Bentonite is a natural material indispensable for underground cavity construction, also in the context of safety-critical applications such as radioactive waste disposal. The material behavior of bentonite is complex in the sense that it exhibits nonlinearity, heterogeneity and strong dependence on coupled interactions. Moreover, the material behavior can vary heavily at different geological sites. As a consequence, it has not yet been possible to develop a universal material model for bentonite. Machine learning and statistical methods open up new possibilities to accelerate and automate material model selection, parameter identification and further development of material models by linking information from different sources (lab tests and monitoring). Within this collaborative project, these possibilities will be explored together with partners from BGE Tec GmbH and TU Freiberg (Prof. Thomas Nagel).
Funding Body: Federal Ministry for the Environment, Nature Conservation, Nuclear Safety and Consumer Protection
Funding Period: 02/2025 – 01/2028
The design of underground cavities is subject to numerous uncertainties. Computational models provide insight into areas that are neither inaccessible to the human eye nor to sensors. A limiting factor, however, are modeling assumptions and the identification of model parameter. To better exploit the possibilities of computational modeling in the context underground cavity construction, automated calibration and optimization with in-build uncertainty estimates is indispensable. In this project our primary focus is on Kriging.
Funding Body: Federal Ministry for the Environment, Nature Conservation, Nuclear Safety and Consumer Protection
Funding Period: 05/2023 – 04/2026
Further Reading
Artificial intelligence is gaining rapidly importance across disciplines. How can we cope with the fast paced research and development in this field? In the BMBF funded collaborative project KI4ALL, we are developing AI related microcredits: small, interchangeable teaching units. When clustered, microcredits can be integrated into existing curricula, or be used in continued education scenarios.
Funding Body: Federal Ministry of Education and Research
Funding Period: 01/2022 – 12/2025
Further Reading
If it were possible to include process parameters into the computational optimization of material properties, the design of additively manufactured components could enable the local manipulation of material properties. However, this requires optimization not only of the structure-property, but of the full process-structure-property chain. This project focuses on the development of a methodology for online prediction of microstructures from thermal measurements. Thereby, this project will contribute to online property control in metal additive manufacturing.
Funding Body: German Research Foundation
Funding Period: 07/2023 – 06/2026
Further Reading
Within the subproject C04 of SPP100+, we aim to develop a monitoring strategy for structures based on available measuring principles and the provision of corresponding time-variant condition information. The focus is on an adaptive AI-based service life prediction for a combined impact of chloride exposure and mechanical loads. The monitoring and forecast data will be linked in an extended building information model (digital twin). The service life management system willenable optimised and locally differentiated maintenance and repair measures.
Funding Body: German Research Foundation
Funding Period: 10/2022 – 09/2025
Further Reading
Infrastructures are usually designed under the assumption of an ideal state that lasts during the entire service life. Yet, materials are subject to continuous change, eventually degrade and thereby harm reliability. The fundamental goal of the research training group is the development of scientific approaches to describe and to evaluate the evolution of the physical behavior of buildings and infrastructures during service life. Based on the broad education regarding different building materials, the doctoral-students will get the possibility to understand and to evaluate completely different phenomena and to describe them by advanced models for life-time-prognosis of civil engineering structures.
Funding Body: German Research Foundation
Funding Period: 04/2020 – 09/2024
Further Reading