TY - CONF A1 - Mueller, I. A1 - Freitag, S. A1 - Memmolo, V. A1 - Moix-Bonet, M. A1 - Möllenhoff, K. A1 - Golub, M. A1 - Sridaran Venkat, R. A1 - Lugovtsova, Yevgeniya A1 - Eremin, A. A1 - Moll, J. A1 - Tschöke, K. ED - Rizzo, P. ED - Milazzo, A. T1 - Performance Assessment for Artificial Intelligence-Based Data Analysis in Ultrasonic Guided Wave-Based Inspection: A Comparison to Classic Path-Based Probability of Detection N2 - Performance assessment for GuidedWave (GW)-based Structural Health Monitoring (SHM) systems is of major importance for industrial deployment. With conventional feature extraction methods like damage indices, pathbased probability of detection (POD) analysis can be realized. To achieve reliability quantification enough data needs to be available, which is rarely the case. Alternatives like methods for performance assessment on system level are still in development and in a discussion phase. In this contribution, POD results using an Artificial Intelligence (AI)-based data analysis are compared with those delivered by conventional data analysis. Using an open-access dataset from Open Guided Wave platform, the possibility of performance assessment for GW-based SHM systems using AI-based data analysis is shown in detail. An artificial neural network (ANN) classifier is trained to detect artificial damage in a stiffened CFRP plate. As input for the ANN, classical damage indicators are used. The ANN is tested to detect damage at another position, whose inspection data were not previously used in training. The findings show very high detection capabilities without sorting any specific path but only having a global view of current damage metrics. The systematic evaluation of the ANN predictions with respect to specific damage sizes allows to compute a probability of correct identification versus flaw dimension, somehow equivalent to and compared with the results achieved through classic path-based POD analysis. Also, sensitive paths are detected by ANN predictions allowing for evaluation of maximal distances between path and damage position. Finally, it is shown that the prediction performance of the ANN can be improved significantly by combining different damage indicators as inputs. T2 - 10th European Workshop on Structural Health Monitoring (EWSHM 2022) CY - Palermo, Italy DA - 04.07.2022 KW - Probability of Detection KW - Composites KW - Open Guided Waves Platform KW - Artificial Neural Network PY - 2022 SN - 978-3-031-07257-4 DO - https://doi.org/10.1007/978-3-031-07258-1 SN - 2366-2557 VL - 2 SP - 953 EP - 961 PB - Springer CY - Cham, Switzerland AN - OPUS4-55269 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Rietz, U. A1 - Lerche, D. A1 - Beck, Uwe A1 - Hielscher, Stefan A1 - Kern, Janine T1 - Determination of bonding, adhesive and composite strength by means of centrifuge technology N2 - The quality and durability of bonded joints, coated systems and composites depend on various factors. Therefore effective quantitative tests to determine adhesive, bonding or composite strength are of great need for R&D and QC. In this paper a new measuring principle is described which uses the centrifugal force to generate the test load. By the geometry of the whole measurement set-up, the test specimen are supported from only one side, the influence of shear forces is avoided. The possibility to test up to eight samples in one measurement under identical testing conditions allows a high sample throughput. A detailed description of the whole sample preparation procedure including pre-treatment is followed by the specification of the measuring protocol as well as result analysis. For each application area bonding strength of joints, adhesive strength of coated systems and internal strength of composite materials examples are presented. T2 - EURADH 2014 - 10th European Adhesion Conference CY - Alicante, Spain DA - 22.04.2014 KW - Adhesive strength KW - Bonding strength KW - Composites KW - Centrifuge technology KW - Zentrifugentechnologie KW - Klebfestigkeit KW - Haftfestigkeit KW - Mehr-Proben-Prüfen/Kleben PY - 2014 SN - 978-84-616-9067-1 SN - 84-616-9067-2 SP - Paper 47, 203 EP - 206 AN - OPUS4-31311 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Hamann, M. A1 - Kubowitz, P. A1 - Hofmann, Detlef ED - Xu, Y. L. ED - Zhu, S. ED - Xia, Y. ED - Ni, Y.Q. ED - Law, S.S. ED - Yin, J. H. ED - Su, Z.Q. T1 - Scale of intelligence in hybrid bridge structures - new aspects of monitoring by using fibre-optic sensors in timber elements N2 - In structural engineering timber is appreciated due to its low weight, its high aesthetic quality and because it is a renewable resource. The market share of timber structures and wood based hybrid structures will clearly increase over the next few years due to greater environmental awareness and a higher demand for sustainability. However, building with timber is marked by characteristics which lead to significant disadvantages in comparison wifh technical materials. For example, in outdoor areas Chemical and structural approaches offen lead to unsatisfactory and expensive Solutions with respect to durability. An idea is to make natural lumber a high-performance material which can be designed to meet the engineers’ demands conceming strength, stiffness, durability, shape, safety etc. These changes can affect the material itself, new technologies or a new approach to monitoring. Especially hybrids made of common timber products and technical textiles or enhanced timber products are high-capacitive and reach high bearing strengths with low material input and good durability. These hybrids are particularly qualified to use the advantages of wood and minimize the disadvantages. They can be used in different ways for load bearing structures, i.e. bridges. New construction types need monitoring to observe the stress and strains for which they were designed, and the structures’ behaviour as well as to guarantee required safety levels. The aim of successful usage of fibre optic measurement technology in timber elements was the development of a technology for measuring the lengthening in timber elements and wood based hybrid elements by using fibre optic sensors. The scientific and technical challenge was to develop an applicationtechnology for optical glass fibres in timber and densified veneer wood. In laboratory tests as well as with the erection of a footbridge and during in-situ tests it could be shown that the structurally integrated fibre optic sensor technology used is suitable for short and long term measurement. The developed embedment technology tums out to be practical and fit for good transfer of strain-values from timber to the modified sensor fibres. T2 - SHMII-6 - 6th International conference on structural health monitoring of intelligent infrastructure CY - Hong Kong, China DA - 09.12.2013 KW - Structural health monitoring KW - Structural engineering KW - Timber KW - Composites KW - Hybrid construction types KW - Fibre optic sensor technology KW - Sensor fibres PY - 2013 SN - 978-962-367-768-4 SP - 1 EP - 10 AN - OPUS4-29913 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -