Nowadays, smart manufacturing has attracted more and more interesting and attentions of researchers. As an important prerequisite for smart manufacturing, the cyber-physical integration of manufacturing is becoming more and more important. Cyber-physical systems (CPS) and digital twin (DT) are the preferred means to achieve the interoperability and integration between the physical and cyber worlds. From the perspective of hierarchy, CPS and DT can be divided into unit level, system level, and SoS (system of system) level. To meet the different requirements of each level, the following three complementary technologies, i.e., edge computing, fog computing and cloud computing, are instrumental to accelerate the development of various CPS and DT. In this article, the perspectives of unit-level, system-level, and SoS-level of CPS and DT supported by edge computing, fog computing and cloud computing are discussed.
Lightweight Convolution Neural Networks for Mobile Edge Computing in Transportation Cyber Physical Systems