Modelling module of the intelligent control system for variable volume pressure filter

Abstract

Artificial Intelligence methods like expert systems, fuzzy logic and neural networks have proved to be excellent tools for the control of mineral processes. This technology is currently being embedded directly into process equipment like flotation cells and dewatering filters. This paper presents the modelling module for a pressure filter. The modelling module of the intelligent system predicts filtration using the two-stage hybrid model. The first stage model is based on a numerical model for compressive cake filtration and the second stage model is the identified grey-box model based on the classical filtration model. The filtration parameters for the compressive cake filtration model were obtained from laboratory tests. The parameters for the classical filtration model are defined during filtration using the recursive least square identification method. The two-stage hybrid model of the on-line support system was tested in a full-size filter at a pilot plant.