A Proactive Model for Joint Maintenance and Logistics Optimization in the Frame of Industrial Internet of Things

Abstract

Equipment failures in manufacturing processes concern industries because they can lead to severe issues regarding human safety, environmental impact, reliability, and production costs. The stochastic nature of equipment degradation and the uncertainty about future breakdowns affect significantly the maintenance and inventory decisions. Proactive event processing can facilitate this decision-making process in an Industrial Internet of Things (IIoT) environment, but real-time data processing poses several challenges in efficiency and scalability of the associated information systems. Therefore, appropriate real-time, event-driven algorithms and models are required for deciding on the basis of predictions, ahead of time. We propose a proactive event-driven model for joint maintenance and logistics optimization in a sensor-based, data-rich industrial environment. The proposed model is able to be embedded in a real-time, event-driven information system in order to be triggered by prediction events about the future equipment health state. Moreover, the proposed model handles multiple alternative (imperfect and perfect) maintenance actions and associated spare parts orders and facilitates proactive decision making in the context of Condition-Based Maintenance (CBM). The proposed proactive decision model was validated in real industrial environment and was further evaluated with a comparative and a sensitivity analysis.