Grinding Wheel Management through Neuro-Fuzzy Forecasting of Dressing Cycle Time

A multiple supplier tool management system based on reliable tool delivery forecasting is developed for optimum tool inventory sizing. The system is built up on the basis of historical data on tool management comprising the series of tool shipment and delivery dates between one manufacturing company and several external tool manufacturers in a supply network. If historical data are highly variable due to the incidence of uncertain but not random factors, classical time series analysis cannot measure the Imprecision deriving from events that are neither stochastic nor casual. An alternative is given by the analysis through intelligent computing techniques capable to deal with deterministic events but also take into account unpredictable factors for better results in prediction and forecast. A neuro-fuzzy system is used in this paper to approach optimum tool inventory sizing of CBN grinding wheels for nickel base alloy turbine blade fabrication.