Open Access

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.

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.

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.

Environmentally friendly alternatives to cement are created through the synthesis of numerous base materials. The variation of their proportions alone leads to millions of materials candidates. Identifying suitable materials is very laborious; traditional systematic research in the laboratory consumes a lot of time and effort. Sequential learning (SL) potentially speeds up the materials research process despite limited but highly complex available information. SL does not make direct predictions of material properties but ranks possible experiments according to their utility. The most promising experiments are prioritized over dead-end experiments and experiments whose outcome is already known. Our work has shown that SL seems to be promising for cement research. So far, research has mainly focused on materials whose synthesis is faster and whose material properties require less time for development or characterization (allowing many successive experiments). Contrarily, in the case of binders, SL is only useful if few experiments lead to the desired goal, as for example, the determination of the compressive strength alone typically requires 28 days. In research practice, experimental designs and the availability of resources often determine which data can be used - for example, when some laboratory resources are not available or deemed irrelevant to a task. As a result, new research scenarios are constantly emerging, each of which requires to demonstrate SL’s performance. We are presenting the SLAMD app to facilitate the exploration of SL methods in numerous research scenarios. The app provides flexible and low-threshold access to AI methods via intuitive and interactive user interfaces. We deliberately pursue a software-based research approach (as opposed to code-, or script-based). On the one hand, the results are more comprehensible since we refer to a common (code) basis (’reproducible science’). On the other hand, the methods are easily accessible to all which accelerates the knowledge transfer into laboratory practice.

Alkali-activated binders (AAB) can provide a clean alternative to conventional cement in terms of CO2 emissions. However, as yet there are no sufficiently accurate material models to effectively predict the AAB properties, thus making optimal mix design highly costly and reducing the attractiveness of such binders. This work adopts sequential learning (SL) in high-dimensional material spaces (consisting of composition and processing data) to find AABs that exhibit desired properties. The SL approach combines machine learning models and feedback from real experiments. For this purpose, 131 data points were collected from different publications. The data sources are described in detail, and the differences between the binders are discussed. The sought-after target property is the compressive strength of the binders after 28 days. The success is benchmarked in terms of the number of experiments required to find materials with the desired strength. The influence of some constraints was systematically analyzed, e.g., the possibility to parallelize the experiments, the influence of the chosen algorithm and the size of the training data set. The results show the advantage of SL, i.e., the amount of data required can potentially be reduced by at least one order of magnitude compared to traditional machine learning models, while at the same time exploiting highly complex information. This brings applications in laboratory practice within reach.