Optimising Predictive Control Based on Neural Models

  • Authors:
  • Maciej Ławryńczuk

  • Affiliations:
  • Institute of Control and Computation Engineering, Warsaw University of Technology, Warsaw, Poland 00-665

  • Venue:
  • AIMSA '08 Proceedings of the 13th international conference on Artificial Intelligence: Methodology, Systems, and Applications
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents a Model Predictive Control (MPC) algorithm for on-line economic optimisation of nonlinear technological processes. The economic profit is explicitly expressed in the minimised objective function. The algorithm uses only one dynamic neural model, which is linearised on-line. As a result, an easy to solve on-line quadratic programming problem is formulated. In contrast to the classical multilayer control system structure, the necessity of repeating two nonlinear optimisation problems at each sampling instant is avoided.