The objective of this one-year EAGER project is to explore the theoretical framework of engineering knowledge transfer in Cybermanufacturing Systems. Cybermanufacturing has the potential to fundamentally transform the manner in which people interact with manufacturing. A critical issue with cybermanufacturing such as Cyber-Physical Additive Manufacturing Systems (CPAMS) is quality control of the interconnected and oftentimes distributed manufacturing environments. End-part quality control is made difficult by enormous differences in product designs/varieties, materials, processes, users conditions, and low production volume. A general consequence of such heterogeneity is that quality control policies established for one process are hardly transferable to others, resulting in increased system lead-time and operation cost. A science base for the transfer of control policies across different cybermanufacturing environments does not exist. In the field of Machine Learning, Transfer Learning (TL) has emerged in recent decades to enable knowledge transfer by exploring correlation or similarity between processes. The purely data-driven TL approaches neither take advantage of nor generates physical insights into the relationship between engineering processes. Consequently, there are no analytical principles or guidelines for production engineers to transfer quality control procedures.
|Effective start/end date||9/1/17 → 7/31/18|
- National Science Foundation (CMMI-1833195)
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.