Course detail
Intelligent Manufacturing Systems
FSI-GIS Acad. year: 2020/2021 Summer semester
Progress in manufacturing and in computer technology and especially in their connection brings new approaches in the design of products and their realization in manufacturing processes and production systems. They are currently expressed in the concept of Industry 4.0, which implies that the traditional tools necessary activities in the engineering manufacture are insufficient for the future.The aim of the course is to familiarise students with new approaches and methods:
Manufacturing System as an intelligent system, basic knowledge of artificial intelligence, expert systems, neural networks, methods based on the use of knowledge bases in the manufacturing systems. It is shown how to apply these methods and thereby bring a new quality for each activity in the production and manufacturing system – design of products, process planning, group technology, design of the structure of the manufacturing system, scheduling and production control, management of production quality.
Language of instruction
Czech
Number of ECTS credits
4
Supervisor
Learning outcomes of the course unit
Students will be made familiar with selected methods applied for creating and solution of mathematical models in different subsystems of a manufacturing system. Students will be provided with necessary information and will gain practical experience with algorithms used for these methods, as well as methods of artificial intelligence (expert systems, neural nets).
Prerequisites
Basic knowledge of mathematics and fundamentals of computer science.
Planned learning activities and teaching methods
The course is taught through lectures explaining the basic principles and theory of the discipline. Exercises are focused on practical topics presented in lectures.
According to the possibility of teaching can be organized lectures for students by practitioners and excursions to companies focused on activities related to the course content.
Assesment methods and criteria linked to learning outcomes
The course consists of exercises and lectures. Exercise is completed by credit (awarded in the 13th week). To obtain it is required 100% participation in exercises and activity in exercises. Students will work out the individual work in the prescribed range and quality. Based on the quality of the work in the exercise, the student earns up to 30 points for the exam The work must be submitted in writing and checked and recognized by the teacher. The test is realized by written test, student can get up to 70 points from this test, where 30 points from exercises. Evaluation of the test result is given by the ECTS grading scale.
Aims
The aim of the course is to familiarise students with new modern methods and tools used for design and control of manufacturing systems with respect to automated manufacturing. The emphasis is placed on methods based on application of knowledge base systems and optimisation procedures. Also discussed are the methods based on application of basic principles of AI.
Specification of controlled education, way of implementation and compensation for absences
Attendance at obligatory lessons is checked and only substantial reasons of absence are accepted. Missed lessons can be substituted for via solution of extra exercises.
The study programmes with the given course
Programme M2I-P: Mechanical Engineering, Master's
branch M-VSR: Production Machines, Systems and Robots, compulsory-optional
Type of course unit
Lecture
26 hours, optionally
Syllabus
1. Fundamentals of artificial intelligence methods, basic approaches, difference from algorithmic approaches to problem solving.
2. Neural networks, their basic principles and applications in the area of production systems
3. Classification methods, types of classifiers, choice of predictors, fuzzy logic.
4. Parameter optimization using evolutionary algorithms.
5. Knowledge-based systems – knowledge representation, basic methods.
6. Algorithms for travel planning.
7. Credit
Computer-assisted exercise
13 hours, compulsory
Syllabus
1. Data classification, choice of predictors, comparison of methods
2. Neural networks in the context of the production process
3. Convolutional neural networks
4. Optimization using evolutionary algorithms
5. IoT and cloud systems
6. Fuzzy logic in production system
7. Production process visualization, SCADA / HMI demonstration
8. Production process visualization, SCADA / HMI demonstration
9. Introduction to expert systems,
10. Solving problems with expert systems, application examples.
11. Algorithms for travel planning.
12. Evaluation of final theses
13. Credit