Engineering standards are an important source of knowledge in product development. Despite the increasing digitalisation, the provision and usage of standards is characterised by lots of manual steps. This research paper aims at applying automatic knowledge graph creation in the domain of engineering standards to enable machine-actionable standards. For this, a formula knowledge graph ontology as well as suitable information extraction techniques are developed. The concept is validated using the example of DIN ISO 281, showing the overall capability of automatic knowledge graph creation.

Managing general domain knowledge and asset-specific information in the form of digital representations is especially important and challenging when focusing on long-living and complex assets. Implicit knowledge and existing structures need to be captured and digitalised, ideally without introducing unnecessary complexity through unfamiliar wording or new structures. To achieve this, a methodical approach that utilises ontologies as well as system modelling techniques and focuses on early-stage model instantiation is presented and applied to the cabin retrofit of aircraft

High amount of changes and increasing complexity in CAD design of wiring harnesses result in a lack of time for documentation and transfer of acquired knowledge. To be able to transfer the gained knowledge efficiently during development automating the identification, analyzation and documentation of changes is necessary. This paper shows a methodology to address this challenge for CAD data of wiring harnesses. Thus, it is shown how interrelated change elements can be combined or separated from each other according to their change intention.

This paper builds a patent-based knowledge graph, patent-KG, to represent the knowledge facts in patents for engineering design. The arising patent-KG approach proposes a new unsupervised mechanism to extract knowledge facts in a patent, by searching the attention graph in language models. The extracted entities are compared with other benchmarks in the criteria of recall rate. The result reaches the highest 0.8 recall rate in the standard list of mechanical engineering related technical terms, which means the highest coverage of engineering words.