On dealing with measured disturbances in the modifier adaptation method for real-time optimization

Abstract

Extends the modifier adaptation method for real-time optimisation to include information on measured or estimated disturbances, by estimating process gradients with respect to both decision variables and disturbances. Tested on a laboratory flotation column with changing feed, including delayed disturbance information estimated with ARIMA models, the approach tracked the process optimum under continuously changing conditions.

Dr Paulina Quintanilla

Assistant Professor in Process Systems Engineering

Assistant Professor in Process Systems Engineering at UCL, leading the LOOPS research group. Research interests include machine learning, optimisation and control for processes and physical systems.