Anda ülevaade tehisintellekti ja masinõppe
põhiprintsiipidest ning arendada oskusi nende rakendamiseks tootmises. Üliõpilased omandavad
AI-põhiste mudelite koostamise ja rakendamise
oskused ennustavaks hoolduseks, defektide
tuvastamiseks, tootmise optimeerimiseks ja
riskianalüüsiks.

Students will gain an understanding of the
fundamental principles of artificial intelligence (AI)
and machine learning (ML), along with the skills
to apply these technologies in the manufacturing
sector. They will learn to design and implement
AI-based models and algorithms for predictive
maintenance, defect detection, production planning
and optimization, risk analysis.

Õppeaine läbinud üliõpilane:
- teab tehisintellekti ja masinõppe põhilisi meetodeid ning nende rakendamist kaasaegses tootmises;
- analüüsib ja lahendab tootmises esinevaid probleeme juhendatud ning juhendamata masinõppe meetodite abil;
- kasutab masinõppe tööriistu (nt MATLAB, Python, TensorFlow) praktiliste probleemide lahendamiseks, näiteks ennustava hoolduse või defektide tuvastamiseks;
- oskab rakendada globaalse optimeerimise meetodeid tootmisprotsesside efektiivsuse tõstmiseks;
- kasutab multikriteriaalseid otsustusmeetodeid praktiliste lahenduste väljatöötamisel (riskide hindamine, võtmenäitajate prioriseerimine, protsesside valik, jm.);
- teab tehisintellekti rakendamise eetilisi aspekte.

After completing this course, the student:
- knows the fundamental methods of artificial intelligence and machine learning, and their application in modern manufacturing;
- analyzes and solves problems in manufacturing using supervised and unsupervised machine learning methods;
- uses machine learning tools (e.g., MATLAB, Python, TensorFlow) to solve practical problems such as predictive maintenance or defect detection;
- is able to apply global optimization methods to enhance the efficiency of manufacturing processes;
- applies multi-criteria decision-making methods to develop practical solutions (e.g., risk assessment, prioritization of key indicators, process selection, etc.);
- knows the ethical aspects of AI implementation.

Õppeaine annab tervikliku ülevaate tehisintellekti rakendustest kaasaegses tootmises. Käsitletakse AI meetodeid ja tööriistu, sealhulgas masinõpet, süvaõpet ja tehisnärvivõrke, ning tarkvarasid, nagu MATLAB, Python ja TensorFlow. Masinõppe teemadesse kuuluvad juhendatud ja juhendamata õppemeetodid, sh otsustuspuud, tugivektorklassifitseerimine, regressioon ning klasterdamine. Õpitakse rakendama globaalse optimeerimise ja multikriteriaalsete otsustusmeetodite algoritme. Praktiliste juhtumuuringute kaudu õpitakse tehisintellekti rakendamist ennetavaks hoolduseks, toodete ja tootmisprotsesside optimeerimiseks ning riskide analüüsiks. Kursuses käsitletakse eetiliste aspektide hindamist.

The course provides a comprehensive overview of artificial intelligence (AI) applications in modern manufacturing. It covers AI methods and tools, including machine learning, deep learning and artificial neural networks, as well as software such as MATLAB, Python, and TensorFlow. Topics in machine learning include supervised and unsupervised learning methods, such as decision trees, support vector classification, regression, and clustering. The course also teaches the application of global optimization and multi-criteria decision-making algorithms.Through practical case studies, students will learn how to apply AI for predictive maintenance, product and production process optimization, risk assessment, and analysis. The course also addresses the evaluation of ethical considerations.

Teoreetiline test: 40%.
Praktiline projekt: 40%.
Osalemine ja kodutööd: 20%.

Theoretical test: 40%.
Practical project: 40%.
Participation and homework: 20%.

AI algoritmide koostamine ja rakendamine.
Juhtumuuringute läbiviimine.
Multikriteriaalsete otsustusmeetodite rakendamine
riskide analüüsiks ja võtmeväärtuste prioriseerimiseks.

Development and application of AI algorithms
Implementation of use-cases.
Application of mulricriteria decision making methods
for risk analysis and priorization of the
key performance indicators.

George Chryssolouris , Kosmas Alexopoulos , Zoi Arkouli, 2023, A Perspective on Artificial Intelligence in Manufacturing.
Edited by John Soldatos, 2024, Artificial Intelligence in Manufacturing: Enabling Intelligent, Flexible and Cost-Effective Production Through AI (Open access).
Edited by Jaydip Sen, Sidra Methab, 2021, Machine Learning - Algorithms, Models and Applications (Artificial Intelligence)
Edited by Masoud Soroush, Richard D Braatz, 2024, Artificial Intelligence in Manufacturing: Applications and Case Studies
Edited by Kaushik Kumar, Divya Zindani, J. Paulo Davim, 2024, Artificial Intelligence in Mechanical and Industrial Engineering).
Edited by by Ganesh M. Kakandikar, Dinesh G. Thakur, 2020, Nature-Inspired Optimization in Advanced Manufacturing Processes and Systems.
Edited by Kim Phuc Tran, 2023, Artificial Intelligence for Smart Manufacturing: Methods, Applications, and Challenges.
Alaa Khamis, 2024, Optimization Algorithms: AI Techniques for Design, Planning, and Control Problems.
Anand J. Kulkarni and Suresh Chandra Satapathy, 2020, Optimization in Machine Learning and Applications.
Vadim Smolyakov, 2024, Machine Learning Algorithms in Depth.
Kejriwal, 2022, Artificial Intelligence for Industries of the Future.

Jüri Majak, täisprofessor tenuuris (EM - mehaanika ja tööstustehnika instituut)