Models that represent real problems have been relying so far on historical data to draw upon conclusions. One negative aspect of these models was that they could not predict future states based on ...real data instantly collected or new sources of risk that suddenly appeared. To overcome this problem, this work presents the process of building a realistic predictive model using Bayesian Belief Networks (BBNs) and the AgenaRisk software. BBNs are a direct representation of real problems where their graphical structure represents real causal connections and not just a flow of information. Software tools providing algorithms for dealing with conditional probabilities have been developed. The Bayesian Theorem, a theoretical background for conditional probability, was also explained in the paper. Another benefit of using BBNs is that the reasoning process can operate by propagating information in any direction (top-down or bottom-up) which makes it a powerful tool in risk assessment and a decision-making process. The paper also provides the core principles and the power of BBNs and their application in the project planning phase for ammunition delaboration (resolving problems of surplus and obsolete ammunition in stockpiles), where risk assessment is one of the required processes which helps in making a final decision for project approval or not. The sensitivity and SWOT analyses are also performed as valuable and helpful tools for validation and making conclusions. / Модели, представляющие реальные проблемы при принятии решений, зачастую руководствуются историческими данными. Негативный аспект данных моделей заключается в том, что они не могут предусмотреть обстоятельства в будущем, которые основаны на реальных событиях и новых источниках риска. Для преодоления этой проблемы в данной статье представлен процесс разработки реальной предиктивной модели с применением байесовской сети вероятности и программного обеспечения AgenaRisk. Байесовские сети вероятности напрямую отражают реальные проблемы посредством графических структур, которые представляют не только поток информации, но и условные связи. В качестве теоретического обоснования в данной работе приведена и объяснена теорема Байеса. Преимущество использования байесовых сетей вероятности в процессе принятия решений, заключается в том, что этот процесс производится в „двух направлениях“ (снизу вверх и наоборот), что делает его мощнейшим инструментом для оценки рисков в процессе принятия решений. В статье также представлены базовые принципы и значение байесовых сетей и их применение в процессе разработки проекта по утилизации боеприпасов (утилизация запасов устаревших и непригодных боеприпасов), в котором оценка рисков является одной из сложнейших задач, непосредственно влияющей на принятие окончательного решения о запуске проекта. Наряду с вышеперечисленными методами для обоснования принятия окончательных решений проведены: анализ чувствительности и SWOT анализ. / Modeli koji reprezentuju realne probleme prilikom donošenja zaključaka većinom se oslanjaju na istorijske podatke. Negativan aspekt ovih modela jeste da oni ne mogu da predvide buduća stanja zasnovana na trenutno prikupljenim podacima kao i novim izvorima rizika. Da bi se prevazišao ovaj problem, u radu je prikazan proces izgradnje realnog prediktivnog modela korišćenjem Bajesovih mreža verovatnoće i softvera AgenaRisk. Bajesove mreže verovatnoće najdirektnije reprezentuju realne probleme preko grafičke strukture koja predstavlja uslovne veze, a ne samo tokove informacija. Razvijeni su i softveri koji imaju algoritme za računanje uslovnih verovatnoća. Kao teoretska osnova koristi se Bajesova teorema koja je takođe objašnjena u ovom radu. Druga prednost korišćenja Bajesovih mreža verovatnoće jeste proces zaključivanja koji se može vršiti u „oba pravca” (odozgo nadole i obratno), što ga čini veoma moćnim alatom u proceni rizika i procesu zaključivanja. Takođe, u radu su prikazani osnovni principi i prednosti primene Bajesovih mreža u procesu pripreme projekta delaboracije municije (rešavanje viškova i neperspektivne municije u skladištima). U njemu je procena rizika jedan od zahtevanih aktivnosti koji pomaže u procesu donošenja konačne odluke za pokretanje ili nepokretanje projekta. Analiza osetljivosti i SWOT analiza primenjeni su kao korisni alati za validaciju i donošenje konačnih zaključaka.
Introduction/purpose: When performing the explosive welding procedure, for the safety of workers, it is necessary to take into account the minimum distance between the workers and the place of ...explosion at the time of explosion. Negligence can cause temporary hearing loss, rupture of the eardrum and in some cases even the death of workers. The aim of this paper is to determine the critical distance based on the mass of explosive charge required for explosive welding, provided that the limit pressure is 6.9 kPa in the case of temporary hearing loss and 35 kPa in the case of eardrum rupture. This paper does not take into account other effects of the explosion than those caused by the shock wave. Methods: Depending on the type of explosion, the equivalent explosive mass was calculated. Based on the equivalent explosive mass and the limit pressure, the minimum distances were calculated using the Sadovsky and Kingery-Bulmash equations. Results: The corresponding tables show the results of the calculation of the critical distance of workers from the place of the explosion when there may be temporary hearing loss or rupture of the eardrum. The calculated value of the critical explosion distance by the Kingery-Bulmash method, under the condition of the maximum pressure for temporary hearing loss, is 5.62% lower than the distance value obtained by the Sadovsky method while the value of the critical explosion distance calculated by the Kingery-Bulmash method, under the condition of the maximum pressure for eardrum rupture, is 7.83% lower than the value obtained by the Sadovsky method. Conclusion: The results of the calculation showed that the critical distance from the explosion can be successfully calculated and that the obtained values have small differences depending on the applied calculation method.