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

Intelligent Systems Research Group

The Hybrid Intelligent System Approach

To build experimental models for utilizing the different representations
of heterogeneous information appropriate model architectures have to be selected.

• Neural network models built on large amount of measured typical data
• Output estimator and correction term expert systems encapsulates expert
  knowledge to handle cases with outlier parameters and special situations
• Input and output expert systems accomplish system management functions
  by analyzing the state of the process and the performance of the intelligent system