• Dizajn u mašinstvu, Semester 2, position 3

The aim of the course is to train the students to make decisions in the process of product development and design by using mathematical-algorithm-based procedures and artificial intelligence techniques. Development of students' creative abilities in improving technical/technological characteristics of a product using methods based on conceptual design points out the optimum decision function based on intelligent agents.

Students' learning outcomes of this course are: • The complex use of IC technologies in decision-making. • The implementation of developed software (MATLAB, BPnet, ART Simulator, AnyLogic, TRIZ, Flexy) in solving typical technological problems within decision-making methods based on paradigms of artificial intelligence. • Autonomous selection of the methods based on application of artificial neural networks and genetic algorithms in seeking the optimal solution in the process of product development. • Understanding the interaction of soft and hard real-time subsystems of mobile robot in decision-making during exploring by using reconfiguration of physical structure and intelligent behaviour programming in MATLAB. • Capability for team work.

Introduction to the theory of decision-making; intelligent systems. Systems for design and selection of solutions. Hybrid intelligent manufacturing systems; decision-making methods based on intelligent agents. Decision-making based on paradigms of artificial intelligence. Artificial neural networks; neuron - a processing element, transfer function (activation), architecture, learning algorithms. Application of artificial neural networks in decision-making. Genetic algorithms. Manufacturability of the product, process planning optimization. Intelligent machines and decision-making. Development of advanced technologies for the 21st century.

Conceptual design and decision-making variables (selected examples). Analysis of typical manufacturing problems in domain of decision-making (laboratory work). Algorithms of machine learning and knowledge-based presentation - decision tree induction. Software for simulation of artificial neural networks (laboratory work). Manufacturability of the product - design parameters based on material flow for chosen manufacturing process (programming in MATLAB); application of genetic algorithms in optimization (selected examples). Machine learning of material flow for chosen manufacturing process. Intelligent machines and decision-making (programming in MATLAB) - reconfigurable mobile robots and machine learning (laboratory work). Examples of conceptual designed products with optimal performances, pointing out the application of advanced production technologies (project activities). Project design (design parameters, searching performances, and defining of a decision matrix and decision function).

Defined by Curriculum.

[1] Z. Miljković, M.M. Petrović, INTELLIGENT MANUFACTURING SYSTEMS – with excerpts from robotics and artificial intelligence, Textbook, XXVIII+409 p., UB - Faculty of Mechanical Engineering in Belgrade, 2021 (I edition), 18.1 /In Serbian/ [2] Z. Miljković, D. Aleksendrić, ARTIFICIAL NEURAL NETWORKS – solved examples with theoretical background (2nd ed.), Textbook, UB - Faculty of Mechanical Engineering in Belgrade, 2018, 18.1 /In Serbian/ [3] Z. Miljković, SYSTEMS OF ARTIFICIAL NEURAL NETWORKS IN PRODUCTION TECHNOLOGIES, Monograph book within the Series Intelligent Manufacturing Systems, Vol. 8, UB - Faculty of Mechanical Engineering in Belgrade, 2003, 18.1 /In Serbian/ [4] V.R. Milačić, MANUFACTURING SYSTEMS DESIGN THEORY, Monograph book within the Series Intelligent Manufacturing Systems, Vol. 2, UB - Faculty of Mechanical Engineering in Belgrade, 1987, 18.1 /In Serbian/ [5] Z. Miljković, M.M.Petrović, Handouts, UB - Faculty of Mechanical Engineering in Belgrade, 2022, 18.1 /In Serbian/ [6] Z. Miljković, M.M.Petrović, Software "Moodle" for distance learning (http://147.91.26.15/moodle/), UB - Faculty of Mechanical Eng. in Belgrade, 2022, 18.13 [7] Z. Miljković, M.M.Petrović, Website for Decision-making methods (http://cent.mas.bg.ac.rs/), UB - Faculty of Mechanical Engineering in Belgrade, 2022, 18.13 [8] Z. Miljković, Software packages for simulation of artificial neural networks - BPnet, ART Simulator, MATLAB; Laboratory CeNT website: http://cent.mas.bg.ac.rs/, UB - Faculty of Mechanical Eng. in Belgrade, 18.13 [9] Laboratory mobile robots (PAL-TIAGo - Mobile Manipulator Robot with stereo vision system; K-Team's Khepera II mobile robot with gripper and camera; LEGO Mindstorms NXT and EV3 Sets of reconfigurable mobile robots equipped with sensors and micro-controllers), Laboratory CeNT, UB - Faculty of Mechanical Eng. in Belgrade, 18.12 [10] Laboratory model of designed manufacturing system, Laboratory CeNT, UB - Faculty of Mechanical Eng. in Belgrade, 18.12

Total assigned hours: 75

New material: 20
Elaboration and examples (recapitulation): 10

Auditory exercises: 2
Laboratory exercises: 16
Calculation tasks: 0
Seminar paper: 0
Project: 12
Consultations: 0
Discussion/workshop: 0
Research study work: 0

Review and grading of calculation tasks: 0
Review and grading of lab reports: 0
Review and grading of seminar papers: 0
Review and grading of the project: 4
Test: 2
Test: 4
Final exam: 5

Activity during lectures: 10
Test/test: 25
Laboratory practice: 0
Calculation tasks: 0
Seminar paper: 0
Project: 35
Final exam: 30
Requirement for taking the exam (required number of points): 30

Y. Hatamura, (2006) DECISION-MAKING IN ENGINEERING DESIGN, 265 pp. (ISBN 9781846282614), Springer Science & Business Media, Printed in Germany. ; J.N. Siddall, (1972) ANALYTICAL DECISION-MAKING IN ENGINEERING DESIGN, 431 pp. (ISBN 978-0130345387), Prentice-Hall, Inc. Englewood Cliffs, New Jersey.; Z.Miljković, M.M.Petrović, (2021) INTELLIGENT MANUFACTURING SYSTEMS – with excerpts from robotics and AI, Textbook (In Serbian), XXVIII+409 pp. (ISBN 978-86-6060-071-6), UB-Faculty of Mechanical Eng.; E. Alpaydin, (2010) INTRODUCTION TO MACHINE LEARNING, 2nd Edition, 400 pp. (ISBN 9780262012119), The MIT Press, Cambridge, England.; R.R. Murphy, (2019) INTRODUCTION TO AI ROBOTICS, 2nd Edition, 648 pp. (ISBN 9780262038485), The MIT Press, Cambridge, Massachusetts London, England.