    A2 - Rauch, Herbert E.

    PB - Pergamon Press

    CY - Oxford

    ER -

    Velthuis WJR, de Vries TJA, van Amerongen J. Performance optimisation of learning feed forward control. In Rauch HE, editor, Artificial intelligence in real-time control 1997 (AIRTC'97): a proceedings volume from the IFAC symposium, Kuala Lumpur, Malaysia, 22-25 September 1997. Oxford: Pergamon Press. 1997. p. 391-396