SZSasa Zivanovic

Sasa Zivanovic

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Sasa Zivanovic has a total of 50 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Determination of Backlash Value in the Feed Motion System of Machine Tools Using Shallow Neural Networks

    by Slobodan Tabakovic, Milan Zeljkovic, Alexander Budimir, Sasa Zivanovic

    This paper presents research aimed at detecting and quantifying backlash in the feed motion subsystem of machine tools using positioning accuracy test results. By applying shallow neural networks, we not only estimate backlash magnitude but also analyse the impact of key parameters on its occurrence. This approach enables continuous, data-driven monitoring and prediction of backlash variation while reducing machine tool calibration time in industrial settings. The experimental study used two standard motion methods while monitoring machine and ambient temperature, atmospheric pressure, and humidity. The results show how experimental parameters affect detected backlash. A feed-forward neural network predicts current backlash at specific measurement points. The results demonstrate high accuracy in backlash estimation, significantly simplifying machine calibration during maintenance and providing a foundation for real-time error compensation.

  • Open Access

    Parametric programs of group technology for the production of tool parts for plastic injection molding on a CNC milling machine

    by Goran Vasilić, Saša Živanović, Julija Crnobrnja-Maletić, Ljubomir Nešovanović

    Creating G-code programs for CNC machines intended for any machining process requires certain resources such as time, but also a certain level of knowledge and training of programmers and operators of CNC machines. With the aim of optimally using the existing resources of a production facility, within this work, parametric programs intended for CNC milling machines were analyzed. The analyzed parametric programs were compiled so that they represent part of the group's technology for the production of plastic injection tool parts. The parametric programs themselves are generalized and therefore universal and can be used for the implementation of a specific operation, regardless of the values of the geometric quantities that describe the shape and size of the machine part. For each of the displayed parametric programs, appropriate explanations are given through sketches, algorithms and selected parts of the program. Verification of the analyzed programs was done in the LinuxCNC software system for programming and controlling CNC machines, which confirmed their correctness.

  • Open Access

    Determination of Backlash Value in the Feed Motion System of Machine Tools Using Shallow Neural Networks

    by Slobodan Tabakovic, Milan Zeljkovic, Alexander Budimir, Sasa Zivanovic

    This paper presents research aimed at detecting and quantifying backlash in the feed motion subsystem of machine tools using positioning accuracy test results. By applying shallow neural networks, we not only estimate backlash magnitude but also analyse the impact of key parameters on its occurrence. This approach enables continuous, data-driven monitoring and prediction of backlash variation, while reducing machine tool calibration time in industrial settings. The experimental study followed ISO 230-2, using two standard motion methods while monitoring machine and ambient temperature, atmospheric pressure, and humidity. The results show how experimental parameters affect detected backlash. A feed-forward neural network predicts current backlash at specific measurement points. The results demonstrate high accuracy in backlash estimation, significantly simplifying machine calibration during maintenance and providing a foundation for real-time error compensation.

  • COMPARISON OF LASER INTERFEROMETER SYSTEMS FOR MEASURING POSITIONAL ACCURACY OF MACHINE TOOLS

    by Alexander Buda Budimir, Slobodan Tabakovic, Milan Zeljkovic, Saša Živanovic, Zoran Dimic, Belgrade Lola Institut

    Laser interferometers have become indispensable tools in the high-precision calibration of machine tools, offering sub-micron resolution and enhanced measurement reliability. Since the introduction of stabilized helium–neon (He–Ne) lasers in the 1960s, manufacturers like Hewlett-Packard (HP), Renishaw, and Lasertex have developed systems with increasingly advanced capabilities. This paper presents a technical and historical comparison of three key interferometric systems: HP’s 5525A, Renishaw’s XL-80, and Lasertex’s HPI-3D. The analysis includes specifications such as laser stability, resolution, environmental compensation, and dynamic measurement capabilities. The HP 5525A, although historically significant, lacks modern portability and software integration. In contrast, Renishaw’s XL-80 offers compactness, advanced environmental compensation, and compatibility with international metrology standards. Lasertex’s HPI-3D introduces next-generation capabilities, such as real-time vibration analysis, nanometric resolution, and full 3D geometric evaluation. The comparative findings suggest a clear technological evolution toward higher precision, modularity, and software-driven diagnostics in laser interferometry.

  • PROGRAMMING AND VERIFICATION OF MILLING OPERATIONS FOR CNC MACHINES WITH HORIZONTAL ROTARY AXIS

    by Sasa Živanovic, Julija Maletic, Belgrade Lola Institut, Nikola Vorkapic, Nikola Slavkovic, Zoran Dimic, Radovan Puzovic

    The paper analyses the programming of CNC milling machines with horizontal rotary axis. These are usually machines for rapid prototyping of rotating symmetrical and/or asymmetrical parts. The paper analyses the available programming software, which can be one of the standard CAD/CAM systems or a specialized CAM system. In addition to the analysis of the programming method procedure, the verification of the program by simulating the removal of material and simulating the operation of a virtual machine according to a given program was also considered. Verification of programming methods was realized by machining several characteristic parts, on developed 3-axis desktop CNC milling machine - Multiprodesk, that has two translational and one horizontal rotary axis.

  • CNC SIMULATOR BASED ON LINUXCNC CONTROL AND PROGRAMMING SYSTEM

    by Belgrade The Academy Of Applied Studies Polytechnic, Goran Vasilic, Milan Milutinovic, Saša Živanovic, Zoran Dimic, Belgrade Lola Institut

    This work presents a CNC simulator that was created based on the need to design and form a working environment within which training of operators and programmers of CNC machines will be carried out in an economically profitable way. The CNC simulator is based on a Raspberry PI 5 microcomputer and LinuxCNC open-source software system intended for control and programming of CNC machines and industrial robots. The LinuxCNC software system was configured according to the set requirements and current needs. With the control system configured in this way, two working environments were formed that are currently used in the realization of laboratory exercises of the teaching process of the higher education institution. In the framework of the paper, the created working environments are described, and in the conclusion, the observations obtained by analyzing the results achieved using the CNC simulator are presented.

  • FROM MODULAR LEGACY TO OPEN INNOVATION: EVOLUTION OF THE LOLA CNC SYSTEM ARCHITECTURE

    by Belgrade Lola Institut, Zoran Dimic, Andrija Devic, Saša Živanovic, Aleksa Krošnjar, Stevan Parojcic, Dragan Pavlovic

    This paper provides a comprehensive overview of the development, technical architecture, and practical applications of the LOLA 30 CNC system, a landmark achievement in domestic industrial innovation in the field of numerical control. Developed in the early 1980s by the LOLA Institute, the system is examined within its historical context, with particular attention to its architectural features and its broader impact on industrial autonomy and engineering education. Special emphasis is placed on its modular design, integration with the PA512 programmable logic controller, and representative use cases. The paper also presents a comparative analysis between the LOLA 30 CNC and the modern LOLA ROSA CNC system, which is based on open-architecture hardware and software. Key technological advancements of the new system, particularly in terms of reconfigurability and distributability, are highlighted.

  • Open Access

    Comunity for uniquely management of production and technological resources: JUPITER system and conference

    by Saša T. Živanović, Radovan M. Puzović

    This paper presents a reminder and overview of the duration of the Community for the uniquely management of production and technological resources, which is better known as the JUPITER system. In order to scientifically and expertly verify the results of research projects and determine the future development directions of the JUPITER system, the JUPITER conference was launched as a scientific and professional gathering of members of the Community and other members of the the metalworking industry, scientific research institutions and faculties.