Design and Development of Knowledge Base Scheme for Chromite-based Resin Bonded Sand Core System

Abstract

An expert system is developed in the present paper to predict the mechanical properties of chromite-based resin bonded sand core system. The various properties of sand cores, such as hardness, compression strength, collapsibility, tensile strength, hot strength, shear strength and permeability depends upon numerous process parameters, viz. percentage of resin, percentage of hardener, additives, number of strokes and curing time. In this paper, Mamdani-based fuzzy logic (FL) approach has been used to develop the knowledge base scheme(that is, forward and reverse modeling) for chromite-based resin bonded sand core system. However, the prediction efficiency of FL system depends on the knowledge base (KB), which consists of rule base and data base. Three varied approaches have been implemented in the suggested work. Manually constructed FL system is developed in the first Approach, whereas in Approach 2, genetic algorithm (GA) is exploited to optimize the data base and rule base of FL system developed in Approach 1. On the other hand in Approach 3, automatic evolution of rules is well advised along with the use of GA to optimize data base and rule base. The developed FL system annihilates the need of extensive experimental work in selecting the most potent process parameters. The performances of all three approaches have been examined with the help of twenty experimental test cases. It is to be stated that all the three developed approaches can be effectively used in foundry for making prediction. The results showed that the Approach 3 has outperformed the remaining two, in terms of prediction accuracy.