基于PCA-IPSO-GNN模型的铁路月度客运量预测模型研究
|
摘要
铁路月度客运量预测是铁路客运组织的基础,是铁路路网规划和运营管理的前提条件。本文提出了基于PCA-IPSO-GNN模型的铁路月度客运量预测模型,利用主成分分析(PCA)对铁路月度客运量影响因素进行综合分析,将分析结果作为灰色神经网络(GNN)的输入,同时采用改进的粒子群优化算法(IPSO)优化GNN的白化参数,进而得到更为准确的铁路月度客运量预测值。经过实例验证和比较,PCA-IPSO-GNN预测模型具有较高的精度,可以满足铁路月度客运量的预测需求。
The forecast of railway monthly passenger volume is not only the foundation of the railway passenger transport organization but also the precondition for the railway network planning and operation management. This paper proposes a PCA-IPSO-GNN prediction model, which can use the principal component analysis(PCA) to carry on the comprehensive analysis to the railway monthly passenger volume influencing factor, and sets the PCA results as the grey neural network(GNN)'s input. At the same time, an improved particle swarm optimization(IPSO) algorithm is used to optimize the parameters of GNN to get a more accurate forecast of railway monthly passenger volume. After the example verification and comparison, the PCA-IPSO-GNN prediction model has higher accuracy and can meet the forecast demand of the railway monthly passenger volume.
The forecast of railway monthly passenger volume is not only the foundation of the railway passenger transport organization but also the precondition for the railway network planning and operation management. This paper proposes a PCA-IPSO-GNN prediction model, which can use the principal component analysis(PCA) to carry on the comprehensive analysis to the railway monthly passenger volume influencing factor, and sets the PCA results as the grey neural network(GNN)'s input. At the same time, an improved particle swarm optimization(IPSO) algorithm is used to optimize the parameters of GNN to get a more accurate forecast of railway monthly passenger volume. After the example verification and comparison, the PCA-IPSO-GNN prediction model has higher accuracy and can meet the forecast demand of the railway monthly passenger volume.
引文
[1]郭孜政.铁路客流预测方法研究[D].西南交通大学,2005.
[2]褚鹏宇.融合时空信息的短时交通流预测[D].西南交通大学,2016.
[3]徐薇,黄厚宽,秦勇.基于时空数据挖掘的铁路客流预测方法[J].北京交通大学学报,2004,28(5):16-19.
[4]王惠珍.基于改进灰色系统GM(1,1)模型的成本预测[J].统计与决策,2015(15):83-86.
[5]Chen S M,Hwang J R.Temperature prediction using fuzzy time series[J].IEEE Transactions on Systems Man&Cybernetics Part B Cybernetics A Publication of the IEEE Systems Man&Cybernetics Society,2000,30(2):263-75.
[6]Huarng K.Heuristic models of fuzzy time series for forecasting[J].Fuzzy Sets&Systems,2001,123(3):369-386.
[7]蔺玉佩,杨一文.基于模糊时间序列模型的股票市场预测[J].统计与决策,2010(8):34-37.
[8]Chen M Y,Chen B T.A hybrid fuzzy time series model based on granular computing for stock price forecasting[J].Information Sciences,2015,294(2):227-241.
[9]Kennedy J,Eberhart R.Particle swarm optimization[C].IEEE International Conference on Neural Networks,1995.Proceedings.IEEE,2002:1942-1948 vol.4.
[10]陈贞,何洪亮.基于BP神经网络的安全防范系统效能评估[J].中国公共安全(学术版),2011(1):112-114.
[11]陶海龙,李小平,张胜召等.基于IPSO-BP神经网络的铁路客运量预测[J].铁道运输与经济,2011,33(9):78-82.
[12]陶海龙.基于混合智能算法的铁路运量预测研究[D].兰州交通大学,2012.
[13]刘琳玥.基于PCA-BP神经网络的铁路客运量预测模型研究[J].综合运输,2016(8):43-47.
[14]马西良.基于HPSO-GNN的煤矿井下瓦斯分布区域预测研究[J].煤炭工程,2016,48(11):88-91.
[2]褚鹏宇.融合时空信息的短时交通流预测[D].西南交通大学,2016.
[3]徐薇,黄厚宽,秦勇.基于时空数据挖掘的铁路客流预测方法[J].北京交通大学学报,2004,28(5):16-19.
[4]王惠珍.基于改进灰色系统GM(1,1)模型的成本预测[J].统计与决策,2015(15):83-86.
[5]Chen S M,Hwang J R.Temperature prediction using fuzzy time series[J].IEEE Transactions on Systems Man&Cybernetics Part B Cybernetics A Publication of the IEEE Systems Man&Cybernetics Society,2000,30(2):263-75.
[6]Huarng K.Heuristic models of fuzzy time series for forecasting[J].Fuzzy Sets&Systems,2001,123(3):369-386.
[7]蔺玉佩,杨一文.基于模糊时间序列模型的股票市场预测[J].统计与决策,2010(8):34-37.
[8]Chen M Y,Chen B T.A hybrid fuzzy time series model based on granular computing for stock price forecasting[J].Information Sciences,2015,294(2):227-241.
[9]Kennedy J,Eberhart R.Particle swarm optimization[C].IEEE International Conference on Neural Networks,1995.Proceedings.IEEE,2002:1942-1948 vol.4.
[10]陈贞,何洪亮.基于BP神经网络的安全防范系统效能评估[J].中国公共安全(学术版),2011(1):112-114.
[11]陶海龙,李小平,张胜召等.基于IPSO-BP神经网络的铁路客运量预测[J].铁道运输与经济,2011,33(9):78-82.
[12]陶海龙.基于混合智能算法的铁路运量预测研究[D].兰州交通大学,2012.
[13]刘琳玥.基于PCA-BP神经网络的铁路客运量预测模型研究[J].综合运输,2016(8):43-47.
[14]马西良.基于HPSO-GNN的煤矿井下瓦斯分布区域预测研究[J].煤炭工程,2016,48(11):88-91.