An Expert System Based on a Hybrid Multi-Criteria Decision Making Method for Selection of Non-Conventional Machining Processes

In this study, a knowledge-based system has been developed for selection of non-conventional machining processes using a hybrid multi-criteria decision making Method. This approach is a combination of DEMATEL (Decision Making Trial and Evaluation Laboratory), ANP (Analytic Network Process) and VIKOR (VlseKriterijumska Optimizacija I Kompromisno Resenje, in Serbian, meaning Multi-criteria Optimization and Compromise Solution) methods which evaluates different types of quantitative and qualitative measures of performance and economic factors, and ultimately provides a set of capable processes in order of priority. Twelve machining processes, eight group of workpiece material and eighteen shape features have been investigated in this study. What separates this approach from others is that, this hybrid method considers the influence of factors in the network relation map as well as their relative importance. Moreover, unlike other popular ranking methods such as TOPSIS (Technique for Order Preference by Similarity to the Ideal Solution), it is not just based on two reference points, namely ideal and inferior points; instead, it proposes a compromise solution and not just a single ranking score. Observations have shown that the developed system works satisfactorily, yields acceptable results and makes accurate decisions as well. It also provides a comparative study among the alternative processes by utilizing graphical features for better analysis and judgment of acceptable alternatives.