A Generative Modeling Approach for the Translation of Operational Variables to Short-term Vibrations 121 Conclusions In this contribution, a generative modeling approach is proposed for the translation of vibration signal statistics to short terms dynamics. The methodology is demonstrated on a simulated wind turbine system, where a Gaussian Process Latent Force (GPLF) model is used to map one-minute SCADA data to the GPLF parameters. With fatigue damage accumulation being a critical phenomenon in wind turbine systems, the generated pseudo time series have a satisfactory predictive capability for the quantification of loading cycles at different amplitudes. The relative simplicity of the surrogate model allows still to have a very decent accuracy compared to a high complexity dynamic model, requiring a lot of computational power and parameters. Moreover, another advantage of the proposed methodology is the connection between the scarce SCADA variables and the short-term dynamics. The major advantage of such a methodology is the generative approach that can be used to estimate the fatigue accumulation in critical parts of the structure based on a relatively general and simple implementation, avoiding the pitfall of data availability encountered by many purely data-driven models. References 1. Agathos, K., Tatsis, K., Nicoli, S., Bordas, S.P., and Chatzi, E. “Crack detection in mindlin-reissner plates under dynamic loads based on fusion of data and models”. Computers & Structures, 246:106475 (2021) 2. Gres, S., Do¨hler, M., Andersen, P., and Mevel, L. “Subspace-based mahalanobis damage detection robust to changes in excitation covariance”. Structural Control and Health Monitoring, 28(8):e2760 (2021) 3. Tatsis, K.E., Ou, Y., Dertimanis, V.K., Spiridonakos, M.D., and Chatzi, E.N. “Vibration-based monitoring of a small-scale wind turbine blade under varying climate and operational conditions. part ii: A numerical benchmark”. Structural Control and Health Monitoring, 28(10):e2813 (2021) 4. Tatsis, K., Lourens, E., and Chatzi, E. “A general substructure-based framework for input-state estimation using limited output measurements”. Mechanical Systems and Signal Processing, 150:107223 (2021) 5. Tatsis, K.E., Agathos, K., and Chatzi, E.N. “A hierarchical output-only bayesian approach for online vibration-based crack detection using parametric reduced-order models”. Mechanical Systems and Signal Processing, 167:108558 (2022) 6. Zhao, Y., Zhang, Y., Li, Z., Bu, L., and Han, S. “Ai-enabled and multimodal data driven smart health monitoring of wind power systems: A case study”. Advanced Engineering Informatics, 56:102018 (2023) 7. Gopalakrishnan, S., Laflamme, S., and Hu, C. “Deep cnn-based learning for automated structural damage detection and localization”. Smart Materials and Structures, 26(5):055027 (2017) 8. Malekjafarian, A. and O’Brien, E.J. “Structural damage detection using long short-term memory networks”. Journal of Civil Structural Health Monitoring, 11:765–779 (2021) 9. Choe, D.E., Kim, H.C., and Kim, M.H. “Sequence-based modeling of deep learning with lstm and gru networks for structural damage detection of floating offshore wind turbine blades”. Renewable Energy, 174:218–235 (2021) 10. Azimi, M., Eslamlou, A.D., and Pekcan, G. “Data-driven structural health monitoring and damage detection through deep learning: State-ofthe-art review”. Sensors, 20 (2020) 11. Sarkka, S., Solin, A., and Hartikainen, J. “Spatiotemporal learning via infinite-dimensional bayesian filtering and smoothing: A look at gaussian process regression through kalman filtering”. IEEE Signal Processing Magazine, 30(4):51 – 61 (2013) 12. A´ lvarez, M., Luengo, D., and Lawrence, N.D. “Latent force models”. Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics, pages 9–16 (2009) 13. J.M. Jonkman, M.B.J. FAST User’s Guide. National Renewable Energy Laboratory (2005) 14. Mozafari, V.P.R.J., S. and Dykes, K. “Sensitivity of fatigue reliability in wind turbines: effects of design turbulence and the wo¨hler exponent”. Wind Energ. Sci., pages 799–820 (2024) 15. Iliopoulos, A., Weijtjens, W., Van Hemelrijck, D., and Devriendt, C. “Fatigue assessment of offshore wind turbines on monopile foundations using multi-band modal expansion: Fatigue assessment of monopile owts using multi-band modal expansion”. Wind Energy, 20 (2017)
RkJQdWJsaXNoZXIy MTMzNzEzMQ==