Purchasing decision of machine tool by exploiting uncertain information in nested probabilistic linguistic model

Abstract

As the global environment deteriorates further, the decision-makers of enterprises no longer only consider qualitative factors such as yield in the choice of machine tools, but also pay more attention to the green sustainability and intelligent structure. In this study, a two-stage decision-making framework is established and a decision support system that combines quantitative and qualitative analysis is built to handle the machine tool purchasing decision. The first stage focused on quantitative analysis is to propose the mathematical model of the intelligent production system. Two heuristic algorithms that are automatic optimization method and periodic search method are designed to preliminary screen alternatives. The second stage related to qualitative analysis is to propose an improved TOPSIS method with nested probabilistic linguistic term set to obtain the best alternative comprehensively. In the end, we design the production schedule for the best alternative and prove the practicability and validity of the proposed models and algorithms. This study contributes to providing a theoretical perspective of representing uncertain information, as well as a practical scenario for purchasing decisions.