In manufacturing industry, wider range variants and personalized productions are becoming formidable challenges that needed to be for smart manufacturing. In smart manufacturing, machines are connected cooperatively to seamlessly and quickly adjust production setting to reach market requirements. Furthermore, real-time production data visualization and evaluation are the keys to increase manufacturing productivity, efficiency, and flexibility. This integrated research is aimed to develop an intelligent coil leveling machine through dynamic analysis of real-time machine sensors network for cyber-physical systems implementation in smart manufacturing. In this proposed intelligent coil leveling machine, intelligent sensors network is embedded in the machine to allow real-time monitoring of the machine through feedback controlled system and cloud network to ensure optimized production with optimal machine setting instantly. Intelligent sensors network of the proposed coil leveling machine such as leveling roller indentation, leveling force, and coil curvature has been completed. Preliminary real-time dynamic monitoring of the leveling rollers and coil curvature has been accomplished. Following, real-time dynamic analysis is performed to demonstrate the implementation of the cyber-physical systems where machine learning intelligence can be achieved. Lastly, real-time cloud network monitoring are implemented to allow users to collect manufacturing data online. Through this research, conventional leveling machine can be transformed in which machine setting configurations can be adjusted to the production line through virtual cyber-physical system. Production data can be visualized and evaluated in real-time with precise and intelligent production strategies to ensure customer's requirements and to enhance production efficiency and flexibility in smart manufacturing of sheet metal coil.
Chen, B., & Chang, J. Y. J. (2017). Dynamic Analysis of Intelligent Coil Leveling Machine for Cyber-physical Systems Implementation. In Procedia CIRP (Vol. 63, pp. 390–395). Elsevier B.V. https://doi.org/10.1016/j.procir.2017.03.115