Bayesians networks to assist the inspection planning in small batch production

Abstract

With consumers' tastes changing frequently, companies are forced to adopt small batch production schedules. Inspection planning is a critical phase in the small batch production due to lack of sufficient data to establish control decisions for product variety. We need to focus on the actual process parameters that produce the product rather than the traditional method of measuring a product characteristic to control the process. It is actually the process that produces a product that is responsible for the quality of the output. Once we realize this, we start focusing on process characteristics irrespective of which variety of product it produces. This paper presents an inspection planning decision support system based on probabilistic methods and focused on the process parameters control. The methods used for the construction of the system are introduced, with emphasis on mechanisms to quantify Bayesians networks.