- Romanian

Main Frame (acces to all the site)

Course of Artificial Intelligence and Intelligent System with Application in Power Electronics

Class Meets:

Each Monday, starting at 14:00 and goes up to 17:00 (with 10 minutes breaks at 14.50 and 15.50) in Room P6, from September 27 to January 17 in the next year.

Examination:

Final Exam: 80%
Homework: 10%
Class Participation: 10%

The course cover the following topics:

1. Genetic Algorithms

1.1. What are Genetic Algorithms? Introduction
1.2. Genetic algorithms versus "traditional" methods
1.3. Representation
1.4. The objective and fitness function
1.5. Selection

1.5.1. Roulette wheel
1.5.2. Stochastic Universal Sampling
1.5.3. Ranked based
1.5.4. Tournament
1.5.5. Steady-State

1.6. Operators of GA

1.6.1. Recombination
1.6.2. Crossover

Single point crossover
Multiple point crossover
Uniform crossover
Half uniform crossover (HUX)
Arithmetical crossover
Intermediate Crossover
Linear Crossover
Restricted Crossover

1.6.3. Mutation
1.6.4. Elitism

1.7. Discussion
1.8. Stopping Criteria

1.8.1. Generation Number
1.8.2. Evolution Time
1.8.3. Fitness Threshold
1.8.3. Fitness Convergence
1.8.4. Population Convergence
1.8.5. Gene Convergence

1.9. Parameters of the Genetic Algorithms
1.10. Multiple population
1.11. Fundamental Theorem of GA's
1.12. Building block hypothesis
1.13. Epistasis
1.14. Deceptive Genetic Algorithms
1.15. Test Function

2. Application of the Genetic Algorithms in Power Electronics

2.1. Power factor correction - generality
2.2. Passive Filter Design Using Genetic Algorithms
2.3. Evolutionary Approach for Line Current Harmonic Reduction in AC/DC Converters
2.4. Control Technique for Active Power Filters using Genetic Algorithms

3. Fuzzy Systems

3.1. Introductions
3.2. Fuzzy sets
3.3. Operation with membership functions
3.4. Fuzzy inference system (Mamdani)
3.5. T and S norm
3.6. Fuzzy inference system (Sugeno)
3.7. Self-organization linguistic fuzzy system
3.8. Adaptive crisp filters
3.9. Adaptive fuzzy filters

4. Application of the Fuzzy Systems in Power Electronics

4.1. Implementation of a Fuzzy controller for DC-DC Converters
4.2. Fuzzy Logic Applied to Speed Control of a Stepping Motor Drive

Lab syllabus:

1. Introduction to TMS320C6711 DSP
2. Code Composer Studio
3. Interrupts
4. Using McBSP
5. Using EDMA 1
6. Using EDMA 2
7. DSP-BIOS - Real-Time Scheduling and Analysis Tools 1
8. DSP-BIOS - Real-Time Scheduling and Analysis Tools 2
9. DSP genetic algorithm implementation 1
10. DSP genetic algorithm implementation 2
11. DSP genetic algorithm implementation 3
12. DSP fuzzy system implementation 1
13. DSP fuzzy system implementation 2
14. DSP fuzzy system implementation 3
    

Bibliography

1. K. Sundareswaran, Mullangi Chandra, Evolutionary Approach for Line Current Harmonic Reduction in AC/DC Converters, IEEE Transactions on Industrial Electronics, Vol. 49, no. 3, June 2002, pp. 716-719
2. Yaow-Ming Chen, Passive Filter Design Using Genetic Algorithms, IEEE Transactions on Industrial Electronics, Vol. 50, no. 1, February 2003, pp. 202-207
3. M. El-Habrouk, M. K. Darwish, A New Control Technique for Active Power Filters Using a Combined Genetic Algorithm/Conventional Analysis, IEEE Transactions on Industrial Electronics, Vol. 49, no. 1, February 2002, pp. 58-66
4. Bernard Widrow, Gregory L. Plett, Nonlinear Adaptive Inverse Control, In Proceedings of the 36th Conference on Decision & Control, San Diego, California USA, December 1997, pp. 1032 - 1037