Filtern
Dokumenttyp
- Zeitschriftenartikel (3)
- Vortrag (2)
- Beitrag zu einem Tagungsband (1)
Sprache
- Englisch (6)
Schlagworte
- Clustering (6) (entfernen)
Organisationseinheit der BAM
Eingeladener Vortrag
- nein (2)
In civil engineering the information about the quantitative ingress of harmful species like Cl⁻, Na⁺ and SO²⁻₄ is of great interest to evaluate the remaining life time of structures. These species are triggering different damage processes like the alkali-silica reaction (ASR) or the chloride-induced corrosion of the reinforcement. For the evaluation of the heterogeneous concrete it is necessary to discriminate between the different phases mainly cement matrix and aggregates. The transport processes are only proceeding in the cement matrix therefore the measured concentrations should be regarded to the cement content. For the 2D evaluation of element distributions different multivariate cluster-algorithms like k-means and Expectation-Maximization-algorithm (EM-algorithm) have been tested. The methods are compared and different figures of merit will be presented. After phase separation non-relevant information of the aggregates can be excluded. The ingress of harmful species is then quantified using chemometrics. Due to concrete cores from a parking deck the methods have been validated and verified with standard methods of wet-chemistry.
We present the results of several machine learning (ML)- inspired data fusion algorithms applied to multi-sensory nondestructive testing (NDT) data. Our dataset consists of Impact-Echo (IE), Ultrasonic Pulse Echo (US) and Ground Penetrating Radar (GPR) data collected on large-scale concrete specimens with built–in simulated honeycombing defects. The main objective is to improve the detectability of honeycombs by fusing the information from the three different sensors. We describe normalization, feature detection and optimal feature selection. We have used unsupervised and supervised ML, i.e., classification and clustering, for data fusion. We demonstrate 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 methods were evaluated on a concrete specimen. The effectiveness of the proposed approach was demonstrated on a separate full-scale concrete specimen. The results indicate the transportability of the conclusions from one specimen to the other.
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.
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 paper demonstrates that the instrumented indentation test (IIT), together with a trained artificial neural network (ANN), has the capability to characterize the mechanical properties of the local parts of a welded steel structure such as a weld nugget or heat affected zone.
Aside from force-indentation depth curves generated from the IIT, the profile of the indented surface deformed after the indentation test also has a strong correlation with the materials’ plastic behavior. The profile of the indented surface was used as the training dataset to design an ANN to determine the material parameters of the welded zones. The deformation of the indented surface in three dimensions shown in images were analyzed with the computer vision algorithms and the obtained data were employed to train the ANN for the characterization of the mechanical properties. Moreover, this method was applied to the images taken with a simple light microscope from the surface of a specimen. Therefore, it is possible to quantify the mechanical properties of the automotive steels with the four independent methods: (1) force-indentation depth curve; (2) profile of the indented surface; (3) analyzing of the 3D-measurement image; and (4) evaluation of the images taken by a simple light microscope. The results show that there is a very good Agreement between the material parameters obtained from the trained ANN and the experimental uniaxial tensile test. The results present that the mechanical properties of an unknown steel can be determined by only analyzing the images taken from its surface after pushing a simple indenter into its surface.