Module also offered within study programmes:
General information:
Name:
Soft computing in modeling and control
Course of study:
2019/2020
Code:
RIME-2-220-WM-s
Faculty of:
Mechanical Engineering and Robotics
Study level:
Second-cycle studies
Specialty:
Wytwarzanie mechatroniczne
Field of study:
Mechatronic Engineering
Semester:
2
Profile of education:
Academic (A)
Lecture language:
English
Form and type of study:
Full-time studies
Responsible teacher:
dr hab. inż. Smoczek Jarosław (smoczek@agh.edu.pl)
Module summary

The course is intended to provide the students with the knowledge and understanding of computational intelligence and soft computing concepts and their applicability to solve the real-world decision-making, modeling and control problems. The selected soft computing concepts and techniques, including fuzzy logic, artificial neural network, evolutionary computing, swarm intelligent and their hybrids are introduced and discussed with application examples.

Description of learning outcomes for module
MLO code Student after module completion has the knowledge/ knows how to/is able to Connections with FLO Method of learning outcomes verification (form of completion)
Skills: he can
M_U001 Student is able to identify, select and implement a suitable soft computing method to solve the problem. Activity during classes,
Test,
Completion of laboratory classes
M_U002 The student is able to select and apply the supervised or unsupervised techniques for fuzzy model/controller identification/design. Activity during classes,
Completion of laboratory classes,
Test
M_U003 Student is able to apply the software tools in Matlab program to implement the soft computing methods for modeling and control system design. Activity during classes,
Completion of laboratory classes,
Test
Knowledge: he knows and understands
M_W001 Student has knowledge about the soft computing techniques and their applicability to solve the real word problems. Activity during classes,
Test
M_W002 The student has knowledge in modeling of dynamic systems and control system design using soft computing methods: knowledge engineering, fuzzy logic, artificial neural networks, evolutionary algorithms, and their hybrids. Activity during classes,
Test,
Execution of laboratory classes
Number of hours for each form of classes:
Sum (hours)
Lecture
Audit. classes
Lab. classes
Project classes
Conv. seminar
Seminar classes
Pract. classes
Zaj. terenowe
Zaj. warsztatowe
Prace kontr. przejść.
Lektorat
45 30 0 15 0 0 0 0 0 0 0 0
FLO matrix in relation to forms of classes
MLO code Student after module completion has the knowledge/ knows how to/is able to Form of classes
Lecture
Audit. classes
Lab. classes
Project classes
Conv. seminar
Seminar classes
Pract. classes
Zaj. terenowe
Zaj. warsztatowe
Prace kontr. przejść.
Lektorat
Skills
M_U001 Student is able to identify, select and implement a suitable soft computing method to solve the problem. + - + - - - - - - - -
M_U002 The student is able to select and apply the supervised or unsupervised techniques for fuzzy model/controller identification/design. - - + - - - - - - - -
M_U003 Student is able to apply the software tools in Matlab program to implement the soft computing methods for modeling and control system design. - - + - - - - - - - -
Knowledge
M_W001 Student has knowledge about the soft computing techniques and their applicability to solve the real word problems. + - - - - - - - - - -
M_W002 The student has knowledge in modeling of dynamic systems and control system design using soft computing methods: knowledge engineering, fuzzy logic, artificial neural networks, evolutionary algorithms, and their hybrids. + - - - - - - - - - -
Student workload (ECTS credits balance)
Student activity form Student workload
Summary student workload 128 h
Module ECTS credits 5 ECTS
Udział w zajęciach dydaktycznych/praktyka 45 h
Preparation for classes 15 h
przygotowanie projektu, prezentacji, pracy pisemnej, sprawozdania 41 h
Realization of independently performed tasks 25 h
Examination or Final test 2 h
Module content
Lectures (30h):

The general program of lecture:

  1. Introduction to artificial intelligence, computational intelligence and soft computing. Review of the main soft computing components and their hybrids. Examples of artificial applications to real world problems.
  2. Introduction to fuzzy logic, fuzzy set theory.
  3. Fuzzy approximate reasoning. Mamdani inference system.
  4. TS fuzzy inference systems. Analytical methods in fuzzy modeling and control.
  5. Fuzzy logic control. Knowledge-based and analytical methods of fuzzy controller design.
  6. Type-2 fuzzy logic. Interval type-2 fuzzy sets and logic.
  7. Fundamentals of artificial neural network.
  8. Multilayer perceptrons and backpropagation learning algorithm.
  9. Data-based fuzzy modeling (machine learning, fuzzy clustering).
  10. Adaptive neuro-fuzzy inference system (Matlab examples).
  11. Evolutionary computation. Simple genetic algorithm.
  12. Real coded genetic algorithm, evolutionary strategies.
  13. Genetic fuzzy systems.
  14. Swarm intelligence.

Laboratory classes (15h):

Matlab based:
- implementation of soft computing techniques (fuzzy logic, genetic algorithms, artificial neural network) in laboratory exercises and assignments,
- implementation of a fuzzy rule-based system using Matlab language,
- control system design using classical and soft computing-based techniques,
- fuzzy model identification using supervised and unsupervised methods (genetic fuzzy system, neuro-fuzzy model, fuzzy clustering algorithms).

Additional information
Teaching methods and techniques:
  • Lectures: The lectures are in the form of multimedia presentations.
  • Laboratory classes: Students develop problem-solving skills by doing the lab exercises that correspond to the material given in the lectures.
Warunki i sposób zaliczenia poszczególnych form zajęć, w tym zasady zaliczeń poprawkowych, a także warunki dopuszczenia do egzaminu:

Condition of gaining credit:
Laboratory classes: participation in classes, completion of all laboratory exercises (individual/team reports)
Condition to take exam: passing laboratory part (reports) and small project work

Participation rules in classes:
  • Lectures:
    – Attendance is mandatory: No
    – Participation rules in classes: Attendance to the lecture is not obligatory but recommended, and rewarded with the student’s final grade being raised.
  • Laboratory classes:
    – Attendance is mandatory: Yes
    – Participation rules in classes: Student should study the material given in the lectures that will be practiced during the lab classes. Condition of gaining credit: participation in classes, completion of all laboratory exercises (individual/team reports).
Method of calculating the final grade:

Final grade: the weighted average of grades from examination (40%), laboratory part (40%), small project (20%)

Sposób i tryb wyrównywania zaległości powstałych wskutek nieobecności studenta na zajęciach:

Students who have missed class should contact with the instructor (during his consultation hours or next class meeting) and ask him how to make up missed work.

Prerequisites and additional requirements:

Prerequisites and additional requirements not specified

Recommended literature and teaching resources:

J.-S. R. Jang, C.-T. Sun, E. Mizutani: “Neuro-Fuzzy and Soft Computing, A Computational Approach to
Learning and Machine Intelligence”, Pentice Hall, Upper Saddle River, NJ, 1997.
J.M. Mendel: “Uncertain rule-based fuzzy logic systems. Introduction and new directions”, Pentice Hall, Upper Saddle River, NJ, 2001.

Scientific publications of module course instructors related to the topic of the module:

1. Smoczek J., Szpytko J., Particle swarm optimization-based multivariable generalized predictive control for an overhead crane, IEEE-ASME Transactions on Mechatronics, 22 (1), pp. 258-268, 2017.
2. Smoczek J., Experimental verification of a GPC-LPV method with RLS and P1-TS fuzzy-based estimation for limiting the transient and residual vibration of a crane system, Mechanical Systems and Signal Processing, vol. 62-63, pp. 324-340, 2015.
3. Smoczek J.: Fuzzy crane control with sensorless payload deflection feedback for vibration reduction. Mechanical System and Signal Processing 46 (1), pp. 70-81, 2014.
4. Smoczek J., Szpytko J.: Evolutionary algorithm-based design of a fuzzy TBF predictive model and TSK fuzzy anti-sway crane control system. Engineering Applications of Artificial Intelligence 28, pp. 190-200, 2014.
5. Smoczek J. Soft computing methods in overhead travelling crane control. Publishing House of Sustainable Technologies – National Research Institute, Radom 2013.
6. Smoczek J.: Interval arithmetic-based fuzzy discrete-time crane control scheme design. Bulletin of the Polish Academy of Sciences – Technical Sciences 61 (4), pp. 863-870, 2013.
7. Smoczek J.: Evolutionary optimization of interval mathematics-based design of TSK fuzzy controller for anti-sway crane control. International Journal of Applied Mathematics and Computer Science 23 (4), pp. 749-759, 2013.

Additional information:

None