Clustering aided approach for decision making in computationally expensive multiobjective optimization

摘要: Typically, industrial optimization problems need to be solved in an efficient, multiobjective and global manner, because they are often computationally expensive (as function values typically based on simulations), may contain multiple conflicting objectives, have several local optima. Solving such challenging time consuming when the aim is find most preferred Pareto optimal solution. In this study, we propose a method where use advanced clustering technique reveal essential characteristics of approximation set, which has been generated beforehand. Thus, decision maker (DM) involved only after computation finished. After initiation phase, moderate number cluster prototypes projected set presented DM studied. This allows him/her rapidly gain overall understanding main problem without placing too much cognitive load DM. Furthermore, also suggest some ways applying our approach different types demonstrate it with example related internal combustion engine design.