|
50370 Fuzzy control and neural networks
| |
Danish title: Fuzzy regulering og neurale netværk
|
| Type: Å, Language: EED |
| |
Credit points:
5 point |
|
| | | Previous course: C5354 |
| Offered by:
Department of Automation
(IAU) |
| No credit points with: C5354 |
| Prerequisite: C3630/C5001/36230/50300/72131/72231/C8201 |
| Recommended semester:
7th - 9th semester |
| Limitation: Max. 30 |
| Scope and form: Lectures, Internet lessons, group work and laboratory exercises. |
| Examination:
Evaluation of report (½) and oral examination (½)
(13 point scale
) |
| Remarks: Both examination groups (days) are used for the oral examination. A half course is available on Internet (http://www.iau.dtu.dk/~jj/learn). |
| Contact person: |
Jan Jantzen, IAU, Building 326, Tel. +45 4525 3561 |
|
| Aim: Fuzzy control is applied in consumer products such as washing machines, video cameras, and rice cookers, as well as in industry for controlling for example cement kilns, underground trains, and robots. Fuzzy control is automatic control using rules, and it is based on fuzzy logic, which in short is computing with words rather than numbers. Fuzzy logic (without control) is also being applied within image processing, decision support, medical diagnosis, and in the financial sector. The course objectives are to explain the basics, to show how fuzzy logic is applied, and to teach the participants how to design a fuzzy controller. There is a link to neural networks, and the course explains what neuro-fuzzy data processing is, and it shows some applications. |
| Contents: Fuzzy set theory, rule based and table based controllers, tuning, performance, self-organisation, neural networks, neuro-fuzzy methods, applications. Laboratory exercise: design of a fuzzy controller for an inverted pendulum (Matlab, Simulink, lab. rig). |
|
|
