Göm meny

Schedule for System Identification 2018

The course starts on Febrary 14 at 13.15 in Algoritmen and continues for 10 weeks. The detailed schedule will be decided at the first meeting. Send an email to me (Lennart-Ljung-at-liu.se) if you want to participate.

The schedule below is a tentative outline of the course. The dates and times will be fixed at the first meeting.

>
Date Notes Chapters Problems
We 14/2 13.15Overview......
We 21/2 13.15Nonlinear Models Kap 1,2,32G.4, 2E.2, 2E3, 3G.2, 3E.4
We 28/2 13.15Linear Models - Special IssuesKap 4,54G.4, 4G.5, 4E.1, 4E.3, 5G.1, 5E.2
We 7/3 13.15Chapters 8 - 9 6,76G.1, 6G.3, 6G.5, 7G.1, 7G.4,7E.1, 7E.3
We 14/3 13.15... 8,9 8G.2 8G.3, 8E.3, 9G.2, 9E.3, 9E.4
We 21/3 13.15...Data Discussion..
We 28/3 13.15Experiment Design Kap 10,1110G.3,10E.1,10E.3,11E.4,11D.1,11E.3
We 18/4 13.1512,13,1413G.2,13E.1,13E.3,13E.5.14G.2
We 25/4 13.15 ...15,16,17, Summary15E.1,16G.1,16E.2,16E.3
We 2/5 13.15...Reports on micro-projects; Questions..

Part of the last meeting will be devoted to questions on the whole material.

The exam period is three days that you select yourself in the designated period.

The organization of the lectures is as follows: The material of the chapters will be discussed during the first half of the lecture on the indicated day. It is assumed that the participants have read and digested the material before that and also have solved the indicated problems. The participants should be prepared to take active part in the discussion of the material. The second half of the lecture will be used to introduce next week's material.

It is recommended that the participants meet an additional time per week, without the lecturer, to discuss the problems and prepare the discussion for the next lecture.

An errata list for the textbook is available here

The course contains two projects to be performed in groups of 1-3 students: An identification problem with real data and a "micro-project".

Data tests

Working with real data sets will be an essential part of the course. the DAISY identification site

and work with it during the first few weeks. Preferably the work should be carried out using the System Identification Toolbox. (Matlab 8 or higher). If you need some exercises to get further familiar with this toolbox you can download this file. Some useful data for these exercises are realdata.mat

Project ideas:

1. Investigate what the MATLAB-package LOLIMOT (https://sourceforge.net/projects/lolimot/) can do for LOcal LInear MOdels. How does it compare with Tree- NLARX models?
2. Data tapering (windowing), see excercise 6G.5, is standard for spectral estimation in signal processing. Check by simulation the benefits for estimating a signal's spectrum. If we have dynamical system y=Gu, check how tapering works when spectral analysis is used for estimating G. How about ARX-modeling?
3. The Australian UNIT Matlab Toolbox (I have a copy) has implemented the EM algorthm for estimating linear state-space models. How does that work? Any differnces in efficiency and coping with local minima?
4. How can IDNLARX handle Wiener-Hammerstein Models and Hammerstein-Wiener?
5. Investigate some new ideas to improve spectral estimated with polynomial and rational interpolations. (Schoukens, Pintelon, Hjalmarsson, McKelvey)
6. "Elastic Nets" are combinations of L1 and L2 regularization. The Statistics Toolbox has mfiles for elastic nets for linear regression. Investigate how that works for ARX identification problems.
7. Test the Support Vector Machine Toolbox.(http://asi.insa-rouen.fr/enseignants/~arakoto/toolbox/)
8. Investigate how Balanced Model order reduction (BALRED) can handle FOCUS on certain frequency bands and trade-offs between measured and noise channels.

For the Exam:

You get a copy of the exam by sending a mail to lennart.ljung-at-liu.se telling when you want to receive it. You then have 72 hours to work on it. Return your solutions by email to me (scanned hand-written pages are OK). If you have a handwritten exam, also leave a sealed envelope with the exam to Ninna. The exam will be available from May 11. The last date for returning the exam is June 8 at 24.00. Remember to write your name on all pages!

On June 15, at 15.15 (prel time) we will have a meeting when the graded exams are returned.

Files for the exam: tenta18