• Semester 4, position 4

The aim of the course is to develop student's ability to model and analyze real systems using discrete event simulation along with the application of models, analysis of simulation results and comparison of alternative solutions. Artificial intelligence will be understood through models, the structure of intelligent agents and machine learning. By using of simulation and software tools, students will get knowledge for application of artificial neural networks.

After the course, the students will be able to: • develop models of manufacturing systems and other discrete systems, • implement the model by using adequate simulation software, • verify the built model, • evaluate and analyze simulation outputs and compare alternative solutions, • give suggestions for the optimization of real systems, • choose methods based on the application of artificial neural networks for solving engineering problems along with modeling of optimal structure, • use software for the simulation of artificial neural networks and analyze and present obtained results.

Introduction to discrete event simulation. What is a simulation, when it is applicable to use simulation, classification of models, types of simulation, steps in simulation, study, advantages/disadvantages of simulation study. Concept of discrete event simulation, list processing. Simulation package AnyLogic. Application of simulation. Verification and evaluation of simulation models, analysis of output data, and comparison of alternative designs of systems. Simulation of manufacturing systems. Artificial intelligence - definitions, basic concepts and paradigms. Knowledge bases, knowledge acquisition, models of learning, searching tree, development of soft-computing, autonomous systems. Structure of artificial neural network (ANN), neuron - processing element, transfer (activation) function. ANN models, learning algorithms, uncertainty of system, non-linearity, estimation, clustering. Application of ANN.

General principles and simulation examples. Simulation of single-chanel systems, and event handling. Introduction to softwares for modeling and analysis of real systems based on discrete event simulation (lab work). Artificial neural networks in intelligent systems. Introduction to softwares for simulation of artificial neural networks (lab work). Recognition systems, simulation of systems of artificial neural networks, simulation of mobile robot motion (examples). Homeworks and seminar works dealing with the simulation of real systems and application of artificial neural networks (recognition systems - robot vision; recognition of manufacturing features of mechanical parts; recognition of objects for grasping - robot vision).

Defined by curriculum of study programme/module.

[1] B. Babic, COMPUTER INTEGRATED SYSTEMS AND TECHNOLOGIES (in Serbian), Faculty of Mechanical Engineering, 2017; [2] Z. Miljkovic, SYSTEMS OF ARTIFICIAL NEURAL NETWORKS IN PRODUCTION TECHNOLOGIES (in Serbian), Series IMS, Vol. 8, University of Belgrade, Faculty of Mechanical Engineering, 2003; [3] Z. Miljkovic, D. Aleksendric, ARTIFICIAL NEURAL NETWORKS – solved examples with short theory background (in Serbian), Textbook, University of Belgrade, Faculty of Mechanical Engineering, 2009; [4] B. Babic, Z. Miljkovic, M.Petrovic, Handouts, University of Belgrade, Faculty of Mechanical Engineering, 2023; [5] B. Babic, Z. Miljkovic, M. Petrovic, Software "Moodle" for distance learning (http://147.91.26.15/moodle/), University of Belgrade, Faculty of Mechanical Engineering, 2023; [6] B. Babic, Z. Miljkovic, M. Petrovic, Website for Computer simulation and artificial intelligence (http://cent.mas.bg.ac.rs/nastava/ksivi_mo/KSiVI.html), University of Belgrade, Faculty of Mechanical Engineering, 2023; [7] AnyLogic simulation software; [8] Z. Miljkovic, Software packages for simulation of artificial neural networks - BPnet, ART Simulator; Laboratory CeNT website: http://cent.mas.bg.ac.rs/nastava/ksivi_mo/KSiVI.html, University of Belgrade, Faculty of Mechanical Engineering;

Total assigned hours: 75

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

Auditory exercises: 0
Laboratory exercises: 22
Calculation tasks: 0
Seminar paper: 8
Project: 0
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: 6
Review and grading of the project: 0
Test: 0
Test: 4
Final exam: 5

Activity during lectures: 15
Test/test: 20
Laboratory practice: 0
Calculation tasks: 0
Seminar paper: 35
Project: 0
Final exam: 30
Requirement for taking the exam (required number of points): 30

B.Babic, Computer Integrated Manufacturing Systems and Processes (in Serbian), University of Belgrade – Faculty of Mechanical Engineering, Belgrade, 2017. ISBN 978-86-7083-960-1; Z.Miljkovic, M.Petrovic, INTELLIGENT MANUFACTURING SYSTEMS-with robotics and artificial intelligence backgrounds (in Serbian), University of Belgrade–Faculty of Mechanical Engineering, Belgrade, 2021.; J. Banks, J. S. Carson, B. L. Nelson and D. M. Nicol (2005), DISCRETE EVENT SYSTEM SIMULATION, 4th Ed., Pearson Education International Series; ISBN 9780131446793; E. Alpaydin, (2004) INTRODUCTION TO MACHINE LEARNING, The MIT Press, Cambridge, Massachusetts London, England; ISBN 9780262012119; R. R. Murphy, (2000) INTRODUCTION TO AI ROBOTICS, A Bradford Book, The MIT Press, Cambridge, Massachusetts London, England; ISBN 0-262-13383-0