A fuzzy AHP–ANN-based decision support system for machine tool selection in a flexible manufacturing cell

Abstract

In respond to new market requirements and competitive positioning of manufacturing companies and in order to provide cost effective, high performance products, there is a need for reconfigurable manufacturing systems with a view of introducing new manufacturing technologies. However one of the problems faced is how to select the alternative machines that are consistent with manufacturing goals. In this paper a decision support system is presented for machine tool selection in flexible manufacturing cell using fuzzy analytic hierarchy process (fuzzy AHP) and artificial neural network. A program is developed in the model to find the Priority weights of the Evaluation Criteria and Alternative's Ranking called PECAR for fuzzy AHP model. The artificial neural network (ANN) is used to verify the results of fuzzy AHP (PECAR program) and to predict the alternatives' ranking. A feed forward back propagation ANN is designed and trained using the results from the program. A numerical example to select the most suitable CNC machine based on data collected from a designed questionnaire is given to demonstrate the applicability of the proposed model. The result of neural net simulation is compared with the results from fuzzy AHP model. It is concluded that the proposed decision support system by combining the fuzzy AHP and ANN models can be used as a powerful tool to select the most suitable alternative machines to form the structure of a flexible manufacturing cell.