Filtern
Dokumenttyp
- Vortrag (8) (entfernen)
Sprache
- Englisch (8)
Referierte Publikation
- nein (8) (entfernen)
Schlagworte
- Data fusion (8) (entfernen)
Organisationseinheit der BAM
Eingeladener Vortrag
- nein (8)
We present the results of a machine learning (ML)- inspired data fusion approach, applied to multi-sensory nondestructive testing (NDT) data. Our dataset consists of Impact-Echo (IE), Ultrasonic Pulse Echo (US) and Ground Penetrating Radar (GPR) measurements collected on large-scale concrete specimens with built–in simulated honeycombing defects. In a previous study we were able to improve the detectability of honeycombs by fusing the information from the three different sensors with the density based clustering algorithm DBSCAN. We demonstrated the advantage of data fusion in reducing the false positives up to 10% compared to the best single sensor, thus, improving the detectability of the defects. The main objective of this contribution is to investigate the generality, i.e. whether the conclusions from one specimen can be adapted to the other. The effectiveness of the proposed approach on a separate full-scale concrete specimen was evaluated.
This talk demonstrates the results of the IGSTC-project entitled "NDT-Data Fusion".
Project approach:
Nondestructive testing (NDT) of concrete buildings allows to coordinate efficient repair measures. Multi-sensor platforms collect large data sets. Nevertheless, 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) and enables automated algorithm based data analysis.
We present the project achievements, namely:
- Development of building scanner system for multisensory NDT
- Laboratory multi sensor investigations
- Development of data fusion concept for honeycombing and pitting corrosion
- Field testing
Half-cell potential mapping (HP) is the most popular nondestructive test (NDT)-method for the localization of corrosion damage in concrete. It is generally recognized, that HP is prone to the environmental factors that arise from salt induced deterioration, such as varying moisture and chloride gradients. Additional NDT-methods are capable to determine distinctive areas, but cannot yet be used to estimate more accurate testing results. We introduce a supervised machine learning (SML) based approach for data fusion to make use of the additional sensor information. SML are methods that explore relations between different (sensor) data from predefined data labels. We use a simple linear classifier named logistic regression to distinguish defect and intact areas. The test performance improves drastically compared to the best single method, HP. In order to generate representative, labeled data we conducted a comprehensive experiment that simulates the deterioration-cycle of a chloride-exposed building part in the lab. Our data set consist of 18 measurement campaigns, each containing HP-, ground-penetrating-radar-, microwave-moisture-, and Wenner-resistivity-data. We detail the challenges that arise with a data driven approach in NDT and how we addressed them.
The use of duplex stainless steels (DSS) in energy related applications is well known. Nowadays, DSS steels become more favorable than austenitic steels due to the outstanding mechanical properties, the good corrosion resistance and the lower nickel content. However, the use of the duplex grade in acidic environments such as seawater often leads to severe degradation of the structural integrity of the steel by hydrogen-induced/assisted cracking (HAC) phenomena, which can eventually result in premature failure. Hydrogen assisted degradation and cracking of steels are active fields of research even though this topic is intensively studied for more than a century. A bottleneck is the analytical validation of the theoretical models proposed ion the literature at the sub-micron scale.
Industrial and the research communities see a need for an accurate analytical method by which it is possible to image the distribution of hydrogen in the microstructure of a steels or and other alloys. Among the very few available methods hydrogen imaging methods, Time-of-Flight secondary ion mass spectrometry (ToF-SIMS) has the principal capability for mapping of hydrogen in a steel’s microstructure. The combination of ToF-SIMS with multivariate data analysis (MVA), electron microscopy (SEM) and electron-backscattered diffraction (EBSD) is a powerful approach for providing chemical and structural information. The use of data fusion techniques has been shown recently to enhance the better understanding of the hydrogen induced degradation processes in in a DSS steel.
Laser powder bed fusion (L-PBF) is one of the most promising additive manufacturing (AM) technologies for the production of complex metallic real part components. Due to the multitude of factors influencing process conditions and part quality and due to the layer-wise characteristic of the process, monitoring of process signatures seems to be mandatory in case of the production of safety critical components. Here, the iterative process nature enables unique access for in-situ monitoring during part manufacture. In this talk, the successful test of the synchronous use of a high-frequency infrared camera and a camera for long time exposure, working in the visible spectrum (VIS) and equipped with a near infrared filter (NIR), will be introduced as a machine manufacturer independent thermal detection monitoring set-up. Thereby, the synchronous use of an infrared camera and a VIS NIR camera combines the advantages of high framerate and high spatial resolution. The manufacture of a 316L stainless steel specimen, containing purposely seeded defects and volumes with forced changes of energy inputs, was monitored during the build. The measured thermal responses are analysed and compared with a defect mapping obtained by micro X-ray computed tomography (CT).
The first results regarding methods for data analysis, derived correlations between measured signals and detected defects as well as sources of possible data misinterpretation are presented in this talk.
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.
LIBS ConSort: Development of a sensor-based sorting method for constuction and demolition waste
(2023)
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.