Over 100

The digital transformation is bringing about far-reaching changes across all areas of society. In the integration of BIM – which involves the optimised planning, construction and management of facilities, buildings and infrastructure – with Structural Health Monitoring (SHM), a digital twin acts as a central element of efficient data organisation.

The objective of this project is to develop a method that implements automated, data-driven modelling based on the H2/H-infinity norm and system identification methods, coupled with machine learning. This enables a condition analysis, in the form of a digital twin, to be carried out over the lifetime of the real twin – the structure – which is then integrated into an SHM/BIM concept. Based on process-oriented cooperative systems, specific, physically interpretable indicators are capable of automatically detecting and localising structural changes.

The numerical method utilises stochastic, multicorrelated output-only measurement data, with particular consideration given to and classification of environmental and operational conditions. The automatically generated, parameterised stochastic process models from system and filter theory enable the prediction of future damage conditions in the structure under investigation. This provides the building authority with a set of tools for the proactive planning of maintenance measures on structures, with significant economic benefits.

As part of the joint project under the DFG Priority Programme “Hundert plus – Extending the service life of complex building structures through intelligent digitalisation”, HTWK Leipzig is working on the following sub-project: “Automatic data-driven modelling and H2/H∞-norm-based dimensionality reduction of process-oriented and cooperative systems for SHM condition analysis using system identification and machine learning methods on exposed structures”.

Visit the project website