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

Intelligent Systems Research Group

The direct and indirect neural modeling approach

Direct method builds inverse (controller) neural model using the available data set

Indirect method creates plant model in the first step, and uses this model to generate patterns for the training of the inverse model

wpe2.jpg (27644 bytes)