An intelligent controller for aluminium smelter potlines

The control parameters for the Hall-Heroult electrolytic process to industrially produce aluminium metals are cryolite ratio, current efficiency and heat balance which are seen to be dependent on the bath resistance. In this paper, the authors present an intelligent controller based on the bath resistance process model, using the MLIAC (Multi Level Intelligent Control) architecture. The design is targeted to improve the real-time performance of the intelligent control, i.e. through the use of a simple plant model, a priori learning, adaptation based on asynchronous parametric estimation, and an inference mechanism based on SQL like constructs, in a structured data environment. The controllers are modular, distributed, hierarchical, and well coordinated. Simulation studies, are in progress, and are expected to show it is possible to achieve higher plant productivity, and a high net energy savings with the MLIAC architecture