Simulation-based optimization using DEA and DOE in production systems

Abstract

Production System (PS) is the process of planning, organizing, directing, and controlling the tactical and strategic planning of di erent components of a company in order to transform inputs into nished products, which must be e ectively managed. Important parts of a PS that always face major challenges in manufacturing include production strategy, resource allocation, logistics, and production planning. Because of the importance of examining various PS components and evaluating their performance in key indicators of organization, it is necessary to evaluate the impact of any changes in these elements on the system prior to its creation. In this regard, the present study aims to increase the efficiency and determine the useful methods to evaluate and optimize the performance of di erent PS parts. To this end, an integrated Discrete-Event Simulation (DES), Design Of Experiments (DOE), Data Envelopment Analysis (DEA), and Multi-Attribute Decision Making (MADM) models were implemented to analyze and optimize the real PS process. In the case study of the automobile manufacturing industry in Iran, accurate analysis was applied to the proposed approach and its di erent aspects were considered, as well. The results indicate that the proposed approach is a practical way for evaluating and optimizing the performance of di erent PS parts, compared to previous models, and helps manufacturing companies make efficient decisions regarding increased productivity and fewer essential problems.