Evaluating melt iron features by computer aided recognition of thermal analysis cooling curves

A relation database of thermal analysis cooling curves, composition, microstructure and mechanical properties of various cast irons under fixed casting condition has been set up. Based on the pattern recognition principle, the authors developed an approach to precisely evaluate the melt iron features and predict the mechanical properties of the corresponding casting by finding a corresponding cooling curve from the database which is most similar to the measured one. This method is self-adaptive to the production condition and has been put into application in several foundries.