Application of BP Neural Network in Risk Evaluation of Railway Construction

Abstract

Research purposes: Chinese railway construction project is an important part of the implementation of the "Belt and Road" strategy, and the risk evaluation of overseas railway construction is the primary link of the project. Firstly, this paper synthesizes various risk factors, mainly analyzes the Asian and European countries along the railway construction project, and establishes a railway construction project risk evaluation system. Secondly, it uses different training algorithms for the political, economic and cultural differences between the two continents, to establish two independent BP neural network models. Research conclusions: (1) This paper establishes a BP neural network model for risk assessment using different functions for different situations in Asia and Europe. (2) Through the created neural network model, in the macro-risk evaluation of the railway construction target country, only the experts can give the scores of the respective risks in the target country, and the overall construction risk score of the target country can be obtained without tedious manual overall scoring. (3) The research results can be used for risk assessment of high-speed railway construction.