Wissenschaftliche Artikel der BAM
Filtern
Dokumenttyp
Sprache
- Englisch (2)
Schlagworte
- Composite structures (2) (entfernen)
Organisationseinheit der BAM
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.
Fibre-reinforced plastics (FRP) especially carbon-fibre-reinforced polymer (CFRP) and glass-fibre-reinforced polymer (GFRP) are commonly used materials in high pressure vessels and storage units for automotive and aerospace purposes. Optical fibres are suitable to be integrated or directly applied to the surface of FRP components. Using optical fibres it is possible to monitor the distributed strain profiles and changes within the fatigue life of a pressure vessel to ensure the operational safety. Within artificial ageing experiments we used swept wavelength interferometry (SWI) based distributed strain sensing for the monitoring of commercial high-pressure composite cylinder. This artificial ageing was performed using test conditions of 503bar pressure load (service pressure 300 bar) and 89 °C for 100 h. The polyimide coated optical fibres were glued to the surface externally in circumferential and axial direction. Using distributed strain sensing (DSS) material expansion of over 0.5% were monitored with sub-centimetre spatial resolution. Within the circumferential direction we observed up to 10 % local fluctuation compared to the median strain caused by inhomogeneous material expansion, which could cause local material fatigue. In addition, we determined material degradation manifested itself as localized remaining material expansion and/or contraction. Results have been validated by other non-destructive methods like digital strip projection.