TY - GEN A1 - Wiggenhauser, Herbert A1 - Kind, Thomas A1 - Mielentz, Frank A1 - Strangfeld, Christoph A1 - Völker, Christoph A1 - Wilsch, Gerd T1 - Non-destructive testing in civil engineering at BAM N2 - Research and Development in Non-Destructive Testing in Civil Engineering at BAM has de-veloped over more than two decades. Highlights of present research are ultrasound phase array probes, ground penetrating radar applications for the assessment of existing structures and Laser Induced Breakdown Spec-troscopy (LIBS) to determine which chemical elements on the surface of a specimen are. RFID sensor devel-opments for wireless moisture monitoring and data fusion for the combined analysis of sensor data are fast developing areas. In addition, a selection of application cases is briefly described. T2 - Vortrag über die Aktivitäten des Fachbereichs 8.2 in der zerstörungsfreien Prüfung im Bauwesen. KW - Ultrasonic testing KW - RFID-sensors KW - Data fusion KW - Ground penetrating radar KW - LIBS PY - 2017 SP - 1 EP - 10 CY - Berlin AN - OPUS4-44132 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Haller, T. A1 - Völker, Christoph A1 - Hartmann, T. T1 - Machine learning based multi-sensor fusion for the nondestructive testing of corrosion in concrete N2 - 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. T2 - SMAR2019 - 5th International Conference on Smart Monitoring, Assessment and Rehabilitation of Civil Structures CY - Potsdam, Germany DA - 27.08.2019 KW - Machine Learning KW - NDT KW - Half-Cell Potential Mapping KW - Corrosion KW - Reinforced Concrete KW - Data Fusion PY - 2020 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-498563 UR - http://www.ndt.net/?id=24890 VL - 25 IS - 1 SP - 24890-1 EP - 24890-8 PB - NDT.net CY - Kirchwald AN - OPUS4-49856 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Völker, Christoph T1 - Understanding distributed data – a semantic web approach for data based analysis of NDT data in civil engineering N2 - 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. T2 - EGU General Assembly 2020 CY - Online meeting DA - 04.05.2020 KW - Ontology KW - NDT KW - Concrete KW - Onotology KW - Semantic Data Management KW - Reproducible Science PY - 2020 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-518076 DO - https://doi.org/10.5194/egusphere-egu2020-19332 AN - OPUS4-51807 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Völker, Christoph T1 - Daten verständlich machen mit einem Semantic Web basierten Ansatz für die ZfP im Bauwesen N2 - 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. T2 - Seminar ZfP 4.0 Die ZfP im Zeichen der Digitalisierung CY - Frankfurt am Main, Germany DA - 08.10.2020 KW - Ontologien KW - Semantisches Datenmanagement KW - Reproduzierbare Wissenschaft PY - 2020 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-518092 AN - OPUS4-51809 LA - deu AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Völker, Christoph T1 - Explore and Exploit - Strategische Erweiterung der fraktographischen Datenbank mit Machine Learning N2 - 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. T2 - AG Fraktographie im DVM/DGM Gemeinschaftsausschuss „Rasterelektronenmikroskopie in der Materialprüfung“ CY - Online meeting DA - 20.11.2020 KW - Bild Klassifizierung KW - Small Data KW - Unsicherheitsberechnung KW - Erklärbare KI PY - 2020 AN - OPUS4-51810 LA - deu AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Völker, Christoph T1 - Prospects and challenges of data-driven NDT - current work in junior research group 8.K N2 - 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. T2 - Abteilungsseminar der Abteilung 8 CY - Online meeting DA - 18.11.2020 KW - Machine Learning KW - Small Data KW - Semantic Web KW - Materials Discovery KW - Explainable AI PY - 2020 AN - OPUS4-51811 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Völker, Christoph T1 - Artificial intelligence in NDT (AI NDT) a networking workshop N2 - 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. T2 - Workshop on Artificial Intelligence in NDT (AI-NDT) CY - Online meeting DA - 30.10.2020 KW - Data Science KW - Materials Informatics KW - NDT PY - 2020 AN - OPUS4-51812 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Völker, Christoph T1 - Trends in Materials Informatics N2 - 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. T2 - PhD Day at BAM 2020 CY - Online meeting DA - 15.09.2020 KW - Materials Informatics KW - Small Data PY - 2020 AN - OPUS4-51814 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Völker, Christoph T1 - Quantifizierung der Unsicherheit für einen dünnbesetzten maschinellen Lerndatensatz (ML) in der zerstörungsfreien Prüfung im Bauwesen (ZfPBau) N2 - Das maschinelle Lernen (ML) wurde erfolgreich zur Lösung vieler Aufgaben in der zerstörungsfreien Prüfung im Bauwesen (ZfPBau) eingesetzt. Allerdings ist die Erstellung von Referenzdaten in den meisten Fällen extrem teuer und daher viel knapper als in anderen Forschungsbereichen. Auch decken die verfügbaren Daten mitunter nur ein einziges Szenario ab, so dass die Leistungsindikatoren oft nicht die tatsächliche Leistung des ML-Modells in der praktischen Anwendung widerspiegeln. Schätzungen, die die Übertragbarkeit von einem Szenario auf ein anderes quantifizieren, sind erforderlich, um dieser Herausforderung gerecht zu werden und den Weg für Anwendungen in der Praxis zu ebnen. In diesem Beitrag stellen wir Werkzeuge zur Beschreibung der Unsicherheit von ML in neuen ZfPBau-Szenarien vor. Zu diesem Zweck haben wir einen bestehenden Trainingsdatensatz zur Klassifizierung von Korrosionsschäden der Bewehrung in Beton um eine neue Fallstudie erweitert. Die Messungen wurden an großflächigen Betonproben mit eingebauter chloridinduzierter Korrosion des Bewehrungsstahls durchgeführt. Das Experiment simulierte den gesamten Lebenszyklus von chloridinduzierten Sichtbetonbauteilen im Labor. Unser Datensatz umfasst Potenzialfeld- und Radarmessungen. Die einzigartige Fähigkeit, die Schädigung zu überwachen und eine gezielte Korrosion einzuleiten, ermöglichte es, die Daten zu labeln - was für die Konstruktion von ML-Modellen entscheidend ist. Um die Übertragbarkeit zu untersuchen, erweitern wir unser Modell um Metadaten - wie etwa Konstruktionsmerkmale des Prüfkörpers und Umweltbedingungen. Dies erlaubt es, die Veränderung dieser Merkmale in neuen Szenarien mit statistischen Methoden als Unsicherheiten auszudrücken. Wir vergleichen verschiedene auf Stichproben und statistischer Verteilung basierende Ansätze und zeigen, wie diese Methoden eingesetzt werden können, um Wissenslücken von ML-Modellen in der ZfP zu schließen T2 - DGZfP Jahrestagung 2021 CY - Online meeting DA - 10.05.2021 KW - Machine Learning KW - Zerstörungsfreie Prüfung KW - Datenfusion KW - Multi Sensor KW - Unsicherheitsquantifizierung PY - 2021 AN - OPUS4-54124 LA - deu AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Völker, Christoph T1 - Uncertainty quantification for a sparse machine learning (ML) data set in non-destructive testing in civil engineering (NDT-CE) N2 - ML has been successfully applied to solve many NDT-CE tasks. This is usually demonstrated with performance metrics that evaluate the model as a whole based on a given set of data. However, since in most cases the creation of reference data is extremely expensive, the data used is generally much sparser than in other areas, such as e-commerce. As a result, performance indicators often do not reflect the practical applicability of the ML model. Estimates that quantify transferability from one case to another are necessary to meet this challenge and pave the way for real world applications. In this contribution we invetigate the uncertainty of ML in new NDT-CE scenarios. For this purpose, we have extended an existing training data set for the classification of corrosion damage by a new case study. Our data set includes half-cell potential mapping and ground-penetrating radar measurements. The measurements were performed on large-area concrete samples with built-in chloride-induced corrosion of reinforcement. The experiment simulated the entire life cycle of chloride induced exposed concrete components in the laboratory. The unique ability to monitor deterioration and initiate targeted corrosion initiation allowed the data to be labelled - which is crucial to ML. To investigate transferability, we extend our data by including new design features of the test specimen and environmental conditions. This allows to express the change of these features in new scenarios as uncertainties using statistical methods. We compare different sampling and statistical distribution-based approaches and show how these methods can be used to close knowledge gaps of ML models in NDT. T2 - EGU General Assembly 2021 CY - Online meeting DA - 19.04.2021 KW - Data fusion KW - Non-destructive testing PY - 2021 DO - https://doi.org/10.5194/egusphere-egu21-8798 AN - OPUS4-54125 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Völker, Christoph T1 - Presenting “SLAMD” - The Sequential Learning App for Materials Discovery N2 - 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. T2 - DGM Materials Week 2021 CY - Online meeting DA - 07.09.2021 KW - Sequential learning KW - Scientific software KW - Alcali activated binders PY - 2021 AN - OPUS4-54128 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -