Automatic data-driven modeling and H2/H∞ - Norm-based dimensional reduction of process-oriented and cooperative systems for SHM condition analysis using system identification and machine learning methods on exposed structures
The digital transformation is bringing about far-reaching changes in all areas of society. In the fusion of BIM, the optimized planning, execution and management of facilities, buildings and infrastructure, with structural health monitoring (SHM), a digital twin acts as a central element of efficient data organization.
The objective of this project is a method that realizes automated data-driven modelling based on the H2/H-infinity standard and methods of system identification coupled with machine learning. This enables a condition analysis as a digital twin over the service life of the real twin, the building, which is incorporated into an SHM/BIM concept. Based on process-oriented cooperative systems, special physically interpretable indicators are able to automatically display and localize structural changes.
The numerical method works with stochastic multi-correlated output-only measurement data with special consideration and classification of environmental and operating conditions. The automatically generated parameterized stochastic process models of the system and filter theory enable a prediction of future damage states of the investigated structure. This provides the building owner with a set of tools for the predictive planning of maintenance measures on structures with high economic benefits.
Start: September 2022
