Course detail

Intelligent Control Systems

FSI-RIRAcad. year: 2007/2008

The course gives a brief overview of control theory, learning and adaptation, classical concept of learning and basic methods of soft computing. The emphasis is put on the use of soft computing methods in control problems solving. An applicability of introduced resources to engineering problems solving is discussed.

Language of instruction

Czech

Number of ECTS credits

5

Mode of study

Not applicable.

Guarantor

prof. RNDr. Ing. Tomáš Březina, CSc.

Department

Institute of Automation and Computer Science (ÚAI)

Learning outcomes of the course unit

Students will learn how and when to use the basic resources of soft computing for control problems solving.

Prerequisites

The knowledge of basic relations from graphs theory, probability theory and statistics is supposed. The orientation in control theory a fuzzy logic is suggested.

Co-requisites

Not applicable.

Planned learning activities and teaching methods

Teaching methods depend on the type of course unit as specified in the article 7 of BUT Rules for Studies and Examinations.

Assesment methods and criteria linked to learning outcomes

Course-unit credit requirements: active participation in seminars and individual elaboration of an assigned project. The examination comprises written and oral parts. The written part is represented by a test with four questions. Oral part consists of discussion on the written part with possible complementary questions. The evaluation is fully in competence of a tutor according to the valid directives of BUT.

Course curriculum

Not applicable.

Work placements

Not applicable.

Aims

The goal is to master the basics of methods used in intelligent control and common potential of soft computing use for control as well as the frame of "intelligent" controllers design.

Specification of controlled education, way of implementation and compensation for absences

The attendance at lectures is recommended while at seminars it is obligatory. Education runs according to week schedules. The form of compensation of missed seminars is fully in the competence of a tutor.

Recommended optional programme components

Not applicable.

Prerequisites and corequisites

Not applicable.

Basic literature

Hangos, K. M., Lakner, R., Gerzson, M.: Intelligent Control Systems (An Introduction with Examples), ISBN: 978-1-4757-7529-7,  Springer New York, NY (EN)

Recommended reading

Not applicable.

Classification of course in study plans

  • Programme B3901-3 Bachelor's

    branch B3904-00 , 3. year of study, winter semester, compulsory

Type of course unit

 

Lecture

26 hours, optionally

Teacher / Lecturer

prof. RNDr. Ing. Tomáš Březina, CSc.

Syllabus

1. General concept of feedback/feedforward control systems.
2. Overview of classical, modern control systems, adaptive and robust control systems.
3. Learning process as basis for adaptive control.
4. Intelligent control systems.
5. Neuron model and neural network structures.
6. Rule-based systems. Fuzzy control.
8. Fuzzy decision making.
9. Markov decision processes, reinforcement learning.
10. Multi-agent reinforcement learning.
11. Hybrid neural network and fuzzy logic controllers12. Fuzzy Q-learning, Multi-agent fuzzy reinforcement learning.
13. Genetic algorithm basics, optimization and control design.

Computer-assisted exercise

26 hours, compulsory

Teacher / Lecturer

prof. RNDr. Ing. Tomáš Březina, CSc.

Syllabus

1. Basics of work with Matlab/Simulink/Control System Toolbox.
2. Case study: classical design of controller.
3. Basics of work with Matlab/Simulink/Fuzzy Logic Toolbox.
4. Basics of work with Matlab/Simulink/Fuzzy Logic Toolbox.
5. Case study: neural controller.
6. Case study: rule–based controller.
7. Case study: fuzzy controller I.
8. Case study: fuzzy controller II.
9. Case study: QL–regulator.
10. Case study: reinforcement multi–agent learning.
11. Case study: neuro–fuzzy regulator.
12. Case study: Fuzzy QL–controller.
13. Accreditation.