Filtern
Erscheinungsjahr
- 2016 (2)
Dokumenttyp
- Vortrag (2) (entfernen)
Sprache
- Englisch (2)
Referierte Publikation
- nein (2) (entfernen)
Schlagworte
- Clustering (2) (entfernen)
Eingeladener Vortrag
- nein (2)
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.
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.