
This article analyzes the state of passenger railtransport in recent years, as well as the impact on them ofexternal factors. The use of the method of artificial neuralnetworks to predict passenger turnover, in particular withits dynamic change in the conditions of martial law inUkraine and the spread of active hostilities in our country.The assessment and possible impact of the risks ofdestruction of railway infrastructure, the magnitude ofwhich depends on: the minimum distance from the frontline, state border or the Black Sea coast, to a particularrailway section; the number of military and strategicfacilities near a given site; availability of locomotivedepots with fuel reserves; the size of railway stations inthese areas; the size of railway junctions (by number ofdirections); availability of high platforms on which it ispossible to load and unload military echelons; topographicfeatures of the area (the presence of bridges, viaducts,overpasses). Accordingly, a formula was formed tocalculate the amount of costs from the destruction ofrailway infrastructure at each site. An optimization modelfor the organization of passenger transportation by rail hasbeen developed, taking into account the possible capacityof each section, running speed of trains, length of the train,population of passenger cars, as well as the obtaineddegrees of risk. The use of genetic algorithms for solvingthis mathematical model is substantiated and their basicscheme of work is formed. The possibility of using theresults of this study to improve existing decision supportsystems and implement them in automated workplacesrelated to passenger logistics is assessed.
У статті проаналізовано стан пасажирських залізничних перевезень за останні роки, а також вплив на нихзовнішніх факторів. Обґрунтовано використання методу штучних нейронних мереж для прогнозуванняпасажирообігу, зокрема при його динамічній зміні в умовах воєнного стану в Україні та поширенні активнихбойових дій на території нашої держави. Оцінено можливий вплив ризиків руйнування залізничноїінфраструктури. Відповідно до цього було сформовано оптимізаційну модель, що враховує можливі ризики приперевезенні пасажирів. Обґрунтовано використання генетичних алгоритмів для вирішення цієї математичноїмоделі та сформовано їхню принципову схему роботи.
пасажирообіг, залізничні пасажирські перевезення, інфраструктура, штучні нейронні мережі, теорія ризиків, генетичні алгоритми, passenger turnover, railway passenger transportation, infrastructure, artificial neural networks, degree of risk, genetic algorithms
пасажирообіг, залізничні пасажирські перевезення, інфраструктура, штучні нейронні мережі, теорія ризиків, генетичні алгоритми, passenger turnover, railway passenger transportation, infrastructure, artificial neural networks, degree of risk, genetic algorithms
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
