Railway Passenger Volume Forecast by GA-SA-BP Neural Network

Since the BP neural network algorithm has some unavoidable disadvantages, such as slowly converging speed and easily running into local infinitesimal, the genetic algorithm and simulated annealing algorithm with the overall search capability has been put forward to optimize authority value and threshold value of BP nerve network. In this paper, GA-SA-BP neural network algorithm model has been established and applied into the railway passenger volume forecast. The result shows that this model has significant advantages inspect of fast convergence speed, good generalization ability and not easy to yield minimal local results. In generally, this model exhibits good representation and strong prediction ability, and is a helpful tool in the future railway passenger volume prediction.