Hybrid Koopman-neural network approach for robust parameter estimation and prediction in duffing oscillators

سال انتشار: 1403
نوع سند: مقاله ژورنالی
زبان: انگلیسی
مشاهده: 51

فایل این مقاله در 16 صفحه با فرمت PDF قابل دریافت می باشد

استخراج به نرم افزارهای پژوهشی:

لینک ثابت به این مقاله:

شناسه ملی سند علمی:

JR_TAVA-10-1_002

تاریخ نمایه سازی: 31 فروردین 1404

چکیده مقاله:

Nonlinear dynamical system research is essential in science and engineering because it could be potentially employed to represent real-world phenomena.  Traditional methods rely on pre-defined models or computationally expensive simulations, limiting their applicability to only numerical data. In the present research, without any prior knowledge of the system, we suggest a novel way to build a linear representation of the Duffing oscillator by fusing the capabilities of deep neural networks with the Koopman operator. This recently established methodology makes it easier to estimate system parameters effectively and accurately predict the oscillator's future behavior. Our approach incorporates a modified training procedure that restricts the Koopman operator to a single linear layer within the neural network, improving interpretability and potentially reducing training complexity. This methodology not only simplifies nonlinear system analysis but also paves the way for advancements in predictive modeling across various fields. Notably, our method yields distinctive eigenvalues of the Koopman generator matrix, enabling the Koopman operator to exhibit robustness against noise and capture a spectrum of Duffing equation behaviors. This includes the precise prediction of periodic oscillations and the capturing of period-doubling bifurcation, all while maintaining tractability within the neural network framework.

نویسندگان

Yassin Riyazi

M.Sc. Student, School of Mechanical Engineering, College of Engineering, University of Tehran, Tehran, Iran

Navidreza Ghanbari

Assistant Professor, School of Mechanical Engineering, College of Engineering, University of Tehran, Tehran, Iran

Arash Bahrami

Assistant Professor, School of Mechanical Engineering, College of Engineering, University of Tehran, Tehran, Iran

مراجع و منابع این مقاله:

لیست زیر مراجع و منابع استفاده شده در این مقاله را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود مقاله لینک شده اند :
  • B.O. Koopman, Hamiltonian systems and transformation in Hilbert space, Proceedings ...
  • G.E. Hinton, R.R. Salakhutdinov, Reducing the dimensionality of data with ...
  • B. Lusch, J.N. Kutz, S.L. Brunton, Deep learning for universal ...
  • K. Champion, B. Lusch, J.N. Kutz, S.L. Brunton, Data-driven discovery ...
  • E. Kaiser, J.N. Kutz, S.L. Brunton, Sparse identification of nonlinear ...
  • A. Krizhevsky, I. Sutskever, G.E. Hinton, ImageNet classification with deep ...
  • K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale ...
  • K.He, X.Zhang, S.Ren,J.Sun,Deep residual Learning for image recognition, in: Proceeding ...
  • S.L. Brunton, M. Budišić, E. Kaiser, J.N. Kutz, Modern Koopman ...
  • C.W. Rowley, I. Mezić, S. Bagheri, P. Schlatter, D.S. Henningson, ...
  • P.J. Schmid, L. Li, M.P. Juniper, O. Pust, Applications of ...
  • M.O. Williams, I.G. Kevrekidis, C.W. Rowley, A data–driven approximation of ...
  • F. Moon, P.J. Holmes, A magnetoelastic strange attractor, Journal of ...
  • K.A. Kumar, S.F. Ali, A. Arockiarajan, Magneto-elastic oscillator: Modeling and ...
  • G. Duffing, Ingenieur: Erzwungene Schwingungen bei veränderlicher Eigenfrequenz und ihre ...
  • C. Runge, Über die numerische Auflösung von Differentialgleichungen, Mathematische Annalen, ...
  • C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, ...
  • Y. LeCun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning ...
  • J. Schmidhuber, S. Hochreiter, Long short-term memory, Neural Comput, ۹ ...
  • Q. Li, F. Dietrich, E.M. Bollt, I.G. Kevrekidis, Extended dynamic ...
  • نمایش کامل مراجع