An intelligent signal validation system for a cupola furnace. II. Testing and analysis

In part I, the motivation behind the signal validation system for the cupola furnace was presented, and a methodology for developing an ANN rule based filter (ANN-RBFTE) and inferential sensors for the molten-iron temperature was described. In this paper we present the testing results of the filter and inferential sensors using cupola experimental data. A methodology for building a signal validation system for the cupola by fusing the data from the ANN-RBFTE and the inferential sensors is also described. The signal validation system is tested using experimental data from a cupola furnace. The testing results verify the excellent performance provided by the validation system. This research provides solid foundation for the implementation of signal validation system to other measurands in the cupola and to other industrial plants.