A multi-objective evolutionary algorithm for EOL product recovery optimization: turbocharger case study

Recently, the importance of the end- of- life ( EOL) product recovery process has been rising since the return rate of products is increasing due to strict environmental regulations on products and economic reasons. In addition to this, the advent of emerging product identification technologies makes product lifecycle data visible at EOL phase. In this regard, the optimization of product recovery processes becomes highlighted as a challenging issue of EOL. At the inspection phase after disassembly, each part can have various EOL recovery options such as re- use, remanufacturing, and disposal. Depending on the selected EOL options of parts, the recovery value of an EOL product will be different. Hence, it is essential to develop a decision- making method that can select the best EOL options of parts for maximizing the recovery value of an EOL product. Although some previous works have focused on improving EOL operations, there has been a lack of research which dealt with EOL product recovery optimization in a quantitative manner. To cope with this limitation, in this study, we focus on a selection problem of EOL product recovery options for a turbocharger case, for maximizing its recovery value which includes both recovery cost and quality. To solve the problem efficiently, we develop a multi- objective evolutionary algorithm ( MOEA). To show the effectiveness of our algorithm, we carry out computational experiments.