Nikola Petrović

Mr. Nikola Petrović

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2024
Verified
Conference Paper
Open access
PDF file
HJHetham Omer Mohamed Jama
Hetham Omer Mohamed Jama
VBVesna Spasojevic Brkic
Vesna Spasojevic Brkic
NPNikola Petrović
Nikola Petrović
UBUglješa Srbislav Bugarić
Uglješa Srbislav Bugarić
MPMartina Perišić
Martina Perišić
An appropriate maintenance strategy can maximize a machine's capacity and economic lifetime and also produce yearly savings of several million euros. That being said, a risk assessment approach can help companies identify the systemic bottlenecks that are interfering with their development and cut a large portion of their profit each year. This paper presents a hybrid reliability-Failure Mode and Effects Analysis (FMEA) methodology to assess the risk associated with belt conveyor systems, particularly in open-pit mining environments. By integrating severity, occurrence, and detection indicators, a 3D risk assessment matrix was developed. Using data from conveyor system maintenance, including downtime and failure occurrences, chi-square tests to analyze system reliability and mean downtime were applied. The methodology allows for a nuanced understanding of the frequency and severity of failures, enabling more informed decision-making about maintenance strategies. The paper highlights the economic implications of system failures and the potential for substantial financial savings through optimized maintenance planning.

5 February 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
AAAl-Sifao A. Abdalla Al-Sifao
Al-Sifao A. Abdalla Al-Sifao
NPNikola Petrović
Nikola Petrović
RJRadiša Jovanović
Radiša Jovanović
UBUglješa Srbislav Bugarić
Uglješa Srbislav Bugarić
To address water shortages, Libya has undertaken one of the most significant global civil infrastructure projects, the Great Man-Made River Project, aimed at transporting groundwater from southern well-fields to densely populated northern cities. The second phase of the project consisted of installing the water supply system, which comprises 479 well pumps, united to deliver around 2 million cubic meters of water to the north. Historical performance data for the water supply system were analyzed, and a model for the system’s reliability calculation was developed: a finite-source, multi-server queuing system with spares (M/M/c//N/Y). The model enabled the analytical calculation of the system’s reliability in different configurations. Each configuration was assessed using a unique risk score, defined as the product of reliability-based parameters and the consequences associated with water-shortage events resulting from system failures. The analysis identified two alternative configurations that satisfy all predefined performance and risk criteria. Both configurations require fewer resources than the original system design, with up to seven fewer spare pumps, allowing for decision-makers to select the most appropriate option based on additional operational and contextual considerations.

1 January 2024
Verified
Conference Paper
Open access
PDF file
UBUglješa Srbislav Bugarić
Uglješa Srbislav Bugarić
VBVesna Spasojevic Brkic
Vesna Spasojevic Brkic
NPNikola Petrović
Nikola Petrović
NJNemanja Janev
Nemanja Janev
MPMartina Perišić
Martina Perišić
The mining industry has been steadily expanding annually to keep up with the increasing demands. Consequently, used machinery needs to work efficiently, which indicates that unexpected downtimes should be at the minimum possible level. Proper identification and risk evaluation of the potential breakdown is the most important element for efficient equipment maintenance and breakdown prevention. This research has focused on its reliability function determination and analyzed the consequences of downtime and the cost of repairs over a period of one year. Delays on the observed mining machine were classified according to the type of downtime: mechanical, technological, power/electricity, and downtime due to external influences. Input elements for risk assessment were severity of consequence (S), probability of occurrence (O), and failure detectability (D). The method used in this paper is based on the cost of maintenance and the impact of bulldozer breakdowns on reliability in order to maintain profitability and, by reducing the number of unwanted events caused by sudden failure of parts, increase safety during operation. Results show that the monitored bulldozer belongs to the lowest defined risk class, so its use is economically justifiable.

3 March 2025 in International Journal of Occupational Safety and Ergonomics
Verified
Journal Article
Closed access
IMIvan N. Mihajlović
Ivan N. Mihajlović
NPNikola Petrović
Nikola Petrović
VBVesna Spasojevic Brkic
Vesna Spasojevic Brkic
NMNenad Milijić
Nenad Milijić
Objectives. Considering that there is no standardized questionnaire for safety climate and resilience assessment, authors usually review a large number of questionnaires from the available literature, which results in a high number of questions distributed to respondents. As the questionnaire length increases, resistance from the respondents increases. Artificial intelligence (AI) tools until now have not been used for item reduction, besides the need for selecting and retaining only the most relevant and informative questions in the questionnaire with adequate accuracy. Methods. AI tools such as multiple linear regression analysis (MLRA) and the multilayer perceptron artificial neural network (MLP ANN) are used in the development of a model able to cluster respondents' ratings and to predict values of organizational resilience based on the respondents' ratings of the specific questions. Results. AI could be used as a valuable tool for item reduction, since the prediction accuracy for MLRA tools is 70.4-71.5% and for the MLP ANN it is 76.4%. Conclusions. This research proves that machine learning algorithms can be used to build predictive models that determine which survey questions are the most predictive for organizational resilience index calculation using safety climate factors.

1 January 2025
Verified
Conference Paper
Closed access
Boban NikolićBoban Nikolić
Boban Nikolić
Breda KeglBreda Kegl
Breda Kegl
JDJovan Dorić
Jovan Dorić
DMDragan Marinkovic
Dragan Marinkovic
NPNikola Petrović
Nikola Petrović
The operation of diesel engines with biodiesel and its blends provides notable environmental and economic benefits. Although certain deviations in engine performance may occur, biodiesel remains a suitable alternative fuel when it meets regulatory standards. This study focuses on the difference in fuel consumption between biodiesel and diesel. Based on the analysis of a mechanically controlled fuel injection system, correlations between key fuel properties (density, speed of sound, and discharge coefficient) and fuel consumption were established, enabling the prediction of consumption differences depending on the physical and chemical characteristics of the fuel.

1 January 2025
Verified
Conference Paper
Closed access
SMSaša Marković
Saša Marković
DMDragan Marinkovic
Dragan Marinkovic
DMDanijel Markovic
Danijel Markovic
NPNikola Petrović
Nikola Petrović
Boban NikolićBoban Nikolić
Boban Nikolić
Screw conveyors are widely used in the transportation of various bulk materials in the industry because of their simple structure and low cost. The paper will present the calculation of screw conveyors, including an analysis of all relevant coefficients, as well as the selection of bulk material types and classes. The case study examines several instances of conveyor use, analyzing capacities, motor powers, and shaft loads.