en_GB
Hold Ctrl-tasten nede. Trykk på + for å forstørre eller - for å forminske.

ELE620_1

System Identification

This is the study programme for 2020/2021.


An introduction to stochastic processes and their properties: correlation, white noise and power spectrum. Parametric system identification: ARX and ARMAX models, adaptive filtering, LS and RLS methods. State space models and Kalman filter. Mass and energy balance based models, discretization of continuous systems.

Learning outcome

  • Describe discrete and continuous dynamic systems by transfer-functions and state-space-models.
  • Transform a dynamic system from one form to another.
  • Describe stochastic a system.
  • Do state and parameter estimation by Kalman filtering and RLS.

Contents

An introduction to stochastic processes and their properties: correlation, white noise and power spectrum. Parametric system identification: ARX and ARMAX models, adaptive filtering, LS and RLS methods. State space models and Kalman filter. Mass and energy balance based models, discretization of continuous systems and elements of fault diagnosis.

Required prerequisite knowledge

None.

Exam

Weight Duration Marks Aid
Written exam1/14 hoursA - FNo printed or written materials are allowed. Approved basic calculator allowed.

Coursework requirements

Exercises
At least 6 of 8 exercises should be approved by course instructor within the specified deadlines to get access to exam.

Course teacher(s)

Course teacher
Damiano Rotondo , Tom Ryen

Method of work

4 hours of lectures and 1-2 hours exercises per week.

Overlapping courses

Course Reduction (SP)
System identification (MIK130_1) 10
System identification (MIK130_2) 10

Open to

Admission to Single Courses at the Faculty of Science and Technology
Robot Technology and Signal Processing - Master's Degree Programme

Course assessment

Form and/or discussion.

Literature


Link to reading list


This is the study programme for 2020/2021.

Sist oppdatert: 08.08.2020

History