Search

Copyright of Railway Standard Design is the property of Railway Standard Design Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In order to scientifically evaluate the possibility of subway flood disaster, enhance the prevention and emergency response ability of subway flood disaster and reduce personal injury and property loss, this paper takes the relevant data extracted from the historical events of subway flood disaster in China as samples, deconstructs the disaster-causing factors of subway flood disaster, and analyzes the factors from three dimensions: natural factors, surrounding environment and flood control ability. A total of 13 disaster-causing factors are used to analyze the causes and related information of subway flood disaster, and a neural network model for predicting whether subway flood disaster will occur is constructed based on DNN neural network method. The results show that:(1) The subway flood disaster prediction model performs well in accuracy and F1 score index evaluation, with the accuracy of 85% and F1 score value of 0. 9, and the test set results are basically consistent with the actual subway flood disaster. (2)In addition, poor flood control ability and bad surrounding environment factors will aggravate the vulnerability of the disaster-bearing environment of subway stations and should be addressed. (3)Natural factors are the key elements of subway flood disaster, and the timeliness between natural factors and flood control information dispatching should be strengthened. [ABSTRACT FROM AUTHOR]