PSI - Issue 64

Robby Weiser et al. / Procedia Structural Integrity 64 (2024) 492–499 Robby Weiser / Structural Integrity Procedia 00 (2019) 000 – 000

499

8

result, individual vehicle axes can no longer be identified. The sequential approach selecting a suitable network architecture leads to a consistence result. An improvement and optimal coverage of the parameter space of the network architecture could be achieved through a design of experiment. BiLSTMs are appropriate when the features sought within the data are known and the evaluation is based on these features. Without setting up feature vectors and programming algorithms to differentiate the measurement signal, the search variable can be specified by labelling it accordingly. Therefore, BiLSTMs can be applied to measurement data from any bridge. Due to the large number of parameters that have an influence on the crack opening amplitudes, separate training is necessary. Acknowledgements The research presented in this paper is being conducted within the project “ Digital twin as an intermediary between in-situ damage detection and global structural analysis ” . The project is part of the Priority Programme SPP 2388 “ Hundred plus - Extending the Lifetime of Complex Engineering Structures through Intelligent Digitalization ” , funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) – Project No. 501823987. References Begemann, F., Müller, J., Unglaub, J., Dilger, K., Thiele, K., Hensel, J., 2024. Welding under service conditions — Resulting weld quality and fatigue strength assessment. Engineering Failure Analysis 160, 108142. Bundesministerium für Verkehr, Bau und Stadtentwicklung, 2011. Richtlinie zur Nachrechnung von Straßenbrücken im Bestand (Nachrechnungsrichtlinie). Bundesministerium für Verkehr, Bau und Stadtentwicklung, 2012. Technische Lieferbedingungen für Streckenstationen, Berlin. Graves, A., Mohamed, A., Hinton, G., 2013. Speech recognition with deep recurrent neural networks, in: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing. ICASSP 2013 - 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, BC, Canada. 26.05.2013 - 31.05.2013. IEEE, pp. 6645 – 6649. Graves, A., Schmidhuber, J., 2005. Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural networks : the official journal of the International Neural Network Society 18, 602 – 610. Marzahn, G., Hamme, M., 2014. Fallstudie Rheinbrücke Leverkusen im Zuge der A1: Das Bauwerk und seine Schadensentwicklung. In: Krieger, J., Isecke, B. (Eds.) Beurteilung, Ertüchtigung und Instandsetzung von Brücken, vol. 1, Stuttgart, pp. 243 – 246. Mehdianpour, M., 2002. Lebensdauervorhersage von ermüdungsbeanspruchten Stahltragwerken mit Hilfe von Monitoring und begleitenden Versuchen. Dissertation, Braunschweig, 183 pp. Oberlin, T., Meignen, S., Perrier, V., 2014. The fourier-based synchrosqueezing transform, in: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014). Florence, Italy, 4 - 9 May 2014. ICASSP 2014 - 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Florence, Italy. 5/4/2014 - 5/9/2014. IEEE, Piscataway, NJ, pp. 315 – 319. Park, D.S., Chan, W., Zhang, Y., Chiu, C.-C., Zoph, B., Cubuk, E.D., Le V, Q., 2019. SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition, 2613 – 2617. Paschen, M., Hensen, W., Hamme, M., 2017a. Instandsetzungs‐ und S icherungsmaßnahmen bei den Rheinbrücken Leverkusen und DuisburgNeuenkamp – ein Zwischenbericht (Teil 1). Stahlbau 86, 603 – 618. Paschen, M., Hensen, W., Hamme, M., 2017b. Instandsetzungs‐ und Sicherungsmaßnahmen bei den Rheinbrücken Leverkusen und Duisburg‐ Neuenkamp – ein Zwischenbericht (Teil 2). Stahlbau 86, 1113 – 1119. Polizeipräsidium Duisburg, 2021. Verkehrsbericht 2021, Duisburg. Schuster, M., Paliwal, K.K., 1997. Bidirectional recurrent neural networks. IEEE Trans. Signal Process. 45, 2673 – 2681. Steffens, N., Geißler, K., 2021. Standortspezifisches Ziellastniveau und objektspezifische Lastmodelle für die Nachrechnung auf der Basis von Bauwerksmonitoring. Bautechnik 98, 720 – 735.