Filtern
Dokumenttyp
- Vortrag (3) (entfernen)
Sprache
- Englisch (3)
Referierte Publikation
- nein (3) (entfernen)
Schlagworte
- Deep learning (3) (entfernen)
Organisationseinheit der BAM
Eingeladener Vortrag
- nein (3)
The 3D microstructure of an Al alloy matrix composite with two ceramic reinforcements was investigated by synchrotron X-ray tomography. A deep learning algorithm was used for the segmentation of four different phases. We show that convolutional networks with the U-Net architecture are able to solve complex segmentation tasks with small amount of training data.
The following work deals with the quantitative fracture surface evaluation in damage analysis. So far, fracture surfaces have almost exclusively been evaluated qualitatively, i.e. the presence of fracture features is documented and their surface proportions are estimated, if necessary. Many years of experience are required, as well as an intensive comparison with defined comparative images from the literature. The aim of this work is the development of classifiers which can recognize fracture mechanisms or fracture features in scanning electron microscope images (SEM). The basis is 46 SEM images, which have been evaluated by fractography experts with regard to fracture features. The existing data set of images is expanded using augmentation methods in order to increase the variability of the data and counteract overfitting. Only convolutional neural networks (CNN) are used to create the classifiers. Various network configurations are tested, with the SegNet achieving the best results.
Gas distribution mapping (GDM) is a valuable tool for monitoring the distribution of gases in various applications, including environmental monitoring, emergency response, and industrial safety. While GDM is actively researched in the scope of gas-sensitive mobile robots (Mobile Robot Olfaction), there is a potential for broader applications utilizing sensor networks. This presentation gives an overview of the different approaches to GDM and motivate the use of a deep-neural network-based approach. As access to ground truth representations of gas distributions remains a challenge in GDM research, an approach for the simulation of realistic-shaped synthetic gas plumes is described, which was used for training Gas Distribution Decoder, a deep neural network for spatial interpolation of spatially sparse gas measurements.