Analytische Chemie
Filtern
Dokumenttyp
- Beitrag zu einem Tagungsband (2)
- Zeitschriftenartikel (1)
- Vortrag (1)
Sprache
- Englisch (4)
Schlagworte
- Composite structures (4) (entfernen)
Organisationseinheit der BAM
Eingeladener Vortrag
- nein (1)
The aims of the Research Unit „Acting Principles of Nano-Scaled Matrix Additives for Composite Structures“ (DFG FOR 2021) are based on different synergetic pathways. Challenges are to achieve an improved damage tolerance combined with unchanged processability and a proof of the nano-based effect from molecular scale up to structural level. First of all, a comprehensive understanding of the acting mechanisms of nano-scaled ceramic additives onto polymer matrices of continuous fibre reinforced polymer composites with respect to improved matrix dominated properties is in focus. To proof of the nanoscopic and microscopic effects up to structural level; experimental investigations start on the functional correlation between the particle properties and the resulting properties of the epoxy as suspension and in the solid state. This includes tests for the resulting composite structures as well. Along the entire process chain different multi-scale simulations are performed from molecular modelling up to the macroscopic, structural level. The combination of experimental investigations and simulation methods enables a holistic understanding of the acting principles and basic mechanisms.
Specialized techniques based on Scanning Force Microscopy are the basis of our analysis of physicochemical properties of the boehmite nanoparticles and their polymer environment. A surface map of mechanical properties as an input for simulations facilitate a deeper understanding of such composites across all scales. This enables us to understand the macroscopic structure-property relationship and to predict failure mechanisms as well as routes for optimization.
Understanding on how a machine learning model interprets data is a crucial step to verify its reliability and avoid overfitting. While the focus of the scientific community is nowadays orientated towards deep learning approaches, which are considered as black box approaches, this work presents a toolbox that is based on complementary methods of feature extraction and selection, where the classification decisions of the model are transparent and can be physically interpreted. On the example of guided wave benchmark data from the open guided waves platform, where delamination defects were simulated at multiple positions on a carbon fiber reinforced plastic plate under varying temperature conditions, the authors could identify suitable frequencies for further investigations and experiments. Furthermore, the authors presented a realistic validation scenario which ensures that the machine learning model learns global damage characteristics rather than position specific characteristics.
Understanding on how a machine learning model interprets data is a crucial step to verify its reliability and avoid overfitting. While the focus of the scientific community is nowadays orientated towards deep learning approaches, which are considered as black box approaches, this work presents a toolbox that is based on complementary methods of feature extraction and selection, where the classification decisions of the model are transparent and can be physically interpreted. On the example of guided wave benchmark data from the open guided waves platform, where delamination defects were simulated at multiple positions on a carbon fiber reinforced plastic plate under varying temperature conditions, the authors could identify suitable frequencies for further investigations and experiments. Furthermore, the authors presented a realistic validation scenario which ensures that the machine learning model learns global damage characteristics rather than position specific characteristics.
Data-driven analysis for damage assessment has a large potential in structural health monitoring (SHM) systems, where sensors are permanently attached to the structure, enabling continuous and frequent measurements. In this contribution, we propose a machine learning (ML) approach for automated damage detection, based on an ML toolbox for industrial condition monitoring. The toolbox combines multiple complementary algorithms for feature extraction and selection and automatically chooses the best combination of methods for the dataset at hand. Here, this toolbox is applied to a guided wave-based SHM dataset for varying temperatures and damage locations, which is freely available on the Open Guided Waves platform. A classification rate of 96.2% is achieved, demonstrating reliable and automated damage detection. Moreover, the ability of the ML model to identify a damaged structure at untrained damage locations and temperatures is demonstrated.