Establishing work design criteria through a highest expected utility neural network model: An automotive trim case study

The purpose of this research is two-folded. First, it attempts to maximize productivity and yield as well as to minimize the spatial fixed cost through the development of a work design decision making tool for optimizing work cell configurations and ergonomics. Second, the case study applies influence diagram and neural network to analyze and evaluate work/process design criteria. Practically, the industrial problem is to compare the new stand-up sewing cells against the traditional sit-down sewing layout while taking into consideration of ergonomic effect (repetitive motion injury (RMI) likelihood), floor space (SF), yield (%), and cost ($). The work design decision making tool used in the current study is based on influence diagram run on the HUGIN neural network software. Statistical tests are used to benchmark and validate the experimental results and actual data. Findings suggest that neural network is an effective alternative in solving work design problem.