PSI - Issue 64

Eshwar Kumar Ramasetti et al. / Procedia Structural Integrity 64 (2024) 557–564 Author name / Structural Integrity Procedia 00 (2019) 000 – 000

564

8

5. Summary and Conclusions The primary objective of this study was to develop generic AI models to predict the movement of vehicles on bridges. The Nibelungen Bridge in the city of Worms, Germany was chosen as a demonstrator for extending the life span of bridges by using SHM, digital twin and AI methods. In this work, a SHM system was installed on the bridge with seven digital MEMS sensors at various locations and acceleration data was collected along with features. The installation location of sensors was chosen on the idea of investigating errors from the sensor readings along the girder under the bridge. A deep learning model based on CNN architecture was chosen to classify different types of vehicle movement on the bridge. In the first step, a CNN model was developed to classify whether a vehicle is passed or not based on the acceleration data. Furthermore, the model classified if the passed vehicle was car, truck, or large truck. The results showed an accuracy of 98 % in both binary (vehicle passed or not) and multi-label (cars, or trucks, or large trucks) classification, and the model was not overfitting. The developed model can study how many large or heavy trucks passed on the bridge and predict structure behavior with the aim to improve its life span. In the next step, the ambition will be to transfer this model to other sensor datasets of the bridge and see if the model can predict similar results. This developed deep transfer learning model targets to reduce the training data for producing accurate results and transfer to datasets from similar bridges in the future. Acknowledgements The research project is financially supported by German Research Foundation (DFG) in the focus area SPP Hundred Plus (SPP2388) under project no. 501829185. References Arnold, M. and Keller. S., 2024. Machine Learning and Signal Processing for Bridge Traffic Classification with Rader Displacement Time-Series Data. Infrastuctures, 9. Cross, E. J., Koo, K.Y., Brownjohn. W. and Worden. K., 2013. Long-term monitoring and data analysis of the Tamar Bridge. Mechanical Systems and Signal Processing, 35, 16-34. Fenerci, A., Kvåle, A., Petersen, O.W., Ronnquist, A. and Oiseth, O., 2021. Data Set from Long-Term Wind and Acceleration Monitoring of the Hardanger Bridge. Journal of Structural Engineering 147. Herbers, M., Wenner. M. and Marx. S., 2023. A 576 m long creep and shrinkage specimen - Long-term deformation of a semi-integral concrete with a mssive solid cross-section. Strucutral Concrete, 24, 3558-72. Herrmann, R., Ramasetti, E.K., Degener, S., Hille, F., Baeßler, M., 2024. A Living Lab for Structural Health Monitoring at the Nibelungen Bridge Worms for Transfer Learning of Structural Dynamics. 11 th European Workshop on Structural Health Monitoring, Potsdam, Germany. Kang, C., Voigt, C., Eisermann, C., Kerkeni, N., Hegger, J., Hermann, W., & Marx, S., (2024). The Nibelungen bridge as a pilot project for digitally assisted structural maintenance [In German]. Bautechnik, 101, 76-86. Khodabandehlou, H., Pekcan, G. and Fadali, M. S., 2019. Vibration-based structural condition assessment using convolution neural networks. Structural Control and Health Monitoring, 26. Lawal, O., Shajihan, A. V., Mechitov, K. and Spencer, Jr. B.F., 2019. An Event-Classficiation Neural Network Approach for Rapid RailRoad Bridge Impact Detection. Sensors, 23. Onur, A., Osama, A., Serkan, K., Mohammed, H., Moncef, G., Daniel, J.I., 2021. A review of vibration-based damage detection in civil structures: From traditional methods to Machine Learning and Deep Learning applications. Journal of Mechanical Systems and Signal Processing 147, 107077. Patrick, S., Helmrich, M., Herrmann, R., Schneider, R., Baeßler, M., Lorelli, S., Morgenthal, G., 2022. Maintal-Bridge Gemünden: Structural monitoring and identification from a single source [In German]. Bautechnik, 99, 163-172. Sitton, J. D., Zeinalo, Y. and Story, B. A., 2019. Design and field implementation of an impact detection system using committess of neutal networks. Expert System with Applications, 120, 185-196. Sonbul, O. S. and Rashid. M., 2023. Algorithms and Techniques for the Structural Health Monitoring of Bridges: Systematic Literature Review. Sensors 23, 4230. Yu, Y., Wang, C.Y., Gu, Y. and Li, J.C., 2019. A novel deep learning-based method for damage indentification of smart building structures. Structural Health Monitoring-an International Journal, 18, 143-63.