Course detail
Intelligent Manufacturing Systems
FSI-GIS Acad. year: 2027/2028 Winter semester
Progress in production and computer technology, and in particular in their interconnection, brings new approaches in the fields of product design and their realisation in production processes and production systems. These are currently expressed in the Industry 4.0 concept, from which it follows that traditional tools for the necessary activities in the field of engineering production are no longer sufficient for this development.
Students are therefore introduced to new approaches and methods: the conception of a production system as an intelligent system, the fundamentals of artificial intelligence, classification methods and fuzzy logic, optimisation by means of evolutionary algorithms, artificial neural networks, and methods employing knowledge bases.
It is shown how to apply these methods and thereby bring new quality to the individual activities in a production system – product design and construction, technological production preparation, group technology, production scheduling and control, and production quality control. Attention is also paid to path-planning algorithms and their use in production and robot control.
The methods of classification, evolutionary optimisation and fuzzy sets are developed in this course to the depth of parameter design and evaluation of results; their introduction and basic application are the content of the course Data Processing.
Language of instruction
Czech
Number of ECTS credits
4
Supervisor
Entry knowledge
The student is able to describe the principle of Boolean algebra and the fundamentals of mathematical logic. The student is able to explain the concepts of vector, matrix, derivative and integral of a function of one and several variables, and the concepts of probability and conditional probability.
The student is able to write an algorithm in a higher programming language, for example Python, C or MATLAB, and to work with numerical computation libraries. The student is able to describe the basic principles of a relational database and the basic methods of data classification.
Rules for evaluation and completion of the course
The course is completed by a course credit and an examination.
Course credit requirements
Compulsory attendance at computer-aided exercises. Tolerance of one excused absence; the method of making up for missed instruction shall be determined by the teacher.
Continuous fulfilment of partial tasks: data classification, fuzzy controller, evolutionary optimisation, expert system and path planning.
Elaboration of a semester project in the range of 10 to 15 standard pages including a functional implementation, focused on the design of intelligent control of a selected partial process of a production system. The project comprises the choice of method, data preparation, implementation and evaluation of results. It shall be submitted no later than in the 12th teaching week and shall be defended in the 12th teaching week.
A maximum of 0 to 15 points may be awarded for the partial tasks and 0 to 15 points for the semester project and its defence, i.e. 0 to 30 points in total.
The course credit is awarded upon fulfilment of the attendance requirement; the score achieved may be as low as 0 points. The course credit is awarded in the 13th teaching week; the content of the 13th teaching week is the verification of the results of the exercises and the award of the course credit.
Examination
The examination takes the form of a written test covering the areas of artificial intelligence methods, classification, fuzzy logic, evolutionary algorithms, knowledge bases and path planning. A maximum of 0 to 70 points may be obtained from the test.
Only a student who has been awarded the course credit may sit the examination.
Final classification
The overall assessment consists of the points from the exercises (0 to 30 points) and the points from the examination (0 to 70 points), i.e. 100 points at most.
Classification scale: A 90 to 100 points, B 80 to 89 points, C 70 to 79 points, D 60 to 69 points, E 50 to 59 points, F 0 to 49 points.
Aims
The graduate is able to:
- explain the difference between the algorithmic and the knowledge-based approach to problem solving and to place artificial intelligence methods in the context of Industry 4.0,
- select a suitable classification method for an assigned task, prepare predictors and compare the results of alternative methods,
- design and implement a fuzzy controller for an assigned partial process of a production system,
- optimise the parameters of an assigned task by means of an evolutionary algorithm and evaluate the quality of the solution obtained,
- design the structure of a simple knowledge base and demonstrate the inference of an expert system,
- implement a path-planning algorithm in an assigned discretised environment,
- defend the choice of method and interpret the results obtained in a professional discussion.
The study programmes with the given course
Programme N-VSR-P: Production Machines, Systems and Robots, Master's, compulsory-optional
Type of course unit
Lecture
13 hours, optionally
Syllabus
1.- 2. Fundamentals of artificial intelligence methods, basic approaches, differences from algorithmic approaches to problem-solving.
3. – 4. Classification methods, types of classifiers, choice of predictors, fuzzy logic.
5. – 6. Parameter optimization using evolutionary algorithms.
7. – 8. Neural networks, their basic principles, and applications in the area of production systems
9. – 10. Knowledge-based systems – methods of knowledge representation, basic methods.
11. – 12. Algorithms for travel planning.
13. Credit
Computer-assisted exercise
26 hours, compulsory
Syllabus
1. Data classification, choice of predictors, comparison of methods
2. Fuzzy logic in a manufacturing system
3. IoT and cloud systems
4. Convolutional neural networks
5. Optimization using evolutionary algorithms
6. Introduction to expert systems,
7. Solving problems with expert systems, examples of applications.
8. Visualization of the production process, demonstration of SCADA/HMI
9. Visualization of the production process, SCADA/HMI demonstration
10. Work on the assigned project
11. Work on the assigned project
12. Evaluation of final project
13. Credit