Filtern
Erscheinungsjahr
- 2020 (8) (entfernen)
Dokumenttyp
- Vortrag (6)
- Zeitschriftenartikel (2)
Schlagworte
- NDT (3)
- Small Data (3)
- Machine Learning (2)
- Materials Informatics (2)
- Bild Klassifizierung (1)
- Cement (1)
- Classification (1)
- Concrete (1)
- Corrosion (1)
- Data Fusion (1)
Organisationseinheit der BAM
Eingeladener Vortrag
- nein (6)
The composition of concrete determines its resistance to various degradation mechanisms such as ingress of ions, carbonation or reinforcement corrosion. Knowledge of the composition of the hardened concrete is therefore helpful to assess the remaining service life of an existing structure or evaluate the damage observed during inspections. For example, for most existing concrete structures the type of cement originally used is not known and must therefore be determined afterwards. This paper presents a preliminary study on the application of laser-induced breakdown spectroscopy (LIBS) to identify the type of cement. For this purpose, ten different types of cement were investigated. For every type, three cement paste prisms were produced: (i) prisms dried, ground and pressed into tablets, (ii) prisms dried and (iii) prisms untreated. LIBS measurements were performed with a diode-pumped low energy laser (1064 nm, 3 mJ, 1.5 ns, 100 Hz) in combination with two compact spectrometers which cover the UV and NIR spectral range. A reduced subset of spectral features was used to build a classification model based on linear discriminant analysis. The results show that the classification of homogenized pressed cement powder samples provides a high accuracy, however, factors such as a different sample matrix and moisture content can affect the accuracy of the classification. The study demonstrates that LIBS is a promising tool to identify the type of cement.
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.
Data-driven research is considered the new paradigm in science. In this field, data is the new resource from which knowledge is extracted that is too complex for traditional methods. Several factors such as national funding and advances in information technology, are driving the development. In particular, the creation of databases and the analysis of data with artifical intelligence are playing an important role in establishing the new paradigm. However, there are numerous challenges that must be overcome to realize the full potential of data-driven methods. This talk sets the stage for the upcoming workshop by reviewing some of the historical developments and the current state of data-driven science in NDT and materials science.
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.
In the field of non-destructive testing (NDT) in civil engineering, a large number of measurement data are collected. Although they serve as a basis for scientific analyses, there is still no uniform representation of the data. An analysis of various distributed data sets across different test objects is therefore only possible with high manual effort.
We present a system architecture for an integrated data management of distributed data sets based on Semantic Web technologies. The approach is essentially based on a mathematical model - the so-called ontology - which represents the knowledge of our domain NDT. The ontology developed by us is linked to data sources and thus describes the semantic meaning of the data. Furthermore, the ontology acts as a central concept for database access. Non-domain data sources can be easily integrated by linking them to the NDT construction ontology and are directly available for generic use in the sense of digitization. Based on an extensive literature research, we outline the possibilities that this offers for NDT in civil engineering, such as computer-aided sorting, analysis, recognition and explanation of relationships (explainable AI) for several million measurement data.
The expected benefits of this approach of knowledge representation and data access for the NDT community are an expansion of knowledge through data exchange in research (interoperability), the scientific exploitation of large existing data sources with data-based methods (such as image recognition, measurement uncertainty calculations, factor analysis, material characterization) and finally a simplified exchange of NDT data with engineering models and thus with the construction industry.
Ontologies are already the core of numerous intelligent systems such as building information modeling or research databases. This contribution gives an overview of the range of tools we are currently creating to communicate with them.
Im Bereich der Zerstörungsfreien Prüfung (ZfP) im Bauwesen werden eine Vielzahl von Messdaten erfasst. Obwohl Sie als Grundlage für wissenschaftliche Analysen dienen, gibt es noch keine einheitliche Repräsentation der Daten. Eine Analyse verschiedener verteilter Datensätze über unterschiedliche Prüfobjekte hinweg ist daher kaum möglich.
Wir stellen einen Ansatz für ein integriertes Datenmanagement verteilter Datensätze auf Basis von Semantic-Web Technologien vor. Der Ansatz basiert im Kern auf einem mathematischen Modell – der sogenannten Ontologie – welches das Wissen unserer Domäne ZfPBau repräsentiert. Die von uns entwickelte ZfPBau Ontologie wird mit Datenquellen verknüpft und beschreibt so die semantische Bedeutung der Daten. Darüber hinaus fungiert die Ontologie als zentrales Konzept für den Datenbankzugriff. Domänen-fremde Datenquellen können durch die Verknüpfung mit der ZfPBau Ontologie einfach integriert werden und stehen zur generischen Nutzung im Sinne der Digitalisierung direkt zur Verfügung. Basierend auf einer umfangreichen Literaturrecherche, skizzieren wir die Möglichkeiten die sich daraus für die ZfP im Bauwesen ergeben, wie zum Beispiel Messdaten computergestützt zu sortieren, zu analysieren, Zusammenhänge zu erkennen und zu erklären.
Der erwartete Nutzen dieses Ansatzes der Wissensrepräsentation und des Datenzugriffs für die ZfP-Community ist eine Erweiterung des Wissens durch Datenaustausch in der Forschung (Interoperabilität), die wissenschaftliche Verwertung großer existierender Datenquellen mit datenbasierten Verfahren (wie Bilderkennung, Messunsicherheitsberechnungen, Faktoranaylsen, Materialcharackterisierung) und letztlich ein vereinfachter Transfer von ZFP-Daten in Ingenieurmodelle und somit in die Baupraxis.
Ontologien sind bereits Kern vielzähliger intelligenter Systeme wie Building-Information-Modeling oder Forschungsdatenbanken. Der Beitrag gibt einen Überblick über die Werkzeuge die wir derzeit für die Kommunikation mit ihnen schaffen.
Machine learning based multi-sensor fusion for the nondestructive testing of corrosion in concrete
(2020)
Half-cell potential mapping (HP) is the most popular non-destructive testing method (NDT) for locating corrosion damage in concrete. It is generally accepted that HP is susceptible to environmental factors caused by salt-related deterioration, such as different moisture and chloride gradients. Additional NDT methods are able to identify distinctive areas but are not yet used to estimate more accurate test results. We present a Supervised Machine Learning (SML) based approach to data fusion of seven different signal features to obtain higher quality information. SMLs are methods that explore (or learn) relationships between different (sensor) data from predefined data labels. To obtain a representative, labelled data set we conducted a comprehensive experiment simulating the deterioration cycle of a chloride exposed device in the laboratory. Our data set consists of 18 measurement campaigns, each containing HP, Ground Penetrating- Radar, Microwave Moisture and Wenner resistivity data. We compare the performance of different ML approaches. Many outperform the best single method, HP. We describe the intrinsic challenges posed by a data-driven approach in NDT and show how future work can help overcome them.