Online Simulation Optimization Using Neutrosophic Cross-Efficiency DEA and Box–Behnken Experimental Design (A Case Study on the Automotive Paint Shop)

Abstract

Paint shops are considered as bottlenecks in many automobile companies. As all processes in the paint shop are involved with chemical materials, time is really crucial in the production process, so offering instant remedial actions is crucial. This paper optimizes an online simulation (OS) model, using Discrete-Event Simulation (DES), applied to a paint shop in the automotive industry. To this aim, an integrated Box–Behnken design (BBD) and cross-efficiency data envelopment analysis (DEA) under a neutrosophic environment have been implemented. The former has generated cost-effective scenarios with the minimum number of experimental design, and the latter has provided the efficiency of each scenario enabling to obtain a unique weight for each decision-making unit (DMU) using aggressive and benevolent models as well as a general representation of the human perception toward risks arising from uncertain information, leading to determine the optimal scenario. The proposed approach has been implemented in an automotive industrial plant in Iran, and the results have shown that this approach, compared with previous studies, is a practical way for online monitoring and optimizing the paint shop.