Präsentation
Filtern
Dokumenttyp
- Vortrag (5)
Sprache
- Englisch (5)
Referierte Publikation
- nein (5)
Schlagworte
- AI (5) (entfernen)
Organisationseinheit der BAM
Eingeladener Vortrag
- nein (5)
Enhanced crack detection method using Convolutional Neural Networks for Varestraint type tests
(2023)
Varstraint type tests are globally established in the measurement of hot cracking susceptibility of welds. Evaluation of such tests is done under a light microscope and can be heavily influenced by human subjectivity. To reduce the human error source in evaluation, a concept based on Convolutional Neural Networks (CNNs) is proposed. An AI was constructed and trained on self-produced data to detect and segment cracks in microscope images. The advantages, besides a faster evaluation, include higher precision and the availability of data that was not available before.
Irrespective of the experimental care used to acquire Computed Tomography Data, certain artifacts might still exist such as: Noise, Blurring, Ring Artifacts etc. To tackle this problem, a complete multi-level framework employing AI (Deep Artificial Neural Nets), targeting specific artifacts individually, is presented. The goal is to render the data suitable for subsequent unproblematic segmentation without any loss of information, compared to manual conditioning with traditional filters.
The strategy can therefore be used to acquire faster CT data (e.g. in-situ investigations) and ensure legacy with existing data obtained, perhaps, on older instruments.
A large amount of data and information is collected in the field of non-destructive testing (NDT) in civil engineering. The weakly structured data are usually evaluated with regard to specific testing tasks (e.g. geometry determination, damage localization, quality assurance). While the data offers great economic potential, i.e. to support construction planning, monitoring and maintenance processes, the evaluation is manual and case-by-case and therefore too inefficient for broader applications. We present recent visions and approaches how these large amounts of data need to be handled in the future and how we aim to make the acquired knowledge accessible to our stakeholders. Building on initiatives in materials research, we stress the importance of further research in the field of semantic data integration particularly motivate why an ontology is needed for the area of NDT in civil engineering.
Artificial intelligence (AI), machine learning, and neural networks have revolutionized fields such as self-driving cars or machine translation. Indeed, AI has progressed so far that scientists such as Stephen Hawking now fear that it may destroy humankind altogether. So, let’s get started and use AI in surface science.
Here we train neural networks to use raw measurement data as input and immediately return the desired output parameters. We discuss the example of X-ray reflectivity measurements of ultrathin films, which contain reciprocal space information and must traditionally be fitted with dynamic scattering theory. Instead, we train the neural network with simulated X-ray data of multilayer structures and then apply it to measurement data. The neural network yields high accuracy results, is robust against noise, and performs significantly faster than fitting algorithms in real-time experiments. The presented neural network data analysis is becoming increasingly attractive, because free software has become very accessible and specialized computer chips (NPU) are currently being rolled out.