The main goal of this research was the development of an algorithm for the implementation of negative risk parameters in a synthesis model for a risk level assessment for a specific machine used in the mining industry. Fuzzy sets and fuzzy logic theory, in combination with statistical methods, were applied to analyze the time picture state of the observed machine. Fuzzy logic is presented through fuzzy proposition and a fuzzy composition module. Using these tools, the symmetric position of the fuzzy sets with regard to class was used, and the symmetric fuzzy inference approach was used in an outcome calculation. The main benefit of the proposed model is being able to use numerical and linguistic data in a risk assessment model. The proposed risk assessment model, using fuzzy logic conclusions and min–max composition, was used on a mobile crushing machine. The results indicated that the risk level of the mobile crushing machine was in the “high” category, which means that it is necessary to introduce maintenance policies based on this high risk. The proposed risk assessment model is useful for any engineering system.

The study presented here analyzes mining accidents and fatal injuries in Serbian underground coal mines over a period of 50 years, in order to assess the effectiveness of legislation changes in the overall safety of work environment. Two distinct periods, prior to 2000 and after 2000 were compared. The data from the period after 2000 were further analyzed to provide better understanding of the results. In order to assess the overall state of safety in Serbian mines, the data on fatal injuries were also compared to the international data. It was found that the legislative changes are more easily accepted by the common workers than by the mine management. Consequently, the key recommendation for the safety of coal mine companies in Serbia is the investment in the new technology. Additionally, mine management should be in the focus of the mining inspection with a stronger penal policy regarding mine safety neglect.

During 2011, a study was undertaken to assess safety conditions in Serbian underground coalmines by analysis of injury data. The study covered all Serbian coalmines, identified week spots from the aspect of safety, and recommended possible courses of action. Since then, Serbia has made changes to safety and health legislation; all coalmines introduced new preventive measures, adopted international standards, and made procedures for risk management. After 10 years a new study has been performed to analyze the impact of these changes. In this study, the injuries that have occurred in the Serbian underground coal mines over the last 20 years were analyzed. Statistical data analysis was performed by IBM SPSS Statistics v23. The injuries that occurred in the last ten years were compared with the results of the previous study (2000–2009). The average values of injury rates for both periods were compared for each of the categories (severity, age, body part, qualification), and the results were presented as absolute difference or percentile difference. The results showed reduction in the number of injuries in the category of 20–30 years old workers, where the new training procedures for workers, which were set by mandatory legal regulations, certainly contributed. They also showed an increase in the number of injuries in the category of old workers, which indicates that the law did not have a positive effect on this category. The total number of injuries is still high; therefore, it is necessary to introduce mechanization and automation in mines and have a better policy for older workers who retire later nowadays.

Artificial neural networks (ANN) are a powerful tool in the decision-making process, especially in solving the complex problems with a large number of input data. The possibility to predict the work-related injuries in the underground coal mines, based on application of the neural networks, is analyzed in this work. the input data for the network were obtained based on a survey of 1300 respondents. After analyzing the input data influence on the network output, 14 most influential inputs were selected, with help of which the network correctly predicted whether the worker would suffer the work-related injury or not, with 80% precision. The two models were developed, based on the multilayer perceptron (MLP) and radial basis function (RBF) networks. The two models’ results were compared to each other. The sensitivity analysis was used to select the most influential parameters, like mine, age of miners, as well as their work experience. The parameters were further analyzed by use of the descriptive statistics. The selected parameters are direct indicators of problems that can cause injuries. The obtained results point to the fact that the work-related injuries can be successfully predicted by application of the artificial neural networks. The proposed models’ importance is reflected in the clear indicators for enforcing the stricter occupational safety and organizational measures in order to reduce the number of work-related injuries in underground mines.

Background: Mining is a high-risk sector, particularly in underground environments, where workers face daily hazards. This research evaluates workplace safety perceptions in Serbian underground coal mines, ranking workers by education, age, and job role, while incorporating injury data to provide a comprehensive assessment of safety across different worker groups. Objective: This study is aimed at analyses of the correlation between occupational health and safety (OHS) perceptions and the injury index across different worker groups, to identify improvement opportunities and propose targeted measures for enhancing OHS practices. Methods: The PROMETHEE II method categorized workers based on production units, qualifications, and age, focusing on criteria like protective equipment, work conditions, risk awareness, management, work organization, and training. The entropy method provided objective weightings for these criteria, allowing for comparison with injury index rankings to establish priorities for improvement. Results: Štavalj and Vrška Čuka ranked highest in OHS perception. Workers with MSc/Dr qualifications displayed heightened awareness of safety, while those aged 56 to 65 exhibited the best understanding of health and safety. Spearman rank correlation coefficients revealed a strong negative correlation (−0.796) for production units, a strong positive correlation (0.70) for qualifications, and a very strong positive correlation (0.90) for age concerning PROMETHEE II rankings and injury index indicators. Conclusions: The disparities between worker perception rankings and injury index rankings suggest opportunities for targeted safety improvements and enhanced training protocols.

The mining industry in Serbia has an important place in the country's economic development. Bearing in mind that the number of injuries that occur in the mining industry is unacceptably high, occupational safety and health is a challenge that existing and future mines will have to deal with. Studying injuries in mining, it was noticed that injuries requiring an absence from work for more than three days (especially fatal ones) are diametrically different in relation to the cause and manner of events related to injuries for which an absence from work is not necessary. In this research, authors focused on injuries that were characterized as ones requiring an absence from work. The statistical analysis of work-related injuries in mining is presented, as well as analysis of the direct causes of injuries, which are described as unsafe conduct of employees, unsafe conduct of company's management and/or unsafe working environment. In relation to classification of causes of injuries, a recommendation on what needs to be changed in order to remedy this situation in Serbia is given.