“Data-driven identification of passive friction dynamics with kernel methods”
Authors: Marie Hayashi Strand and Olav Egeland,Affiliation: SINTEF and NTNU
Reference: 2026, Vol 47, No 2, pp. 51-69.
Keywords: Data-driven identification, RKHS, passivity, friction estimation
Abstract: This paper presents a method for data-driven identification of passive systems, with a focus on systems with nonlinear friction models. This is achieved by approximating the passive dynamics of a given system in a reproducing kernel Hilbert space (RKHS). The main novelty of this approach is the use of a quadratic kernel model to ensure that the estimated friction dynamics is passive. The regularized regression is done by optimizing a convex Fenchel dual of the optimization problem. The method was validated with a simulation study, where it was first applied to the estimation of a Karnopp friction model with Stribeck effects. It was also applied to the identification of systems dynamics of a mass-spring-damper (MSD) system with the same friction model. The identification was performed using two different forms of input data: sampled input and output signals and the Legendre coefficients corresponding to these signals. Results demonstrated accurate identification of training data, as well as examples of generalization to test data. Passivity and causality of the approximated continuous system do not guarantee passivity and causality of its corresponding discretized or spectrally approximated system. Although simulation results demonstrate this, increasing the sample size could increase representation accuracy and thereby the preservation of these properties.
PDF (1026 Kb)
DOI: 10.4173/mic.2026.2.2References:
[1] Armstrong-Helouvry, B. (1991). Control of machines with friction, The Springer International Series in Engineering and Computer Science. Springer. doi:10.1007/978-1-4615-3972-8
[2] Armstrong-Helouvry, B., Dupont, P., and Canudasde Wit, C. (1994). A survey of models, analysis tools and compensation methods for the control of machines with friction, Automatica. 30(7):1083–1138. doi:10.1016/0005-1098(94)90209-7
[3] Aronszajn, N. (1950). Theory of reproducing kernels, Trans. American Society. 68(3):337 -- 404. doi:10.1090/S0002-9947-1950-0051437-7
[4] Boffi, N.M., Tu, S., and Slotine, J.-J.E. (2022). Nonparametric adaptive control and prediction: theory and randomized algorithms, ArXiv:2106.03589v3 [math.
[5] Borwein, J.M. and Lewis, A.S. (2006). Convex analysis and nonlinear optimization: Theory and examples, Springer, 2nd edition. doi:10.1007/978-0-387-31256-9
[6] Boyd, S. and Vandenberghe, L. (2004). Convex Optimization, Cambridge University Press. doi:10.1017/CBO9780511804441
[7] Brogliato, B., Lozano, R., Maschke, B., and Egeland, O. (2020). Dissipative Systems Analysis and Control: Theory and Applications, Communications and Control Engineering. Springer, 3 edition. doi:10.1007/978-3-030-19420-8
[8] Canuto, C., Quarteroni, A., Hussaini, M.Y., and Zang, T.A. (2006). Spectral Methods: Fundamentals in Single Domains, 2006. doi:10.1007/978-3-540-30726-6
[9] Cheng, C.-A. and Huang, H.-P. (2016). Learn the Lagrangian: A vector-valued RKHS approach to identifying Lagrangian systems, IEEE Transactions on Cybernetics. 46(12):3247--3258. doi:10.1109/TCYB.2015.2501842
[10] Cucker, F. and Smale, S. (2002). On the mathematical foundations of learning, Bull. Am. Math. Soc.. 39:1--49. doi:10.1090/S0273-0979-01-00923-5
[11] CVXResearch, I. (2012). CVX: MATLAB software for disciplined convex programming, 2012. https://cvxr.com/cvx/.
[12] Dahl, P.R. (1968). A Solid Friction Model, Technical Report TOR-0158(3107-18)-1, The Aerospace Corporation, El Segundo.
[13] Desoer, C.A. and Vidyasagar, M. (1975). Feedback Systems: Input-Output Properties, Elsevier Inc.
[14] Egeland, O. and Gravdahl, J.T. (2002). Modeling and Simulation for Automatic Control, Marine Cybernetics.
[15] Evgeniou, T., Pontil, M., and Poggio, T. (2000). Regularization networks and support vector machines, Advances in Computational Mathematics. 13:1--–50. doi:10.1023/A:1018946025316
[16] Gentle, J.E. (1998). Numerical Linear Algebra for Applications in Statistics, Statistics and Computing. Springer. doi:10.1007/978-1-4612-0623-1
[17] Golub, G.H. and VanLoan, C.F. (2013). Matrix Computations, Johns Hopkins University Press, Baltimore, MD, USA, 4 edition.
[18] Karnopp, D. (1985). Computer simulation of stick-slip friction in mechanical dynamic systems, J. Dyn. Syst., Meas., Control. 107(1):100–103. doi:10.1115/1.3140698
[19] Khosravi, M. and Smith, R.S. (2023). Kernel-based identification with frequency domain side-information, Automatica. 150. doi:10.1016/j.automatica.2022.110813
[20] Marteau-Ferey, U., Bach, F., and Rudi, A. (2020). Non-parametric models for non-negative functions, In Proceedings of the 34th Conference on Neural Information Processing Systems (NeurIPS 2020), NIPS '20. 2020.
[21] Micchelli, C.A. and Pontil, M. (2005). On learning vector-valued functions, Neural Computation. 17(1):177--204. doi:10.1162/0899766052530802
[22] Micheli, M. and Glaunes, J.A. (2014). Matrix-valued kernels for shape deformation analysis, Geometry, Imaging and Computing. 1(1):57--139. doi:10.4310/GIC.2014.v1.n1.a2
[23] Minh, H.Q. and Sindhwani, V. (2011). Vector-valued manifold regularization, In Proceedings of the 28'th International Conference on Machine Learning. 2011.
[24] Moreschini, A., Bin, M., Astolfi, A., and Parisini, T. (2025). A generalized passivity theory over abstract time domains, IEEE Transactions on Automatic Control. 70(1):2--17. doi:10.1109/TAC.2024.3423510
[25] Muzellec, B., Bach, F., and Rudi, A. (2022). Learning PSD-valued functions using kernel sums-of-squares, ArXiv:2111.11306v2 [stat.
[26] Pillonetto, G., Chen, T., Chiuso, A., Nicolao, G.D., and Ljung, L. (2022). Regularized System Identification: Learning Dynamic Models from Data, Springer Nature. doi:10.1007/978-3-030-95860-2
[27] Pillonetto, G., Dinuzzo, F., Chen, T., Nicolao, G.D., and Ljung, L. (2014). Kernel methods in system identification, machine learning and function estimation: A survey, Automatica. 50(3):657--682. doi:https://doi.org/10.1016/j.automatica.2014.01.001
[28] Pillonetto, G., Quang, M.H., and Chiuso, A. (2011). A new kernel-based approach for nonlinear system identification, IEEE Transactions on Automatic Control. 56(12):2825--2840. doi:10.1109/TAC.2011.2131830
[29] Press, W.H., Teukolsky, S.A., Vetterling, W.T., and Flannery, B.P. (2007). Numerical Recipes: The Art of Scientific Computing, Cambridge University Press, 3 edition.
[30] Schoelkopf, B. and Smola, A.J. (2002). Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond, MIT Press. doi:10.7551/mitpress/4175.001.0001
[31] Shali, B.M. and van Waarde, H.J. (2024). Towards a representer theorem for identification of passive systems, 2024, ArXiv:2404.08297v1 [math.
[32] Singh, S., Richards, S.M., Sindhwani, V., Slotine, J.-J.E., and Pavone, M. (2021). Learning stabilizable nonlinear dynamics with contraction-based regularization, The International Journal of Robotics Research. 40(10-11):1123--1150. doi:10.1177/027836492094993
[33] Smith, T. and Egeland, O. (2024). Learning Hamiltonian dynamics with reproducing kernel Hilbert spaces and random features, European Journal of Control. 80:101128. doi:10.1016/j.ejcon.2024.101128
[34] Smith, T. and Egeland, O. (2025). Nonparametric adaptive payload tracking for an offshore crane, ArXiv:2503.12250v2 [cs.
[35] Strand, M.H. (2025). Data-driven Identification of Passive Friction Dynamics with Linear and Quadratic Kernel Models, Master's thesis, Norwegian University of Science and Technology (NTNU), Trondheim, Norway. https://nva.sikt.no/registration/0199c8021f51-63967d4c-61e0-422d-a9b4-b6ac88c2ebfd.
[36] Tanaka, Y., Iwata, T., and Ieda, N. (2022). Symplectic spectrum Gaussian processes: Learning Hamiltonians from noisy and sparse data, In S.Koyejo, S.Mohamed, A.Agarwal, D.Belgrave, K.Cho, and A.Oh, editors, Advances in Neural Information Processing Systems, volume35. Curran Associates, Inc., pages 20795--20808. doi:10.52202/068431-1512
[37] Toh, K.-C., Todd, M.J., and Tutuncu, R.H. (2012). On the implementation and usage of SDPT3 – a MATLAB software package for semidefinite-quadratic-linear programming, version 4, 0. 2012. doi:10.1007/978-1-4614-0769-0_25
[38] Vidyasagar, M. (2002). Nonlinear Systems Analysis, Classics in Applied Mathematics. SIAM, 2 edition. doi:10.1137/1.9780898719185
[39] van Waarde, H.J. and Sepulchre, R. (2023). Kernel-based models for system analysis, IEEE Transactions on Automatic Control. 68(9):5317--5332. doi:10.1109/TAC.2022.3218944
[40] Wahba, G. (1990). Spline Models for Observational Data, CBMS-NSF Regional Conference Series in Applied Mathematics. SIAM, 1990. doi:10.1137/1.9781611970128
[41] Wang, Z. and Forni, F. (2025). Passive nonlinear FIR filters for data-driven control, ArXiv:2508.05279v1 [eess.
[42] Canudasde Wit, C., Olsson, H., Astrom, K., and Lischinsky, P. (1995). A new model for control of systems with friction, IEEE Transactions on Automatic Control. 40(3):419--425. doi:10.1109/9.376053
BibTeX:
@article{MIC-2026-2-2,
title={{Data-driven identification of passive friction dynamics with kernel methods}},
author={Strand, Marie Hayashi and Egeland, Olav},
journal={Modeling, Identification and Control},
volume={47},
number={2},
pages={51--69},
year={2026},
doi={10.4173/mic.2026.2.2},
publisher={Norwegian Society of Automatic Control}
};