Performance-oriented antiwindup for a class of linear control systems with augmented neural network controller

Guido Herrmann, Matthew Turner, Ian Postlethwaite

    Research output: Contribution to journalArticlepeer-review

    19 Citations (Scopus)

    Abstract

    This paper presents a conditioning scheme for a linear control system which is enhanced by a neural network (NN) controller and subjected to a control signal amplitude limit. The NN controller improves the performance of the linear control system by directly estimating an actuator-matched, unmodeled, nonlinear disturbance, in closed-loop, and compensating for it. As disturbances are generally known to be bounded, the nominal NN-control element is modified to keep its output below the disturbance bound. The linear control element is conditioned by an antiwindup (AW) compensator which ensures performance close to the nominal controller and swift recovery from saturation. For this, the AW compensator proposed is of low order, designed using convex linear matrix inequalities (LMIs) optimization.
    Original languageEnglish
    Pages (from-to)449-465
    JournalIEEE Transactions on Neural Networks
    Volume18
    Issue number2
    DOIs
    Publication statusPublished - 2007

    Fingerprint Dive into the research topics of 'Performance-oriented antiwindup for a class of linear control systems with augmented neural network controller'. Together they form a unique fingerprint.

    Cite this