The Application of Improved BP Neural Network in the Prediction of Railway Passenger Volume Time Serial
Zhu Wang · Zhongguo tiedao kexue · 2005
Aimed at the shortcomings of the prediction methods for the passenger traffic volume of railways, the improved BP neural network is adopted to predict the time serial of the railway passenger traffic volume. The improved BP neural network theory is analyzed.The railway passenger traffic volume from 1980 to 1998 is normalized.The time serial neural network prediction model of railway passenger traffic volume is set up.The network parameters is designed.The network learning and training simulation experiment is carried out.The prediction result of the improved and normal BP neural network is compared and analyzed. The prediction result of the improved BP neural network is proved to be more accurate and precise.