基于灰色模型的北京轨道交通昌平线客流预测及应用

Passenger flow prediction and application of Beijing subway Changping Line based on grey model

应用灰色GM(1,1)、Verhulst模型可以克服轨道交通客流预测时历史数据较少的弊端。计算发现,GM(1,1)模型预测结果较真实值偏小3.04%,Verhulst模型预测结果较真实值偏大1.78%,通过使用变异系数法确定权重对两种模型进行改进,预测值较真实值偏小0.734%,优于GM(1,1)模型2.31%,优于Verhulst模型2.52%,有利于预测结果准确性的提升。通过应用灰色预测方法,可以为轨道交通运营企业在提高线路运力、预判站车客流压力、进行商业网点布置方面提供决策依据。

The grey GM(1,1)and Verhulst models can overcome the disadvantage of less historical data in rail transit passenger flow prediction.Through calculation,it is found that the predicted result of GM(1,1)model is 3.04%smaller than the true value.The predicted result of Verhulst model is 1.78%larger than the true value.By using the coefficient of variation method to determine the weight,the two models are improved,and the predicted value is 0.734%smaller than the true value,which is better than GM(1,1)model 2.31%and Verhulst model 2.52%,which is conducive to the improvement of the accuracy of prediction results.The application of grey forecasting method can help the rail transit operators to improve the line capacity,predict the passenger flow pressure of the station,and provide decision-making basis for the layout of commercial outlets.