Unveiling Relations in the Industry 4.0 Standards Landscape based on\n Knowledge Graph Embeddings

Industry~4.0 (I4.0) standards and standardization frameworks have been\nproposed with the goal of \\emph{empowering interoperability} in smart\nfactories. These standards enable the description and interaction of the main\ncomponents, systems, and processes inside of a smart factory. Due to the\ngrowing number of frameworks and standards, there is an increasing need for\napproaches that automatically analyze the landscape of I4.0 standards.\nStandardization frameworks classify standards according to their functions into\nlayers and dimensions. However, similar standards can be classified differently\nacross the frameworks, producing, thus, interoperability conflicts among them.\nSemantic-based approaches that rely on ontologies and knowledge graphs, have\nbeen proposed to represent standards, known relations among them, as well as\ntheir classification according to existing frameworks. Albeit informative, the\nstructured modeling of the I4.0 landscape only provides the foundations for\ndetecting interoperability issues. Thus, graph-based analytical methods able to\nexploit knowledge encoded by these approaches, are required to uncover\nalignments among standards. We study the relatedness among standards and\nframeworks based on community analysis to discover knowledge that helps to cope\nwith interoperability conflicts between standards. We use knowledge graph\nembeddings to automatically create these communities exploiting the meaning of\nthe existing relationships. In particular, we focus on the identification of\nsimilar standards, i.e., communities of standards, and analyze their properties\nto detect unknown relations. We empirically evaluate our approach on a\nknowledge graph of I4.0 standards using the Trans$^*$ family of embedding\nmodels for knowledge graph entities. Our results are promising and suggest that\nrelations among standards can be detected accurately.\n