Abstract
Modeling of dynamical systems is essential in many areas of engineering, such as product development and condition monitoring. Currently, the two main approaches in modeling of dynamical systems are the physical and the data-driven one. Both approaches are sufficient for a wide range of applications but suffer from various disadvantages, e.g., a reduced accuracy due to the limitations of the physical model or due to missing data. In this work, a methodology for modeling dynamical systems is introduced, which expands the area of application by combining the advantages of both approaches while weakening the respective disadvantages. The objective is to obtain increased accuracy with reduced complexity. Two models are used, a physical model predicts the system behavior in a simplified manner, while the data-driven model accounts for the discrepancy between reality and the simplified model. This hybrid approach is validated experimentally on a double pendulum.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Sextro, W.: Dynamic Contact Problems with Friction, 2nd edn. Springer, Heidelberg (2007)
Klus, S., Nüske, F., Peitz, S., Nieman, J.-H., Clementi, C., Schütte, C.: Data-driven approximation of the Koopman generator: model reduction, system identification, and control. Physica D 406, 132416 (2020)
Vlachas, P.R., Byeon, W., Wan, Z.Y., Sapsis, T.P., Koumoutakos, P.: Data-driven forecasting of high-dimensional chaotic systems with long short-term memory network. Proc. R. Soc. A Math. Phys. Eng. Sci. 474, 20170844 (2018)
Lukoševičius, M., Jaeger, H.: Reservoir computing approaches to recurrent neural network training. Comput. Sci. Rev. 3(3), 127–149 (2009)
Kaiser, E., et al.: Cluster-based reduced-order modelling of a mixing layer. J. Fluid Mech. 754, 365–414 (2014)
von Stosch, M., Oliveira, R., Peres, J., Feyo de Azevedo, S.: Hybrid semi-parametric modeling in process systems engineering: past, present and future. Comput. Chem. Eng. 60, 86–101 (2014)
von Stosch, M., Glassey, J.: Benefits and challenges of hybrid modeling in the process industries: an introduction. In: Hybrid Modeling in Process Industries, pp. 1–12. CRC Press, Boca Raton (2018)
Isermann, R., Münchof, M.: Identification of Dynamic Systems: An Introduction with Applications, 1st edn. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-540-78879-9
Bieker, K., Peitz, S., Brunton, S.L., Kutz, J.N., Dellnitz, M.: Deep model predictive flow control with limited sensor data and online learning. Theoret. Comput. Fluid Dyn. 34(4), 577–591 (2020). https://doi.org/10.1007/s00162-020-00520-4
Halfmann, C., Holzmann, H.: Adaptive Modelle für die Kraftfahrzeugdynamik, 1st edn. Springer, Heidelberg (2003). https://doi.org/10.1007/978-3-642-18215-0
Kramer, M.A., Thompson, M.L., Bhagat, P.M.: Embedding theoretical models in neural networks. In: American Control Conference, pp. 475–479 (1992)
Sohlberg, B., Jacobsen, E.W.: Grey box modelling - branches and experiences. In: Proceeding of the 17th IFAC World Congress, pp. 11415–11420 (2008)
Matei, I., de Kleer, H., Feldman, A., Rai, R., Chowdhury, S.: Hybrid modeling: applications in real-time diagnosis. arXiv:2003.02671 (2020)
von Stosch, M., Portela, R.M.C., Oliveira, R.: Hybrid model structures for knowledge integration. In: Hybrid Modeling in Process Industries, pp. 13–35. CRC Press, Boca Raton (2018)
Thompson, M.L., Kramer, M.A.: Modeling chemical processes using prior knowledge and neural networks. AIChE J. 40(8), 1328–1340 (1994)
Deuflhard, P., Hohmann, A.: Numerische Mathematik 1, 4th edn. De Gruyter, Berlin (2008)
Daubechies, I.: Ten Lectures on Wavelets, 3rd edn. Society for Industrial and Applied Mathematics, Philadelphia (1994)
Alpaydin, E.: Maschinelles Lernen, 2nd edn. De Gruyter Oldenbourg, Berlin, Boston (2019)
Agarwal, M.: Combining neural and conventional paradigms for modelling, prediction and control. Int. J. Syst. Sci. 28(1), 65–81 (1997)
Kaheman, K., Kaiser, E., Strom, B., Kutz, N., Brunton, S. L.: Learning discrepancy models from experimental data. arXiv:1909.08574 (2019)
Brunton, S.L., Proctor, J.L., Kutz, J.N.: Discovering governing equations from data by sparse identification of nonlinear dynamical systems. Proc. Natl. Acad. Sci. 113(15), 3932–3937 (2016)
Champion, K., Lusch, B., Kutz, N., Brunton, S.L.: Data-driven discovery of coordinates and governing equations. Proc. Natl. Acad. Sci. 116(45), 22445–22451 (2019)
Forster, O.: Analysis 1: Differential- und Integralrechnung einer Veränderlichen, 12th edn. Springer Spektrum, Wiesbaden (2016)
Dankert, H., Dankert, J.: Technische Mechanik: computerunterstützt, 2nd edn. B. G. Teubner, Stuttgart (1995)
Shinbrot, T., Grebogi, C., Wisdom, J., Yorke, J.: Chaos in a double pendulum. Am. J. Phys. Am. Assoc. Phys. Teachers 60, 491–499 (1992)
Magnus, K., Popp, K., Sextro, W.: Schwingungen, 10th edn. Springer Vieweg, Wiesbaden (2016). https://doi.org/10.1007/978-3-658-13821-9
Breiman, K., Friedman, J.H., Olshen, R.A., Stone, C.J.: Classification and Regression Trees, 1st edn. CRC Press, Boca Raton (1984)
Breiman, L.: Bagging predictors. Mach. Learn. 24, 123–140 (1996)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Wohlleben, M., Bender, A., Peitz, S., Sextro, W. (2022). Development of a Hybrid Modeling Methodology for Oscillating Systems with Friction. In: Nicosia, G., et al. Machine Learning, Optimization, and Data Science. LOD 2021. Lecture Notes in Computer Science(), vol 13164. Springer, Cham. https://doi.org/10.1007/978-3-030-95470-3_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-95470-3_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-95469-7
Online ISBN: 978-3-030-95470-3
eBook Packages: Computer ScienceComputer Science (R0)