Logo ČVUT
CZECH TECHNICAL UNIVERSITY IN PRAGUE
STUDY PLANS
2019/2020

Artificial Intelligence in Engineering Application

Login to KOS for course enrollment Display time-table
Code Completion Credits Range
W37A003 ZK 4P+2C
Lecturer:
Jiří Bíla (guarantor)
Tutor:
Jiří Bíla (guarantor)
Supervisor:
Department of Instrumentation and Control Engineering
Synopsis:

The overview of methods of Artificial Intelligence and the ways of their deployment in Engineering. Examples of Problem Solving support in cases of some Engineering Tasks. Formal apparatus for the selected parts of Artificial Intelligence (General Algebra, formal logic, resolution principle, fuzzy sets, fuzzy relational calculus, fuzzy logic, qualitative algebras). Some representative approaches and methods: Searching methods in generalised state space (Search Space). Structural Pattern Recognition - Formal grammars and Automata. Qualitative Modelling and Simulation of Systems. Fuzzy Controllers, Theory and Design of Fuzzy Controllers. (Mamdani and Sugeno controllers.) Implementation of fuzzy controllers in Fuzzy Tool box for MatLab. Examples of Application. Qualitative methods in Fault Detection. Expert Systems and their application in Engineering. Neural Networks. Types of Neural Networks: MLP (Multi-Layer Perceptrons), RBF (Radial Basis Function) and HONNU (Higher Order Neural Network Unit). Implementation of Neural Networks in Neural Network Toolbox for MatLab. Examples of Applications. Genetic algorithms and Genetic Programming.

Requirements:

see lectures

Syllabus of lectures:

P1. Mathematics for Artificial Intelligence.

P2. Formal and SW means for Problem Solving Support.

P3. Structural Pattern Recognition. Formal Grammars.

P4. Formal Grammars and Recognition Automata.

P5. Fuzzy and fuzzy-qualitative modelling and control.

P6. Fuzzy and fuzzy-qualitative modelling and control. (Fuzzy toolboxfor MatLab/Simulink.)

P7. Expert Systems and their application in Engineering.

P8. Neural Networks. Introduction and a MLP Networks (Multi Layer Perceptron).

P9. Neural Networks with s RBFs (Radial Basis Functions). Networks with HONNUs (Higher Order Neural networks Units).

P10. Neural Network Toolbox for MatLab/Simulink.

P11. Genetic algorithms. (Introduction and classical GA.)

P12. Examples of GA Application. Genetic Programming.

P13. Example of a larger application: Analysis and Modelling of CardioVascular System (Heart Rate Variability (HRV), Electro Cardio Graph (ECG)) - comparing of application of non-linear methods with the deployment of Neural networks.

P14. Example of a larger application: Diagnostics of structural and operational faults in materials, constructions and systems.

Syllabus of tutorials:

none

Study Objective:

see lectures

Study materials:

1. Nilsson, N.J.: Artificial Intelligence. A New Synthesis. Morgan Kaufmann Publishers, Inc., San Francisco, California, 1998.

2. Kruse, R., Gebhardt, J. Klawonn: Foundation of Fuzzy Systems.Hohn Wiley and Sons, NY, 1994.

3. Gupta, M.M, Liang J., Homma, N.: Static and Dynamic Neural Networks. IEEE Press, A John Wiley and Sons, 2003.

Note:
Time-table for winter semester 2019/2020:
Time-table is not available yet
Time-table for summer semester 2019/2020:
Time-table is not available yet
The course is a part of the following study plans:
Data valid to 2020-01-24
For updated information see http://bilakniha.cvut.cz/en/predmet10899202.html