Wissenschaftliche Artikel der BAM
Filtern
Erscheinungsjahr
- 2021 (3) (entfernen)
Dokumenttyp
Sprache
- Englisch (3)
Referierte Publikation
- ja (3) (entfernen)
Schlagworte
- Artificial intelligence (1)
- Automated image analysis (1)
- Cracking (1)
- EN 717-3 (1)
- Electron microscopy (1)
- Emission test chamber (1)
- Flask method (1)
- Formaldehyde (1)
- Hydrogen (1)
- Image segmentation (1)
Organisationseinheit der BAM
Paper des Monats
- ja (3) (entfernen)
Offshore wind turbines (OWT) are a major goal of the energy strategy of Germany encompassing the increase of the installed wind power. OWT components are manufactured from welded steel plates with thicknesses up to 200 mm. The underlying standards and technical recommendations for construction of OWTs encompass specifications of so-called minimum waiting time (MWT) before non-destructive testing of the weld joints is allowed. Reason is the increased risk of time-delayed hydrogen assisted cold cracking as hydrogen diffusion is very slow due to the very thick plates. The strict consideration of those long MWT up to 48 h during the construction of OWTs leads to significant financial burden (like disproportionately high costs for installer ships as well as storage problems (onshore)). In this study, weld joints made of S355 ML were examined in comparison with the offshore steel grade S460 G2+M. The aim was to optimize, i.e., reduce, the MWT before NDT considering varied heat input, hydrogen concentration and using self-restraint weld tests. This would significantly reduce the manufacturing time and costs of OWT construction. To quantify the necessary delay time until hydrogen-assisted cold cracks appear, acoustic emission analysis was applied directly after welding for at least 48 h.
We present a workflow for obtaining fully trained artificial neural networks that can perform automatic particle segmentations of agglomerated, non-spherical nanoparticles from scanning electron microscopy images “from scratch”, without the need for large training data sets of manually annotated images. The whole process only requires about 15 minutes of hands-on time by a user and can typically be finished within less than 12 hours when training on a single graphics card (GPU). After training, SEM image analysis can be carried out by the artificial neural network within seconds. This is achieved by using unsupervised learning for most of the training dataset generation, making heavy use of generative adversarial networks and especially unpaired image-to-image translation via cycle-consistent adversarial networks. We compare the segmentation masks obtained with our suggested workflow qualitatively and quantitatively to state-of-the-art methods using various metrics. Finally, we used the segmentation masks for automatically extracting particle size distributions from the SEM images of TiO2 particles, which were in excellent agreement with particle size distributions obtained manually but could be obtained in a fraction of the time.
Formaldehyde is considered as carcinogenic and is emitted from particleboards and plywood used in toy manufacturing. Currently, the flask method is frequently used in Europe for market surveillance purposes to assess formaldehyde release from toys, but its concordance to Levels measured in emission test chambers is poor. Surveillance laboratories are unable to afford laborious and expensive emission chamber testing to comply with a new amendment of the European Toy Directive; they need an alternative method that can provide reliable results. Therefore, the application of miniaturised emission test chambers was tested. Comparisons between a 1 m3 emission test chamber and 44 mL microchambers with two particleboards over 28 days and between a 24 L desiccator chamber and the microchambers with three puzzle samples over 10 days resulted in a correlation coefficient r2 of 0.834 for formaldehyde at steady state. The correlation between the results obtained in microchambers vs. flask showed a high variability over 10 samples (r2: 0.145),
thereby demonstrating the error-proneness of the flask method in comparison to methods carried out under ambient parameters. An exposure assessment was also performed for three toy puzzles: indoor formaldehyde concentrations caused by puzzles were not negligible (up to 8 µg/m3), especially when more conservative exposure scenarios were considered.