A CNN video based control system for a coal froth flotation

Abstract

The design of a control system to monitor a coal froth flotation process is considered. This system is based upon a hydrodynamic model for the resistance and a feedback loop consisting of an image processing application that is responsible for extracting relevant parameters from a video image of the froth. This paper deals with the application of the CNN technology in the design of a prototype control system. A description of the low level image processing methods implemented is given as well as comments on the problems encountered during the design of a prototype control system using a new technology such as the cellular neural network paradigm.