Filtern
Dokumenttyp
Schlagworte
- Data Fusion (11) (entfernen)
Organisationseinheit der BAM
Eingeladener Vortrag
- nein (5)
To see and not to see - Möglichkeiten und Grenzen der Schadensanalyse mit CT an Kompositmaterialien
(2020)
Anhand von drei Beispielen (Datenfusion an CFK; Machine Learning an Metall-Matrix-Kompositen sowie Refraktion an CFK) wird gezeigt, wie die BAM mit neuen Analysemethoden mehr Informationen aus CT-Datensätzen extrahieren kann, sowie mit der Refraktion eine Analysemethode besitzt, die in Fällen eingesetzt werden kann, bei denen klassische Durchstrahlungsmethoden kein Ergebnis liefern.
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.
Flexible automation with compact NMR spectroscopy for continuous production of pharmaceuticals
(2019)
Modular plants using intensified continuous processes represent an appealing concept for the production of pharmaceuticals. It can improve quality, safety, sustainability, and profitability compared to batch processes; besides, it enables plug-and-produce reconfiguration for fast product changes. To facilitate this flexibility by real-time quality control, we developed a solution that can be adapted quickly to new processes and is based on a compact nuclear magnetic resonance (NMR) spectrometer. The NMR sensor is a benchtop device enhanced to the requirements of automated chemical production including robust evaluation of sensor data. Beyond monitoring the product quality, online NMR data was used in a new iterative optimization approach to maximize the plant profit and served as a reliable reference for the calibration of a near-infrared (NIR) spectrometer. The overall approach
was demonstrated on a commercial-scale pilot plant using a metal-organic reaction with pharmaceutical relevance.
Es konnte anhand einer numerischen Voruntersuchung gezeigt werden, dass anhand der kombinierten Auswertung der im Versuch verwendeten Sensorik eine Einteilung der unter Ermüdung in Bohrlochproben auftretenden Rissformen in verschiedene Hauptkategorien (Eckriss, Oberflächenriss, Durchgangsriss) möglich ist.
Es wird eine neu entwickelte Methode zur Thermographiebasierten Rissmessung vorgestellt. Darüber hinaus wird eine numerische Vorarbeit präsentiert, die zeigt, dass anhand der gemeisamen Auswertung der Versuchsdaten aus unterschiedlicher Sensorik die Möglichkeit besteht, die unter Ermüdungsbelastung in Bohrlochproben auftretenden Risse in Geometriekategorien zu unterteilen.
A numerical pre-study has shown that cracks in a flat sample featuring a drilled hole can be classified into one of three crack shape classes based on the combined evaluation of various types of test data.
Visualization of automated multi‐sensor NDT assessment of concrete structures (NDT Data Fusion)
(2017)
Nondestructive testing(NDT) of concrete buildings allows efficient repair measures. Multi-sensor platforms collect large data sets but the data analysis is typically performed manually. Data Fusion uses the full potential of a multi-sensory data set in order to:
- improve information quality (reliability, robustness, accuracy, clarity, completeness)
- enable automated algorithm based data analysis.
This poster summarizes results of the IGSTC-project entitled "NDT-Data Fusion" (short title) and demonstrates a significant improvement in the testing performance for the example of corrosion detection.
Non-Destructive assessment of the National Infrastructure in Germany has been the topic of R&D at BAM since many years. In 1989 BAM has established a R&D group dedicated to the development and application of Non-Destructive Testing in Civil Engineering. Since then, this group has left has participated in numerous research projects and cooperated with many researches and institutes worldwide.
A complex system of inspection and maintenance is in place to inspect and maintain roads, bridges, tunnels and other installations. Based on visual inspection structures like bridges are inspected regularly. In case of concerns which cannot be resolved in this process, a procedure “Object Oriented Damage Analysis” has been put into place where additional inspection methods, especially NDT methods, are being utilized.
NDT methods to establish material properties such as strength, porosity, moisture, carbonation, etc need more attention to strengthen the links between engineers and inspectors. BAM and TU Berlin have established a joint Junior Professor to address this research area with gravity.
Research is currently focused on methods, data, validation, certification and standardization. Industry 4.0 has become a widely discussed topic with unforeseeable impact. Current research topics include
- Large Aperture UltraSound (LAUS) to evaluate very thick concrete elements (> 1m)
- Embedded ultrasound sensors to monitor changes in concrete
- Data fusion algorithms for honeycomb detection, corrosion localization and reinforcement diameter determination
- Reverse Time Migration to improve imaging of concrete structures
- Laser Induced Breakdown Spectroscopy (LIBS) with new applications, improved sensitivity and resolution, new devices
- RFID based humidity and corrosion sensors
- Analysis of scattered Radar waves for the classification of concrete
- Development of reference specimens for selected NDT tasks
The presentation will present examples of current research and ideas for research directions.