450-8707/01 – Non-Conventional Methods of Mechatronical Systems Control (NMŘMS)
| Gurantor department | Department of Cybernetics and Biomedical Engineering | Credits | 4 |
| Subject guarantor | Ing. Zdeněk Slanina, Ph.D. | Subject version guarantor | Ing. Zdeněk Slanina, Ph.D. |
| Study level | undergraduate or graduate | Requirement | Compulsory |
| Year | 2 | Semester | winter |
| | Study language | Czech |
| Year of introduction | 2011/2012 | Year of cancellation | |
| Intended for the faculties | USP, FS | Intended for study types | Follow-up Master |
Subject aims expressed by acquired skills and competences
To acquaint students with modern and efficient control methods, which use non-numeric descriptions of the control law in the science of artificial intelligence. Students will acquire knowledge of fuzzy set mathematics and fuzzy logic, artificial neural networks and evolutionary algorithms. Acquires skills in the design, debugging and application of fuzzy controllers, neural controllers and special intelligent controllers and advanced optimization using genetic algorithms. For the controller design and simulation is used Matlab-Simulink.
Teaching methods
Lectures
Tutorials
Project work
Summary
The course is based on selected methods of artificial intelligence applied in the synthesis of non-conventional controllers of mechatronic systems. Approaches are used Mamdani and Takagi-Sugeno fuzzy controllers and fuzzy-neural controllers. To adapt and optimize the structure and controller parameters are used genetic algorithms. Computer simulations are carried out in Matlab-Simulink.
Compulsory literature:
Recommended literature:
Additional study materials
Way of continuous check of knowledge in the course of semester
Credit conditions:
Students can reach 40 (21 minimal) points for essays and term labor.
Completion of the course:
Students must receive credit and pass the final exam. Final exam has two parts
- Written exam with a gain of 40 (10 minimal) and points
- Oral exam with a gain of 20 (6 minimal) points
The completion of this course the student must complete both parts of the final exam.
E-learning
Other requirements
There are not defined other requirements for student
Prerequisities
Subject has no prerequisities.
Co-requisities
Subject has no co-requisities.
Subject syllabus:
1. Artificial intelligence principles, non-conventional description of complex systems
2. Principles and approaches of knowledge based non-numerical modelling and control
3. Principles of fuzzy sets and fuzzy linguistic logic
4. Rule based modelling, aproximative reasoning and results interpretation, expert systems
5. Fuzzy logic based controller analysis and synthesis, structures and their properties in comparison with conventional controllers
6. Fuzzy control and its application in mechatronics
7. Artificial neural networks, structures and self-learning principles
8. Neural controller synthesis an their properties discussion
9. Combined fuzzy-neural controllers
10. Evolution and genetic algorithms in tasks of optimization of structures and parameters of conventional controllers
11. Genetic algorithms application issues, advanced genetic algorithms and their properties
12. Structural and parameter optimization of non-conventional controllers using genetic algorithms
13. Computational intelligence, integrated fuzzy-neuro-genetic structures in control
14. Intelligent controllers, their structure and application
Conditions for subject completion
Occurrence in study plans
Occurrence in special blocks
Assessment of instruction