Study on Optimal Path Selection of Railway Emergency Based on Neural Network

According to the characteristics of specificity and multi-goal property for the railway transportation organization in emergencies, this paper constructs the path evaluation index system from three aspects, including road network conditions, emergency management and emergency resources. Through the application of analytic hierarchy process, the weight of each evaluation index in the system is determined. In addition, the index is quantized by expert consultation and fuzzy processing with the establishment of three-level BP neural network evaluation model for alternative path assessment. Finally, the feasibility of this approach is proved with the use of algorithm cases.