A decision theory approach to support action plans in cooker hoods manufacturing

Nowadays, Knowledge-Based systems are widespread decision-making tools applied in product design and manufacturing planning. The series production requires agile and rapid decision-making methods to support actions in manufacturing lines. Therefore, agent-based tools are necessary to support the detection, diagnosis, and correction of accidental production faults. The context of Industry 4.0 has been enhancing the integration of sensors in manufacturing lines to monitor production and analyze failures. The motivation of the proposed research is to study and validate decision theory methods to be applied in smart manufacturing. This paper shows a Knowledge-Based approach to support action decision-making processes by a Bayesian network model. The proposed method aims at solving production problems detected in the manufacturing process. In particular, the focus is on the automatic production of cooker hoods. A case study describes how the approach can be applied in the real-time control actions, after a problem in quality is detected.