A Data-Driven Approach for Quality Analytics of Screwing Processes in a Global Learning Factory

Abstract Quality problems of screwing processes in assembly systems, which are an important issue for operation excellence, needs to be quickly analyzed and solved. A network can be very beneficial for root cause analysis due to different data from various factories. Nevertheless, it is difficult to obtain reliable and consistent data. In this context, this paper aims to develop a method for data-driven oriented quality analytics of screwing processes considering a global production network. Firstly, the overview of data structure is introduced. Further, the data transformation is modelled for edge- and cloud-based analytics across the global production network. Lastly, the rules for analyzing are identified. A joint case study based on Learning Factory Global Production (LF) in Germany and I4.0 Innovation Centre and Artificial Intelligence Innovation Factory (IC&AIIF) in China is used to validate the proposed approach, which is also a new teaching method for quality analysis in the framework of learning factory.