Institutional Repository of Vilnius University
Retas Netiesinės Dinamikos Identifikavimas Diferencialinėms Lygtims /
Abstract
dc:descriptionThis work examines the Sparse Identification of Nonlinear Dynamics (SINDy) framework and its applications in system identification. The main objectives are to familiarize with the structure of the SINDy framework, apply it by simulating and analyzing well-known mathematical models, and utilize its essential components to identify the underlying equations governing the dynamics of the models. By exploring sparse regression techniques and conducting separate investigations on the Lotka-Volterra predator-prey model, the simple pendulum, and the Van der Pol oscillator, we study and demonstrate the capabilities and limitations of the SINDy framework. Valuable insights are gained regarding the importance of model construction, algorithm parameters, and noise reduction in achieving accurate and interpretable system identification. Future directions and goals for further work are proposed. Overall, this work serves as an introductory exploration of the SINDy framework, providing a foundation for further research and utilization in understanding complex dynamical systems.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2023
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Valatkevičius, Kasparas,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD192844292&prefLang=en_US