Recent advances in manufacturing industry have paved way for a systematical deployment of cyber-physical systems (CPS), within which information from all related perspectives is closely monitored and synchronized between the physical factory floor and the cyber computational space. Moreover, by utilizing advanced information analytics, networked machines will be able to perform more efficiently, collaboratively and resiliently. Such trend is transforming the manufacturing industry to the next generation, namely internet-of-things (IoT), or Industry 4.0. Since CPS is in the initial stage of development, it is essential to clearly define the structure and methodology of CPS as guidelines for its implementation in industry. To meet such a demand, we have developed a unified CPS framework that can be used as a generic architecture for the implementation of CPS in industrial applications. In addition, corresponding algorithms and technologies at each system layer have also been developed to collaborate with the unified structure and realize the desired functionalities of the overall system for enhanced equipment efficiency, reliability and product quality.

Implementing smart manufacturing based on our CPS architecture offers several advantages for today’s manufacturer. First, it provides a framework for control since energy, productivity, and costs across factories and companies can be monitored and controlled in real-time. With easier access to this information, manufacturers can maximize talent and productivity by strategically deploying their workforce throughout the factories. Secondly, it enables failure prediction – alerts can be set up within manufacturing facilities to notify operators of the mechanical failures and the remaining useful life (RUL) of manufacturing systems or components, preventing larger problems from occurring and reducing system down time. In addition, it can streamline processes by using advanced modeling and simulation, along with new artificial intelligence capabilities, to eliminate costly trial-and-error and actively correct problems in manufacturing processes.