A neuro fuzzy logic approach to material processing

A new application of fuzzy systems to the processing of materials is presen ted. The relationships between temperature, time, and the impact strength o f an austempered ductile iron (ADI) part are adaptively modeled. Pour fuzzy and neuro fuzzy approaches have been used to build predictive models. Thes e are a fuzzy-based model, a backpropagation-based neuro fuzzy model, a clu stering-based model, and a clustering-backpropagation-based neuro fuzzy mod el. The clustering approach, using the subclustering method, yielded the be st predictive results when all models had been given the same input-output training data. The backpropagation-based neuro fuzzy approach suffers from the lack of a higher number of input-output data training sets. All prelimi nary results obtained suggest the adequacy of the fuzzy-based and neuro fuz zy-based modeling techniques to tackle those types of problems in the mater ial-processing areas.