Navigating the Data Model Divide in Smart Manufacturing: An Empirical Investigation for Enhanced AI Integration

In engineering informatics, the myriad data types, formats, streaming and storage technologies pose significant challenges in managing data effectively. The problem grows, as new analytics perspectives are emerging from a totally different AI-based tradition. This divide often necessitates the development of custom solutions that link specific data capture methods to particular AI algorithms. Encouraged by the success of object-centric mining models for discrete processes, we look for large clusters of data management practices where novel bridging data models can help navigate the data model divide. We address this question in a two-cycle design science approach. In a first cycle, over 80 actual data model practices from a wide variety of engineering disciplines were analyzed, leading to four candidate fields. In a second cycle, an initial bridging data model for one of these fields was developed and validated wrt some of the found practices. Our findings offer the prospect of significantly streamlining data pipelines, paving the way for enriched AI integration in production engineering, and consequently, a more robust, data-driven manufacturing paradigm.