TY - CONF A1 - Völker, Christoph A1 - Kruschwitz, Sabine A1 - Boller, C. A1 - Wiggenhauser, Herbert T1 - Feasibility study on adapting a machine learning based multi-sensor data fusion approach for honeycomb detection in concrete N2 - 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. T2 - NDE/NDT for Highway and Bridges: Structural Materials Technology 2016 CY - Portland, Oregon, USA DA - 29.08.2016 KW - Data fusion KW - Concrete evaluation KW - Honeycombing KW - Machine learning KW - Clustering PY - 2016 SN - 978-1-57117-392-8 SP - 144 EP - 148 PB - The American Society for Nondestructive Testing, Inc CY - Portland, Oregon, USA AN - OPUS4-38288 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Völker, Christoph A1 - Kruschwitz, Sabine A1 - Boller, C. A1 - Wiggenhauser, Herbert T1 - Feasibility study on adapting a machine learning based multi-sensor data fusion approach for honeycomb detection in concrete N2 - 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. T2 - NDE/NDT for Highway and Bridges: Structural Materials Technology 2016 CY - Portland, Oregon, USA DA - 29.08.2016 KW - Data fusion KW - Concrete evaluation KW - Honeycombing KW - Machine learning KW - Clustering PY - 2016 AN - OPUS4-38289 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Völker, Christoph A1 - Shokouhi, P. T1 - Clustering based multi sensor data fusion for honeycomb detection in concrete KW - Data fusion KW - Concrete evaluation KW - Honeycombing KW - Machine learning KW - Clustering KW - Density based clustering PY - 2015 U6 - https://doi.org/10.1007/s10921-015-0307-7 SN - 0195-9298 SN - 1573-4862 VL - 34 IS - Article 32 SP - 1 EP - 10 PB - Plenum Press CY - New York, NY AN - OPUS4-35073 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Völker, Christoph A1 - Shokouhi, P. T1 - Data aggregation for improved honeycomb detection in concrete using machine learning-based algorithms N2 - 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. T2 - NDT-CE 2015 - International symposium non-destructive testing in civil engineering CY - Berlin, Germany DA - 15.09.2015 KW - Data fusion KW - Concrete evaluation KW - Honeycombing KW - Machine learning KW - Clustering PY - 2015 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:kobv:b43-350968 UR - https://www.ndt.net/?id=18364 SN - 1435-4934 VL - 20 IS - 11 SP - 1 EP - 8 PB - NDT.net CY - Kirchwald AN - OPUS4-35096 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -