Intelligent Control Systems

Course Description

Classification of artificial neural networks. Neural network (NN) structures suitable for system modeling and control. NN learning algorithms. Application of NN in identification and modeling of complex systems. Selection of suitable NN structures and their validation. NN process model-based control structures. Application of NN for improvement of nonlinear control system performance. Concept of current NN linearization and its application to linear controller synthesis. Application of NN for compensation of system ambiguities. Basic of evolutionary and genetic optimization algorithms. Classification of fuzzy logic controllers. Methods for fuzzy controllers design. Stability of fuzzy control systems. Methods for self-learning fuzzy controllers.

Learning Outcomes

  1. classify artificial neural networks
  2. apply neural network learning algorithms
  3. identify nonlinear dynamical systems via static neural networks
  4. design a neural controller for control of nonlinear dynamical systems
  5. apply genetic algorithms in optimization
  6. classify types of fuzzy logic controllers
  7. apply methods for fuzzy logic controller design

Forms of Teaching


Three hours of lectures per week.

Independent assignments

One homework in the first part of the semester (fuzzy logic).


4 laboratory exercises, 2 in the first part of the semester (fuzzy logic) and 2 in the second one (neural networks).

Grading Method

Continuous Assessment Exam
Type Threshold Percent of Grade Threshold Percent of Grade
Laboratory Exercises 0 % 36 % 0 % 36 %
Homeworks 0 % 8 % 0 % 0 %
Mid Term Exam: Written 0 % 26 % 0 %
Final Exam: Written 0 % 30 %
Exam: Written 0 % 64 %

To pass this course students need to pass all laboratory exercises.

Week by Week Schedule

  1. Fuzzy sets and fuzzy logic, Fuzzy rule base and fuzzy controller structure
  2. Fuzzy logic inference (fuzzy propositions, fuzzy relations, and fuzzy implications), Fuzzy rule base and fuzzy controller structure
  3. Fuzzy inference engines; fuzzyfication and defuzzyfication, Initial setting of fuzzy controller parameters
  4. Fuzzy inference engines; fuzzyfication and defuzzyfication, Initial setting of fuzzy controller parameters
  5. Lyapunov based fuzzy controller stability
  6. Phase-plane based fuzzy controller stability
  7. Self-learning fuzzy controller
  8. Midterm exam
  9. Single objective optimization problem vs; Multi-objective optimization problem, Unconstrained problems; Handling of constraints, Schemes for solution representation; Evolutionary operators (selection, mutation, recombination, etc;), Evolutionary algorithms for SOOP, Swarm-based algorithms for SOOP, Other evolutionary computation methods for SOOP, Evolutionary computation and MOOP (paretto optimality and other approaches), Parallelization of evolutionary computation algorithms
  10. Perceptron (learning paradigms,Hebbian learning, competitive learning, Boltzmann learning), Multilayer perceptron (error-backpropagation learning, credit-assignment problem, backpropagation through time), Self-organizing networks (Hebbian non-supervised learning, Oja's learning rule, PCA using self-organizing network, Sanger's learning rule, Competitive non-supervised learning, winner-takes-all network, Kohonen's self-organizing maps), Radial basis function networks (solving interpolation problem with radial basis function networks, generalized radial basis function networks, relation to regularization theory), Recurrent neural networks (Hopfield network, Hopfield network energy function, Boltzman machine, Elman networks, Jordan networks) and learning algorithms (back propagation through time, reccurent backpropagation), Network ensembles (committee machines, mixture of experts, convolutional neural networks), Spike neuron model and spiking neural network
  11. Algorithms for neural networks training in system identification, Input variable selection, Selection of NN structures suitable for identification and modeling of complex systems
  12. Regularization and validation of neural networks in system identification, Inverse control
  13. Instantaneous linearization
  14. Application of NN for compensation of system uncertainties
  15. Final exam

Study Programmes

University graduate
Audio Technologies and Electroacoustics (profile)
Elective Courses (1. semester)
Communication and Space Technologies (profile)
Elective Courses (1. semester)
Computational Modelling in Engineering (profile)
Elective Courses (1. semester)
Computer Engineering (profile)
Elective Courses (1. semester)
Computer Science (profile)
Elective Courses (1. semester)
Control Systems and Robotics (profile)
Elective Courses (1. semester) Elective Courses of the Profile (1. semester)
Data Science (profile)
Elective Courses (1. semester)
Electrical Power Engineering (profile)
Elective Courses (1. semester)
Electric Machines, Drives and Automation (profile)
Elective Courses (1. semester) Elective Courses of the Profile (1. semester)
Electronic and Computer Engineering (profile)
Elective Courses (1. semester)
Electronics (profile)
Elective Courses (1. semester)
Information and Communication Engineering (profile)
Elective Courses (1. semester)
Network Science (profile)
Elective Courses (1. semester)
Software Engineering and Information Systems (profile)
Elective Courses (1. semester)


(.), A. Cichocki, R. Unbehauen (1993). Neural Networks for Optimization and Signal Processing, John Wiley & Sons,
(.), M. Nørgaard, O. Ravn, N. K. Poulsen, L. K. Hansen (2000). Neural Networks for Modelling and Control of Dynamic Systems, Springer- Verlag, London,
(.), Ivan Petrović, Mato Baotić, Nedjeljko Perić (2015). Inteligentni sustavi upravljanja: neuronske mreže i genetički algoritmi, Sveučilište u Zagrebu Fakultet elektrotehnike i računarstva,
(.), Z. Kovacic, S. Bogdan, Fuzzy Controller Design: Theory and Applications, CRC Press,
(.), .,

Laboratory exercises

For students


ID 222566
  Winter semester
L3 English Level
L1 e-Learning
45 Lectures
10 Laboratory exercises

Grading System

87.5 Excellent
75 Very Good
62.5 Good
50 Acceptable