Filtern
Erscheinungsjahr
- 2020 (3)
Dokumenttyp
- Vortrag (3) (entfernen)
Referierte Publikation
- nein (3) (entfernen)
Schlagworte
- Small Data (3) (entfernen)
Organisationseinheit der BAM
Eingeladener Vortrag
- nein (3)
Explore and Exploit - Strategische Erweiterung der fraktographischen Datenbank mit Machine Learning
(2020)
In diesem Vortrag stellen wir den aktuellen Stand zu einer Masterarbeit zusammen die sich mit dem Thema beschäftigt wie die Generalisierbarkeit von Datenmodellen auf Basis kleiner Datensätze erhöht werden kann. Wir stellen vor, wie die Datenbasis eines fraktogafischen Bildklassifizierers mit einem statistischen Model strategische erweitert, bzw. an eine Anwendung angepasst werden kann.
We have arrived in the data age. But why is it so difficult for the NDT community to achieve real breakthroughs with data-driven science? In this seminar, we will take a brief look at the evolution of mainstream data science to understand why the most exciting times are perhaps just ahead. We will give an overview of our activities in the junior research group 8.K which are aimed at enabling the next generation of data science methods in NDT. The seminar addresses the two main work fields of our group: semantic data management and the handling of limited data resources.
The first field addresses the problem that a uniform representation of our data is not yet available. However, knowledge creation in data science - whose main contribution lies in the analysis of distributed resources - requires common data access based on a collective understanding. To achieve this, we present an ontology-based approach. Ontologies are already the core of many intelligent systems such as building information models or research databases. We summarize some of the basic principles of this technology and describe our approach to create an NDT ontology.
The second field ties in with the first and addresses the application of data-based methods in engineering practice. Especially in the field of non-destructive testing many successful applications have been published. In most cases, however, the creation of referenced data is extremely expensive and therefore much sparser than in other research areas. As a result, the available data may cover only one scenario, so that common benchmarks often do not reflect the actual performance of the model in practical applications. Estimates that quantify the transferability from one scenario to another are not only necessary to overcome this challenge - they also prove to be a powerful tool for the strategic expansion of what we consider knowledge.
Many PhD students are interested in applying machine learning, AI, data science, etc., and there are many good reasons for this. However, there is a disconnect between mainstream data science and materials science, for example, when it comes to the sheer size of the data. This talk will highlight some of the unique challenges in materials informatics and present some interesting approaches to overcome them. Although the field is large, this talk will focus on cases that have some practical relevance to PhD students at BAM.