FCANN Method Applications for Knowledge Extraction From Previously Trained ANN

Nowadays, artificial neural networks are being widely used in the representation of physical processes. Once trained, the nets are capable to solve unprecedented situations, keeping tolerable errors in their outputs. However, humans cannot assimilate the knowledge kept by these networks, since such knowledge is implicitly represented by their structure and connection weights. Recently, the FCANN method, based in formal concept analysis, has been proposed as a new approach in order to extract, represent and understand the behavior of the process through rules. In this work, the approach FCANN will be applied in three processes with different characteristics: solar energy system, climatic behavior and the cold rolling process. The results show the great potential of the new method and discuss the representation of the obtained rules.