Research on Energy Consumption Prediction of Urban Rail Transit Based on Data Mining

Inhalt:
In recent years, our country attaches great importance to the development of rail transit, Urban rail transit system has become one of the most important ways of travel in people's life. Therefore, it is of great theoretical and practical significance to analyze the energy consumption of rail transit, and give energy saving and emission reduction measures according to the results. This paper first studies and summarizes the relevant concepts and prediction methods in the energy consumption prediction field of urban rail operation, and finds that the technical effect of BP neural network is good and relatively common. Therefore, according at the energy consumption of urban rail transit, this paper constructs the energy consumption prediction model based on BP neural network based on the real energy consumption data of a line of Nanjing metro. The input layer of the initial prediction model is 14 influencing variables. After error detection and model training, the average accuracy of the model energy consumption prediction reached 96.15%.In order to reduce the computational complexity of the model, make the model play more value in practical application, this paper and on the basis of the initial model model, using the grey scale correlation analysis, variable reduction, established the input layer for eight variables energy consumption prediction model, model after simplified average accuracy reached 96.55%, also has a good prediction effect.