Digitisation of as-built structures with AI

The condition of a structure is characterised by the fact that it deteriorates faster with age. A preventive measure against ageing is even more successful the earlier it is taken. To prolong the use of complex structures, comprehensive information is required at the earliest possible stage. On the way to preventive maintenance, basic research is required into the methods of acquisition, consolidation and evaluation of all geometry, material, stress and ageing data. Digitisation in the sense of creating a digital twin takes on a completely new meaning in this context, It enables the consolidation and real-time evaluation of all data required for operation and maintenance. However, the construction industry is faced with special challenges here. Structures, especially in the transport infrastructure, are unique objects. They are characterised by enormous dimensions and have a much longer service life than other technical facilities. The changes in terms of degradation are very small and therefore hardly measurable. The basis of condition monitoring is a comprehensive and complete presentation of the structure. This means a digital representation of the complete external and internal structure, including information on materials, defects, etc The research question can be derived from this, whether such a mapping can be efficiently realised, and in which form and with which methods this is possible. This article gives an overview of how such a mapping can succeed even for complex objects and how the generated model can be enhanced with semantic information.