TY - CONF A1 - Klewe, Tim T1 - LIBS-ConSort: Sensor-based sorting of construction and demolition waste N2 - In construction and demolition waste (CDW) recycling, the preference to date has been to apply simple but proven techniques to sort and process large quantities of construction rubble in a short time. This contrasts with the increasingly complex composite materials and structures in the mineral building materials industry. An automated, sensor-based sorting of these building materials could complement or replace the practice of manual sorting to improve processing speed, recycling rates, sorting quality, and prevailing health conditions for the executing staff. A joint project of partners from industry and research institutions approaches this task by investigating and testing the combination of laser-induced breakdown spectroscopy (LIBS) with near-infrared (NIR) spectroscopy and visual imaging. Joint processing of information (data fusion) is expected to significantly improve the sorting quality of CDW, and may enable the detection and separation of impurities such as SO3-cotaining building materials (gypsum, aerated concrete, etc.) We present current advances and results about the methodological development combining LIBS with NIR spectroscopy and visual imaging. Here, applying data fusion proves itself beneficial to improve recognition rates. In the future, a laboratory prototype will serve as a fully automated measurement setup to allow real-time classification of CDW on a conveyor belt. T2 - V. International Conference Progress of Recycling in the Built Environment (RILEM VPRE) CY - Weimar, Germany DA - 10.10.2023 KW - NDT KW - Circular economy KW - LIBS KW - Material classification KW - Data fusion PY - 2023 AN - OPUS4-58756 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Klewe, Tim T1 - LIBS ConSort: Development of a sensor-based sorting method for constuction and demolition waste N2 - Closed material cycles and unmixed material fractions are required to achieve high recovery and recycling rates in the building industry. In construction and demolition waste (CDW) recycling, the preference to date has been to apply simple but proven techniques to process large quantities of construction rubble in a short time. This is in contrast to the increasingly complex composite materials and structures in the mineral building materials industry. Manual sorting involves many risks and dangers for the executing staff and is merely based on obvious, visually detectable differences for separation. An automated, sensor-based sorting of these building materials could complement or replace this practice to improve processing speed, recycling rates, sorting quality, and prevailing health conditions. A joint project of partners from industry and research institutions approaches this task by investigating and testing the combination of laser-induced breakdown spectroscopy (LIBS) with near-infrared (NIR) spectroscopy and visual imaging. Joint processing of information (data fusion) is expected to significantly improve the sorting quality of various materials like concrete, main masonry building materials, organic components, etc., and may enable the detection and separation of impurities such as SO3-cotaining building materials (gypsum, aerated concrete, etc.) Focusing on Berlin as an example, the entire value chain will be analyzed to minimize economic / technological barriers and obstacles at the cluster level and to sustainably increase recovery and recycling rates. We present current advances and results about the test stand development combining LIBS with NIR spectroscopy and visual imaging. In the future, this laboratory prototype will serve as a fully automated measurement setup to allow real-time classification of CDW on a conveyor belt. T2 - 21. International Conference on Building Materials (Ibausil) CY - Weimar, Germany DA - 13.09.2023 KW - Material classification KW - Data fusion KW - Circular economy KW - LIBS KW - Recycling PY - 2023 AN - OPUS4-58495 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Klewe, Tim A1 - Strangfeld, Christoph A1 - Kruschwitz, Sabine T1 - Review of moisture measurements in civil engineering with ground penetrating radar – Applied methods and signal features N2 - When applying Ground Penetrating Radar (GPR) to assess the moisture content of building materials, different medium properties, dimensions, interfaces and other unknown influences may require specific strategies to achieve useful results. Hence, we present an overview of the various approaches to carry out moisture measurements with GPR in civil engineering (CE). We especially focus on the applied Signal features such as time, amplitude and frequency features and discuss their limitations. Since the majority of publications rely on one single feature when applying moisture measurements, we also hope to encourage the consideration of approaches that combine different signal features for further developments. KW - Ground Penetrating Radar KW - Moisture KW - Civil engineering KW - Signal features PY - 2021 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-520684 DO - https://doi.org/10.1016/j.conbuildmat.2021.122250 VL - 278 SP - 122250 PB - Elsevier Ltd. AN - OPUS4-52068 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Klewe, Tim T1 - Feuchtemessung an Fußböden mit Radar und Neutronensonde – Ein Vergleich von Labor und Praxis N2 - Nach Auftreten eines Feuchteschadens in Fußbodenaufbauten sind sowohl die zeitnahe Feststellung als auch Eingrenzung betroffener Bereiche von besonderer Bedeutung. So können erforderliche Renovierungsmaßnahmen effizient geplant und mögliche Folgeschäden vermieden werden. Zur messtechnischen Beantwortung dieser Fragestellungen werden bereits seit vielen Jahren Neutronensonden eingesetzt, welche allerdings keine Tiefenzuordnung des schadensträchtigen Flüssigwassers zulassen. Hierzu müssen mit hohem zeitlichem und finanziellem Aufwand zerstörende Sondierungsbohrungen vorgenommen werden, welche zukünftig durch den parallelen Einsatz des Radarverfahrens vermieden werden könnten. In systematischen Laborstudien wurden gängige Feuchteschäden an häufig anzutreffenden Fußbodenaufbauten simuliert und deren Einfluss auf das Messsignal untersucht. Hierbei kamen Zementund Anhydritestriche, sowie die Dämmmaterialen Styropor, Styrodur, Glaswolle und Perlite-Schüttung mit variierenden Schichtdicken zum Einsatz, um die vielfältigen Konfigurationen der Praxis abzubilden. Für den gewonnenen Datensatz konnten geeignete Signalmerkmale extrahiert werden, welche mithilfe multivariater Datenauswertung eine Klassifizierung des vorliegenden Schadenfalls zulassen. Zum Ende des Forschungsvorhabens steht besonders die Anwendbarkeit der entwickelten Methoden für die Praxis im Fokus. Hierzu wurden Messungen an realen Schadensfällen durchgeführt und deren Ergebnisse mit den Laboruntersuchungen verglichen. Hierbei stellten sich variierende Schichtdicken, sowie vorkommende Fußbodenheizungen und Armierungsgitter als mögliche Fehlerquellen für eine vollständig automatisierte Auswertung heraus. T2 - 81. Jahrestagung der Deutschen Geophysikalischen Gesellschaft (DGG) CY - Online meeting DA - 01.03.2021 KW - Radar KW - Feuchte KW - Fußboden KW - Neutronensonde PY - 2021 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-522227 DO - https://doi.org/10.23689/fidgeo-3955 AN - OPUS4-52222 LA - deu AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Strangfeld, Christoph A1 - Klewe, Tim T1 - Comparison of the Calcium Carbide Method and Darr Drying to Quantify the Amount of Chemically Bound Water in Early Age Concrete N2 - Hydration is the exothermic reaction between anhydrous cement and water, which forms the solid cement matrix of concrete. Being able to evaluate the hydration is of high interest for the use of both conventional and more climate-friendly building materials. The experimental monitoring is based on temperature or moisture measurements. The first needs adiabatic conditions, which can only be achieved in laboratory. The latter is often measured comparing the weight of the material sample before and after oven drying, which is time-consuming. This study investigates the moisture content of two cement-based and two calcium sulphate based mixtures for the first 90 days by using the calcium carbide method and oven drying at 40 °C and 105 °C (Darr method). Thereby, the amount of chemically bound water is determined to derive the degree of hydration. The calcium carbide measurements highly coincide with oven drying at 40 °C. The calcium carbide method is therefore evaluated as a suitable alternative to the time-consuming Darr drying. The prompt results are seen as a remarkable advantage and can be obtained easily in laboratory as well as in the field. KW - Concrete KW - Hydration KW - Material moisture KW - Calcium carbide method KW - Bound water KW - Darr method KW - Oven drying KW - Chemisorption KW - Physisorption PY - 2022 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-564519 DO - https://doi.org/10.3390/ma15238422 VL - 15 IS - 23 SP - 1 EP - 16 PB - MDPI AN - OPUS4-56451 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Klewe, Tim T1 - Signalmerkmale des Radarverfahrens zur Klassifizierung von Feuchteschäden in Fußbodenaufbauten N2 - Zur Eingrenzung und Klassifizierung auftretender Feuchteschäden in geschichteten Fußbodenaufbauten wird bereits seit vielen Jahren das Neutronensondenverfahren eingesetzt. Während eine Eingrenzung des Schadens bereits durch die zerstörungsfrei aufgenommenen Messdaten möglich ist, erfordert die Klassifizierung zeit- und kostenintensive Sondierungsbohrungen. Die somit gewonnenen Tiefeninformationen zur Lage des Flüssigwassers tragen maßgeblich zur Planung der erforderlichen Reparaturarbeiten bei, was die Frage nach einer zerstörungsfreien Alternative zur vertikalen Lokalisierung von Feuchte in Fußböden stellt. Das Radarverfahren ist mit seiner hohen Sensitivität für Wasser besonders geeignet und soll künftig zur automatisierten Klassifizierung typischer Schadensfälle beitragen. In einem laufenden Forschungsvorhaben werden in systematischen Laborstudien gängige Schadensfälle an häufig anzutreffenden Fußbodenaufbauten simuliert und deren Einfluss auf die genannten Verfahren untersucht. Hierbei kommen Zement- und Anhydritestriche, sowie unterschiedliche Dämmmaterialen mit variierenden Schichtdicken zum Einsatz. Wesentlicher Bestandteil der Auswertung ist die Extraktion signifikanter Signalmerkmale des Radarverfahrens, welche Rückschlüsse auf den Schadensfall und ggf. die Wassermenge zulassen. Die Robustheit gegenüber unterschiedlichsten Aufbauten mit wechselnden Schichtdicken und Materialien steht hierbei besonders im Fokus. Erste Ergebnisse empfehlen die Betrachtung der örtlichen Verteilung bestimmter Signalmerkmale im Radargramm (B-Scan), um eine Klassifizierung der Schadensfälle vornehmen zu können. T2 - Fachtagung Bauwerksdiagnose 2020 CY - Berlin, Germany DA - 13.02.2020 KW - Radar KW - Feuchte KW - Signalmerkmale KW - Klassifikation PY - 2020 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-504143 AN - OPUS4-50414 LA - deu AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - THES A1 - Klewe, Tim T1 - Non-destructive classification of moisture deterioration in layered building floors using ground penetrating radar N2 - In the event of moisture deterioration, rapid detection and localization is particularly important to prevent further deterioration and costs. For building floors, the layered structure poses a challenging obstacle for most moisture measurement methods. But especially here, layer-specific information on the depth of the water is crucial for efficient and effective repairs. Ground Penetrating Radar (GPR) shows the potential to generate such depth information. Therefore, the present work investigates the suitability of GPR in combination with machine learning methods for the automated classification of the typical deterioration cases (i) dry, (ii) wet insulation, and (iii) wet screed. First, a literature review was conducted to identify the most common methods for detecting moisture in building materials using GPR. Here, it especially became clear that all publications only investigated individual time-, amplitude- or frequency features separately, without combining them. This was seen as a potential aspect for innovation, as the multivariate application of several signal features can help to overcome individual weaknesses and limitations. Preliminary investigations carried out on drying screed samples confirmed the profitable use of multivariate evaluations. In addition to the general suitability and dependencies of various features, first limitations due to possible interference between the direct wave and the reflection wave could be identified. This is particularly evident with thin or dry materials, for which the two-way travel times of the reflected radar signals become shorter. An extensive laboratory experiment was carried out, for which a modular test specimen was designed to enable the variation of the material type and thickness of screed and insulation, as well as the simulation of moisture deteriorations. The data collected revealed clear differences between dry and deteriored structures within measured B-scans. These deviations were to be detected with the newly introduced B-scan features, which evaluate the statistical deviation of A-scan features within a survey line. In this way, deteriorations to unknown floor structures are recognized, regardless of the material parameters present. In a subsequent training and cross-validation process of different classifiers, accuracies of over 88 \% of the 504 recorded measurements (252 different experimental setups) were achieved. For that, the combination of amplitude and frequency features, which covered all relevant reflections of the radar signals, was particularly beneficial. Furthermore, the data set showed only small differences between dry floors and deteriored screeds for the B-scan features, which could be attributed to a homogeneous distribution of the added water in the screeds. The successfully separation of these similar feature distributions raised the suspicion of overfitting, which was examined in more detail by means of a validation with on-site data. For this purpose, investigations were carried out at five different locations in Germany, using the identical measurement method like in the laboratory. By extracting drilling cores, it was possible to determine the deterioration case for each measurement point and thus generate a corresponding reference. However, numerous data had to be sorted out before classification, since disturbances due to underfloor heating, screed reinforcements, steel beams or missing insulation prevented comparability with the laboratory experiments. Validation of the remaining data (72 B-scans) achieved only low accuracy with 53 \% correctly classified deterioration cases. Here, the previously suspected overfitting of the small decision boundary between dry setups and deteriored screeds within the laboratory proved to be a problem. The generally larger deviations within (also dry) on-site B-scans were thus frequently misclassified as screed deterioration. In addition, there were sometimes strongly varying layer thicknesses or changing cases of deterioration within a survey line, which caused additional errors due to the local limitation of the drilling core reference. Nevertheless, individual on-site examples also showed the promising potential of the applied signal features and the GPR method in general, which partly allowed a profound interpretation of the measurements. However, this interpretation still requires the experience of trained personnel and could not be automated using machine learning with the available database. Nevertheless, such experience and knowledge can be enriched by the findings of this work, which provide the basis for further research. Future work should aim at building an open GPR data base of on-site moisture measurements on floors to provide a meaningful basis for applying machine learning. Here, referencing is a crucial point, whose limitations with respect to the moisture present and its distribution can easily reduce the potential of such efforts. The combination of several reference methods might help to overcome such limitations. Similarly, a focus on monitoring approaches can also help to reduce numerous unknown variables in moisture measurements and increase confidence in the detection of different deterioration cases. KW - NDT KW - Moisture measurement KW - Ground penetrating radar KW - Building floor PY - 2023 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-591044 DO - https://doi.org/10.14279/depositonce-19306 SP - 1 EP - 146 PB - Technische Universität Berlin CY - Berlin AN - OPUS4-59104 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Klewe, Tim A1 - Strangfeld, Christoph A1 - Ritzer, Tobias A1 - Kruschwitz, Sabine T1 - Classification of Practical Floor Moisture Damage Using GPR - Limits and Opportunities N2 - Machine learning in non-destructive testing (NDT) offers significant potential for efficient daily data analysis and uncovering previously unknown relationships in persistent problems. However, its successful application heavily depends on the availability of a diverse and well-labeled training dataset, which is often lacking, raising questions about the transferability of trained algorithms to new datasets. To examine this issue closely, the authors applied classifiers trained with laboratory Ground Penetrating Radar (GPR) data to categorize on-site moisture damage in layered building floors. The investigations were conducted at five different locations in Germany. For reference, cores were taken at each measurement point and labeled as (i) dry, (ii) with insulation damage, or (iii) with screed damage. Compared to the accuracies of 84 % to 90 % within the laboratory training data (504 B-Scans), the classifiers achieved a lower overall accuracy of 53 % for on-site data (72 B-Scans). This discrepancy is mainly attributable to a significantly higher dynamic of all signal features extracted from on-site measurements compared to laboratory training data. Nevertheless, this study highlights the promising sensitivity of GPR for identifying individual damage cases. In particular the results showing insulation damage, which cannot be detected by any other non-destructive method, revealed characteristic patterns. The accurate interpretation of such results still depends on trained personnel, whereby fully automated approaches would require a larger and diverse on-site data set. Until then, the findings of this work contribute to a more reliable analysis of moisture damage in building floors using GPR and offer practical insights into applying machine learning to non-destructive testing for civil engineering (NDT-CE). KW - GPR KW - Material moisture KW - Building floor KW - Machine Learning PY - 2024 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-607932 DO - https://doi.org/10.1007/s10921-024-01111-7 SN - 0195-9298 VL - 43 IS - 3 SP - 1 EP - 16 PB - Springer Science and Business Media LLC AN - OPUS4-60793 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Munsch, Sarah Mandy A1 - Klewe, Tim A1 - Schumacher, K. A1 - Telong, Melissa A1 - Grobla, Lili A1 - Völker, C. A1 - Yared, K. A1 - Kruschwitz, Sabine ED - Rogge, Andreas ED - Meng, Birgit T1 - Anwendung von KI für die Materialoptimierung im Bauwesen N2 - Diese Arbeit untersucht den Einsatz von Künstlicher Intelligenz (KI) in der Materialentwicklung für Beton, mit einem Fokus auf Karbonatisierungswiderstand, CO₂-Reduktion und Kostenoptimierung. Das KI-Tool SLAMD, das auf inverses Materialdesign setzt, konnte in Studien die Entwicklungszeit für Betonmischungen um bis zu 80 % verkürzen. Durch die Integration zusätzlicher 1H-Kernspinresonanz-Daten wurde der Prozess um weitere 40 % beschleunigt. Insgesamt zeigt sich, dass der Einsatz von KI die Effizienz und Nachhaltigkeit in der Materialentwicklung signifikant steigern kann. T2 - 11. Jahrestagung des DAfStb mit 63. Forschungskolloquium der BAM Green Intelligent Building CY - Berlin, Germany DA - 16.10.2024 KW - Künstliche Intelligenz (KI) KW - Materialoptimierung KW - Bauwesen PY - 2024 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-612949 SN - 978-3-9818564-7-7 SP - 192 EP - 200 PB - Bundesanstalt für Materialforschung und -prüfung (BAM) CY - Berlin AN - OPUS4-61294 LA - deu AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Klewe, Tim T1 - Zerstörungsfreie Lokalisierung von Flüssigwasser in Schichtaufbauten - Projektvorstellung N2 - Da derzeit keine zerstörungsfreie Alternative zur Lokalisierung von Leitungswasserschäden in Fußböden existiert, werden in der Regel unter hohem zeitlichen und finanziellen Aufwand Sondierungsbohrungen vorgenommen, um das entnommene Material im Labor thermo-gravimetrisch zu untersuchen. Dabei nehmen Leitungswasserschäden mit rd. 2,6 Milliarden Euro jährlich den deutlich größten Posten bei Gebäudeversicherungen ein. Für derartige Fragestellungen werden seit einigen Jahren Neutronensonden eingesetzt. Mit diesem Verfahren ist es möglich, sich einen Überblick über die Gesamtwassermenge in einem definierten Baustoffvolumen zu verschaffen, jedoch kann flüssiges und chemisch gebundenes Wasser nicht unterschieden werden. Daher werden die Messdaten mit den Ergebnissen der Sondierungsbohrungen kalibriert. So können auch große Flächen wie Industriefußböden in relativ kurzer Zeit größtenteils zerstörungsfrei untersucht werden. Da die integrale Messweise der Neutronensonde allerdings keine Tiefenzuordnung eines gefundenen Feuchteschadens zulässt, muss auch diese Information über die Bohrkerne generiert werden. Die Idee des Projekts ist, durch den parallelen Einsatz des Radarverfahrens in Zukunft auf Sondierungsbohrungen verzichten zu können. Nach der Abgrenzung trockener von feuchten Bereichen über die Neutronensonde, wird das Radarverfahren herangezogen, um typische Schadensfälle zerstörungsfrei zu unterscheiden. In systematischen Laborstudien an modular aufgebauten Referenzprobekörpern untersuchen wir die Nachweisgrenzen und Detektionswahrscheinlichkeiten der beiden Verfahren für verschiedene, häufig anzutreffende Fußbodenaufbauten. Anschließend sollen über Datenfusion und Signalverarbeitung innovative Auswertungsansätze entwickelt werden, welche die Messergebnisse von Neutronensonde und Radar automatisiert zur Gewinnung eines höheren Informationsgehalts und zur Klassifizierung der Schadensfälle kombinieren. Im Rahmen des Projekts wird die erarbeitete Vorgehensweise an real geschädigten Objekten getestet, um die Methode zu etablieren sowie Akzeptanz bei Anwendern und Eigentümern zu schaffen. Könnten durch genauere Schadenseingrenzung die Sanierungskosten um nur 4% gesenkt werden, ergäbe sich in Deutschland eine Kostenreduzierung von ca. 100 Million Euro jährlich. T2 - Bauwerksdiagnose 2018 CY - Berlin, BAM, Germany DA - 15.02.2018 KW - Feuchte KW - ZfP KW - Radar KW - Neutronensonde KW - Fußboden PY - 2018 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-446458 AN - OPUS4-44645 LA - deu AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -