基于遗传优化神经网络的铁路客运量预测研究

The forecasting research of railway passenger capacity based on neural network optimized by GA

采用遗传优化的BP神经网络对铁路客运量的现有数据进行分析,克服了BP网络极易陷入局部解问题,做出合理的客运量预测.首先用遗传算法优化神经网络的连接权,并在遗传进化过程中保留最优个体的方法,选择权值的最优解来建立遗传优化的BP网络预测模型,最后通过铁路客运量数据预测结果的对比仿真实验,表明了该方法的有效性.

After analyzing the forecasting method of railway passenger capacity,a neural net- work optimized by Genetic Algorithm approach was proposed for forecasting railway passengers＇ capacity accurately. Aimed at the problem that BP algorithm is usually trapped to a local optimum and has a low speed of convergence, the Genetic Algorithm is used to optimize the connection weights of neural network. In the evalution processes the best individual is reserved and selected to build the forecasting model. The contradistinctive experimental results of railway passenger capacity show the availability of the method,which plays directive sense for the railway corporation＇ decision-making.