Generalized predictive control for non-stationary systems

Olafur P. Palsson*, Henrik Madsen, Henning T. Søgaard

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

17 Citations (Scopus)


This paper shows how the generalized predictive control (GPC) can be extended to non-stationary (time-varying) systems. If the time-variation is slow, then the classical GPC can be used in context with an adaptive estimation procedure of a time-invariant ARIMAX model. However, in this paper prior knowledge concerning the nature of the parameter variations is assumed available. The GPC is based on the assumption that the prediction of the system output can be expressed as a linear combination of present and future controls. Since the Diophantine equation cannot be used due to the time-variation of the parameters, the optimal prediction is found as the general conditional expectation of the system output. The underlying model is of an ARMAX-type instead of an ARIMAX-type as in the original version of the GPC (Clarke, D. W., C. Mohtadi and P. S. Tuffs (1987). Automatica, 23, 137-148) and almost all later references. This implies some further modifications of the classical GPC.

Original languageEnglish
Pages (from-to)1991-1997
Number of pages7
Issue number12
Publication statusPublished - Dec 1994

Other keywords

  • filtering
  • Generalized predictive control (GPC)
  • impulse response
  • time-varying systems


Dive into the research topics of 'Generalized predictive control for non-stationary systems'. Together they form a unique fingerprint.

Cite this