Course detail
Modelling and Identification
FEKT-MPC-MID Acad. year: 2025/2026 Winter semester
The subject is oriented on:
- identification methods of dynamic systems
- approaches towards nonparametric and parametric identification
- on-line and off-line identification
- spectral estimation, assessment of noise and disturbance influence on identification results
Language of instruction
Czech
Number of ECTS credits
6
Supervisor
Department
Entry knowledge
The subject knowledge on the Bachelor´s degree level is requested.
Rules for evaluation and completion of the course
Numerical Exercises – Max 15 points.
Individual project – Max. 15 points.
Final Exam – Max. 70 points.
The content and forms of instruction in the evaluated course are specified by a regulation issued by the lecturer responsible for the course and updated for every academic year.
Aims
Familiarize students with basic techniques for dynamic system identification and with their possible limitations. The students will get to know how the noise acting on the plant influences the identification results and how to cope with it.
After passing the course, student should be able to
- use non-parametric identification methods
- select suitable excitation signal for the identification
- program and use the basic least squares method
- explain where biased estimate comes from and how to overcome this issue
- use the approaches which enable to enhance the quality of the estimates during practical applications
- utilize the universal programming equipment of MATLAB Simulink and its toolboxes for the identification of dynamic systems
The study programmes with the given course
Programme MPC-KAM: Cybernetics, Control and Measurements, Master's, compulsory-optional
Programme N-AIŘ-P: Applied Computer Science and Control, Master's, compulsory
Type of course unit
Lecture
26 hours, optionally
Syllabus
1. Introduction into dynamic system identification.
2. Nonparametric identification methods, correlation methods, frequency response measurement.
3. Input signal for identification, degree of persistent excitation, pseudorandom binary sequence.
4. Least squares method, derivation, geometric representation, properties.
5. Dynamic system models for system identification, ARX, ARMAX ARARX, general model, pseudolinear regression.
6. Recursive LSM. Numerically stable methods based on square root filtering.
7. Instrumental variable methods. Method with delayed observations, method with additional model.
8. Identification methods based on prediction error whitening. Noise model identification.
9. Practical notes on system identification.
10. Identification using neural nets and fuzzy modeling.
11. Another approaches to system identification.
12. Identification of nonlinear dynamic systems.
13. Course summary. Conclusions.
Exercise in computer lab
26 hours, compulsory
Syllabus
1. Brief introduction into system identification.
2. Parameter identification from impulse and step response.
3. Identification using correlation methods, frequency.
4. Spectral analysis.
5. Input signals for identification, least squares method.
6. Recursive least squares method.
7. Instrumental variable methods.
8. System Identification Toolbox.
9. Identification methods base on whitening of prediction error.
10. Extended frequency analysis, PMS motor parameters identification.
11. Identification using recursive least squares method.
12. Test + work on project.
13. Real experiment – DC motor parameters identification.