Modeling Industrial Processes
with Hybrid-Neural Intelligent Systems
(Intelligent advisory system for a Linz-Donawitz steel converter)

Intelligent Systems Research Group

The Linz-Donawitz converter

LD converter steelmaking is a complex physico-chemical process where many variables have effects on thequality of the resulted steel. The main features of the process are the followings: a large (~150-ton) converter is filled with waste iron, melted pig iron and many additives, then it is blasted through with pure oxygen to burn out the unwanted contamination (e.g. silicon, etc.). There are about 30-50 input parameters registered: like the temperature and the mass values of the components (pig iron, waste iron), the mass values of the different additives (lime, fluorite, etc.), and two essentially important output parameters: the carbon content of the steel and its temperature at the end of the blasting process. During blasting the temperature of the melted material is increased by about 200 C, while the carbon content is decreased to about one hundredth of its starting value.

The quality of the steel and other output parameters are mainly determined by the amount of oxygen used during blasting. The acceptable ranges of the output parameters are rather narrow, so it is an important and rather hard task to create a reliable predictor to determine the amount of oxygen necessary to obtain predetermined quality steel.

Click here to start a step by step demonstration of the process