改进BP神经网络在铁路客运量预测中的应用

The application of improved BP neural network in forecasting railway passenger volume

介绍BP神经网络预测模型的优点及不足,提出运用主成分分析法、灰色关联分析法对BP神经网络结构进行优化,同时运用自适应遗传算法对神经网络的权值和阈值进行优化。运用改进的BP神经网络对客运量进行预测,经多种指标对预测精度进行评价,证明改进的BP神经网络在交通运输需求预测中具有实用价值。

The article first introduces the virtues and defects of the basic BP neural network, secondly, puts forward to optimize the structure of the BP neural network by using principal component analysis method and the grey correlation analysis, meanwhile, to optimize weights and thresholds of the neural network by using adaptive genetic algorithm, finally, forecasts the railway passenger volume by using the improved BP neural network, makes use of the evaluation indexes to appraise the accuracy of prediction results, and testifies the practical worth of the improved BP neural network in transportation demand prediction.