Digital twin with automatic disturbance detection for an expert-controlled SAG mill

Abstract

A digital twin of a semi-autogenous grinding (SAG) mill under expert control, combining fuzzy-logic expert control, a state-space model of the regulatory layer and a recurrent neural network of the mill. A statistical layer detects process disturbances automatically and retrains the model only when needed. Trained and validated on industrial data, it predicts mill behaviour 2.5 minutes ahead with errors below 5%.

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.