Course details

Intelligent Controllers

QA5 Acad. year 2005/2006 Winter semester

Current academic year

Some problems that face us during process control. PID controller as a basic reference controller. Settings and realization of classical industrial controllers. Adaptive, self tuning and heuristic controllers. Adaptive control algorithms based on discrete identification. Typical problems arising during adaptive control. The controllers with artificial intelligence. Introduction into fuzzy logic. Fuzzy controllers. Introduction into neural nets. Neural controllers. Implementation of intelligent controllers in real processes. Example of control of complex process.

Guarantor

Pivoňka Petr, prof. Ing., CSc.

Language of instruction

Czech

Completion

Examination

Time span

  • 39 hrs lectures

Department

Department of Control and Instrumentation (UAMT)

Subject specific learning outcomes and competences

Course absolvent should be an able to design, to realisation, adjust, comparison and development new classical control algorithms and control algorithms with principles of artificial intelligence.

Learning objectives

Critical practical view and comparative study on most used methods of design and realisation classical, modern and control algorithms with artificial intelligence.

Prerequisite knowledge and skills

There are no prerequisites

Study literature

  • Pivoňka, P. a kol.: Fuzzy regulátory. Fuzzy množiny v řízení a regulaci, Návrh a realizace standardních PID a PSD regulátorů, Fuzzy PI/PD/PID regulátory, Alternativní návrhy fuzzy regulátorů. Automatizace, 40, 41, 42, (1997), (1998), (1999) str. P1-P38, ISSN 0005-125X.
  • Pivoňka, P.: Analysis and Design of Fuzzy PID Controller Based on Classical PID Controller Approach. Advances in Soft Computing, Physica Verlag, Springer, Heidelberg, 2000, pp.186-199, ISBN 3-7908-1327-3.
  • Pivoňka, P. - Adamčík, T.: On-Line Trained Neural Nets in Real-Process Control. Neural Network World, Vol.9. No. 1-2, 1999, pp. 75-89, ISSN 1210-0552,

Fundamental literature

  • Kosko,B.: Neural Networks and Fuzzy Systems. Prentice-Hall International (UK) Limited London, 1992.
  • Driankov, D. et al.: An Introduction to Fuzzy Control. Springer-Verlag, Berlin Heidelberg, 1993.
  • Leigh,J.R.: Applied digital control. Prentice-Hall International (UK) Limited Hertfordshire, 1992.
  • Astrom, K., Wittenmark,B.:Computer controlled systems, Prentice-Hall Inc., London, 1997.

Syllabus of lectures

  • Physical background of control.
  • Design and realisation of continuous PID controllers. Different types of PID controllers, realisation, setting of parameters, comparison, anti-windup and switching between algorithms.
  • Design and realisation of discrete analogy of continuous PID algorithms.
  • Philosophy of the process identification and design of controller's algorithm.
  • Optimum settings of controller's parameters, adaptive controllers, self tuning controllers, specific problems of adaptive control.
  • Dead beat controllers, state controllers.
  • Specific problems of optimal control.
  • Specific problems of predictive control.
  • Specific problems of MIMO control.
  • Artificial intelligence in controls algorithms. Fuzzy SISO and MISO controllers.
  • Artificial neural networks.
  • Identification with neural networks.
  • Neural controllers.

Progress assessment

Study evaluation is based on marks obtained for specified items. Minimimum number of marks to pass is 50.

Controlled instruction

There are no checked study.

Back to top