Digital twin-driven cyber-physical production system towards smart shop-floor

Abstract

Smart manufacturing is the core in the 4th industrial revolution. Smart shop-floor is one of the basic units of smart manufacturing. With the development of the advanced technologies (e.g. cloud computing, internet of things, model-based definition, advanced simulation, artificial intelligence), a larger number of virtual shop-floors are being built. However, it is very important that how to realize the intelligent interconnection and interaction between physical shop-floors and virtual ones. Digital twin (DT) is one of the key technologies associated to the cyber-physical system. In this paper, we present our vision on the cyber-physical production system (CPPS) towards smart shop-floor at scale via DT. This paper firstly explores a product manufacturing digital twin (PMDT), which focuses on the production phase in smart shop-floor. The proposed PMDT consists of five models: Product Definition Model (PDM), Geometric and Shape Model (GSM), Manufacturing Attribute Model (MAM), Behavior and Rule Model (BRM) and Data Fusion Model (DFM). And then based on PMDT, this paper proposes a new architecture of CPPS, which is composed of five layers (physical layer, network layer, database layer, model layer, application layer). Finally, this paper addresses the opportunities to use DT for the CPPS to support job scheduling during normal operation. Furthermore, the related further work and suggestions are also discussed.