Composite Process Models Used in Stock Tank Quantity Prediction for Sugar Mill Crystallization Stage Knowledge-Based Supervisory Support

Abstract

The present paper proposes the component process models for a knowledge-based supervisory support system designed to provide expert knowledge in the control and management of a sugar mill crystallization stage. Forecasting stock tank quantities, within the sugar factory crystallization stage, is beneficial to ensure that there are sufficient quantities of stock materials to allow completion of production schedules without disruption. It is shown that integration of projected vacuum pan feed rates with syrup rate production models and vacuum pan phase detection models allows forecasting of stock tank quantities for syrup and molasses in order to work towards the goal of forewarning of potential problems with the current operating strategies and advising corrective procedures. These industrial process models form an integral part of an overall pan stage knowledge-based supervisory support system to assist in providing a better decision-making strategy for crystallization stage operations.