An Edge-Fog-Cloud Computing-Based Digital Twin Model for Prognostics Health Management of Process Manufacturing Systems

Abstract

The prognostics health management (PHM) from the systematic view is critical to the healthy continuous operation of process manufacturing systems (PMS), with different kinds of dynamic interference events. This paper proposes a three leveled digital twin model for the systematic PHM of PMSs. The unit-leveled digital twin model of each basic device unit of PMSs is constructed based on edge computing, which can provide real-time monitoring and analysis of the device status. The station-leveled digital twin models in the PMSs are designed to optimize and control the process parameters, which are deployed for the manufacturing execution on the fog server. The shop-leveled digital twin maintenance model is designed for production planning, which gives production instructions from the private industrial cloud server. To cope with the dynamic disturbances of a PMS, a big data-driven framework is proposed to control the three-level digital twin models, which contains indicator prediction, influence evaluation, and decision-making. Finally, a case study with a real chemical fiber system is introduced to illustrate the effectiveness of the digital twin model with edge-fog-cloud computing for the systematic PHM of PMSs. The result demonstrates that the three-leveled digital twin model for the systematic PHM in PMSs works well in the system's respects.