Statistical Methods for Analysis and Identification of Mechanical Systems

Garant předmětu:

Michael Valášek

Lecturer:

Václav Bauma, Zbyněk Šika, Michael Valášek

Tutor:

Václav Bauma, Zbyněk Šika, Michael Valášek

Supervisor:

Department of Mechanics, Biomechanics and Mechatronics

Synopsis:

The student will be acquainted with the principles and procedures of statistical methods for analysis and identification of mechanical systems.

•Models of dynamic systems: state models, ARX, AR, ARMAX, ARMA, OE, BJ.

•Random process and its statistical characteristics

•Passing random process through linear dynamic system

•Signal processing, sampling, windows

•Identification of linear dynamic system, experimental and operational modal analysis

•Models of nonlinear dynamic systems: Markov chains, Wiener model

•Passing random process through nonlinear dynamic system

•Identification of nonlinear dynamic system

•Stochastic identification methods: regression, correlation, adaptive methods

•Identification of nonlinear systems: neuro-fuzzy methods (LOLIMOT), neural networks.

•Kalman filter for nonlinear systems

•Identification in closed loop control. Identification of unstable systems.

Requirements:

Syllabus of lectures:

Syllabus of tutorials:

Study Objective:

Study materials:

•Julius S. Bendat, Allan G. Piersol: Engineering Applications of Correlation and Spectral Analysis, J. Wiley 2013

•Rolf Isermann, Marco Münchhof : Identification of Dynamic Systems: An Introduction with Applications, Springer 2010

•L. Ljung: System Identification - Theory for User, Prentice Hall PTR, 1999

•Štefan, M.; Šika, Z.; Valášek, M.; Bauma, V.: Neuro-Fuzzy Identification of Nonlinear Dynamic MIMO Systems

•Engineering mechanics. 2006, 13(3), pp. 223-238.

•odkaz: https://moodle-vyuka.cvut.cz/

Note:

Time-table for winter semester 2023/2024:

Time-table is not available yet

Time-table for summer semester 2023/2024:

Time-table is not available yet

The course is a part of the following study plans: