Neuro-Fuzzy Approach to Forecast Returns of Scrapped Products to Recycling and Remanufacturing

摘要

Forecasting of scrapped products to recycling poses severe problems to recycling and remanu-facturing companies due to uncertainties in timing and quantities of returns. In this paper an extended forecasting method to provide prognoses for return values (amount and time) of scrapped products to recycling is presented. The suggested model is based on relevant influencing factors and product life cycle data and has been applied to a case study (photocopiers) for evaluation and usability. The approach employs a simulation study, the design of a fuzzy inference system for the forecasting of the return in a determined planning period and the design of a neuro-fuzzy system for the forecasting of return values with respect to time.