INTELLECTUALIZATION OF MANAGERIAL DECISION SUPPORT IN EMERGENCY SITUATIONS IN RAILWAY TRANSPORTATION

Abstract

This study focuses on the intellectualization of decision-making support for emergency situations (ES) on railway transport. The relevance of the research is determined by the need to improve the efficiency and accuracy of decision-makers’ actions, especially in weakly formalized and rare ES scenarios. The aim of the study is to develop methods and algorithms for intellectualization that reproduce expert actions using artificial neural networks (ANNs). The objectives include: analyzing existing ES classification methods; formalizing expert knowledge; developing and training ANNs based on decision-makers’ experience; and evaluating the effectiveness of the proposed approach through practical examples. The results indicate that using ANNs allows accurate classification of different types of ES, predicting the scale of consequences, and generating recommended actions for decision-makers. The proposed ANN training method enables system adaptation to the specifics of individual railway stations, including rare and weakly formalized situations. The study concludes that intellectualization of decision-making support enhances emergency management efficiency, reduces material and human costs, and opens prospects for further research and implementation of decision support systems on railway transport.