我国农业机械化作业水平的组合预测模型对比研究
|
摘要
为探究不同组合模型对我国农业机械化作业水平预测的影响,以我国农业机械化作业水平时间序列为研究对象,以2001-2012年历史数据作为训练样本,分别选择指数曲线法、三次指数平滑法及灰色预测法构建单项预测模型,并基于单项模型的预测结果,选择误差平方和最小法、Shapley法和IOWGA法构建组合预测模型,对2013-2015年农业机械化作业水平进行预测。预测结果的对比分析表明:组合模型的预测精度从高到低分别为IOWGA组合模型、基于误差平方和最小法组合模型及Shapley组合模型。IOWGA组合预测模型充分汇集了各单项预测模型中的有效信息,且根据预测精度的大小赋予不同的权值,具备更好的预测效果和稳定性,相对误差可控制在1%,可用于我国农业机械化作业水平预测。
To explore the effects of different combination forecasting models on the operation level of agricultural mechanization,the time series of the operation level of agricultural mechanization and the historical data from 2001–2012 are selected as the research object and training sample,respectively,in this study.The exponential curve method,the cubic exponential smoothing method,and the gray forecasting method are adopted to construct the single forecasting model.Moreover,the least sum of squared error(LSSE),Shapley,and IOWGA operators are selected to construct the combination forecasting model and forecast the operation level of agricultural mechanization in 2013–2015 based on the forecasting results of the single model.The comparison results show that the forecasting effect of the IOWGA combination model is the best,followed by that of the combination forecasting model based on LSSE,whereas the Shapley combination model exhibits the lowest forecasting accuracy.The IOWGA combination forecasting model can collect valid information from each forecasting model and assign different weights according to the level of forecasting precision,while exhibiting better forecasting effect and stability.Its relative error can be controlled at 1%.The IOWGA combination forecasting model exhibits the advantage of forecasting the operation level of agricultural mechanization in China.Research results can provide effective references for agricultural mechanization development plan.
To explore the effects of different combination forecasting models on the operation level of agricultural mechanization,the time series of the operation level of agricultural mechanization and the historical data from 2001–2012 are selected as the research object and training sample,respectively,in this study.The exponential curve method,the cubic exponential smoothing method,and the gray forecasting method are adopted to construct the single forecasting model.Moreover,the least sum of squared error(LSSE),Shapley,and IOWGA operators are selected to construct the combination forecasting model and forecast the operation level of agricultural mechanization in 2013–2015 based on the forecasting results of the single model.The comparison results show that the forecasting effect of the IOWGA combination model is the best,followed by that of the combination forecasting model based on LSSE,whereas the Shapley combination model exhibits the lowest forecasting accuracy.The IOWGA combination forecasting model can collect valid information from each forecasting model and assign different weights according to the level of forecasting precision,while exhibiting better forecasting effect and stability.Its relative error can be controlled at 1%.The IOWGA combination forecasting model exhibits the advantage of forecasting the operation level of agricultural mechanization in China.Research results can provide effective references for agricultural mechanization development plan.
引文
[1]杨敏丽,白人朴.我国农业机械化发展的阶段性研究[J].农业机械学报,2005,36(12):167-170.
[2]Huang Z H,Lu H Z,Yang J F,et al.Application of a combination forecasting model in predicting the agricultural mechanization level in China[J].Revista de la Facultad de Ingenieria,2017,32(4):163-171.
[3]鞠金艳,王金武.黑龙江省农业机械化作业水平预测方法[J].农业工程学报,2009,25(5):83-88.
[4]张睿,高焕文.基于灰色GM(1,1)的农业机械化水平预测模型[J].农业机械学报,2009,40(2):91-95.
[5]BATES J M,GRANGER C W J.Combination of forecasts[J].Operations Research Quarterly,1969,20(4):451-468.
[6]Elliott G,Granger C W J,Timmerman A.Handbook of economic forecasting:forecast combinations[M].North Holland:Elsevier,2006.
[7]Liu S L,Hu Z Q,Chi X K.The research of power load forecasting method on combination forecasting model[J].Information Science and Engineering,2010,26:1273.
[8]吴静敏,左洪福,陈勇.基于免疫粒子群算法的组合预测方法[J].系统工程理论方法应用,2006,15(3):229-233.
[9]宋晓华,祖丕娥,伊静,等.基于改进GM(1,1)和SVM的长期电量优化组合预测模型[J].中南大学学报,2012,43(5):1803-1807.
[10]韩冬梅,牛文清,杨荣.线性与非线性最优组合预测方法的比较研究[J].科学情报,2007(11):1672-1678.
[11]Granger C W J,Ramanathan R.Improved Methods of Forecasting[J].Journal of Forecasting,1984,3(2):197-204.
[12]刘静,朱达荣.考虑自变及因变影响的农机总动力组合预测模型[J].农机化研究,2015,37(4):230-236.
[13]Shapley L S.A value for n-persons games[J].Annals of Mathematics Studies,1953,28:307-317.
[14]雷勋平,Robin Q.Shapley值法的改进及其应用研究[J].计算机工程与应用,2012,48(7):23-25.
[15]张淑娟,冯屾,介邓飞,等.基于Shapley值的农机装备水平组合预测[J].农业工程学报,2008,24(6):160-164.
[16]张淑娟,赵飞.基于Shapley值的农机总动力组合预测方法[J].农业机械学报,2008,39(5):60-64.
[17]Jeong R K K.Combining forecasts using optimal combination weight and generalized autoregression[J].Journal of Forecasting,2010,27(5):419-432.
[18]Poncela P,Rodriguez J,Sanchez M R,et al.Forecast combination through dimension reduction techniques[J].International Journal of Forecasting,2011,27(2):224-237.
[19]Costantini M,Pappalardo C.A hierarchical procedure for the combination of forecasts[J].International Journal of Forecasting,2010,26(4):725-743.
[20]Kolassa S.Combining exponential smoothing forecasts using Akaike weight[J].International Journal of Forecasting,2011,27(2):238-251.
[21]Yager R R.Induced aggregation operators[J].Fuzzy Sets and Systems,2003,137:59-69.
[22]林德花,袁振洲.基于IOWA算子的短时交通流预测方法研究[J].科学技术与工程,2013,13(25):7596-7600.
[23]陈华友,盛昭翰.一类基于IOWGA算子的组合预测新方法[J].管理工程学报,2005,19(4):39-42.
[24]施泽军,李凯.基于灰色模型和指数平滑法的集装箱吞吐量预测[J].重庆交通大学学报,2008,27(2):302-304.
[25]鞠金艳,王金武,王金峰.基于BP神经网络的农机总动力组合预测方法[J].农业机械学报,2010,41(6):87-92.
[26]徐梅,晏福,刘振忠,等.灰色GM(1,1)-小波变换-GARCH组合模型预测松花江流域水质[J].农业工程学报,2016,32(10):137-142.
[27]莫颂娟,杨桂元,罗阳.基于IOWGA算子的中国GDP总量的组合预测[J].统计与决策,2015(16):4-7.
[28]胡彦,李秀美,陈华友.基于IOWA算子的税收组合预测模型[J].统计与决策,2009(10):33-35.
[2]Huang Z H,Lu H Z,Yang J F,et al.Application of a combination forecasting model in predicting the agricultural mechanization level in China[J].Revista de la Facultad de Ingenieria,2017,32(4):163-171.
[3]鞠金艳,王金武.黑龙江省农业机械化作业水平预测方法[J].农业工程学报,2009,25(5):83-88.
[4]张睿,高焕文.基于灰色GM(1,1)的农业机械化水平预测模型[J].农业机械学报,2009,40(2):91-95.
[5]BATES J M,GRANGER C W J.Combination of forecasts[J].Operations Research Quarterly,1969,20(4):451-468.
[6]Elliott G,Granger C W J,Timmerman A.Handbook of economic forecasting:forecast combinations[M].North Holland:Elsevier,2006.
[7]Liu S L,Hu Z Q,Chi X K.The research of power load forecasting method on combination forecasting model[J].Information Science and Engineering,2010,26:1273.
[8]吴静敏,左洪福,陈勇.基于免疫粒子群算法的组合预测方法[J].系统工程理论方法应用,2006,15(3):229-233.
[9]宋晓华,祖丕娥,伊静,等.基于改进GM(1,1)和SVM的长期电量优化组合预测模型[J].中南大学学报,2012,43(5):1803-1807.
[10]韩冬梅,牛文清,杨荣.线性与非线性最优组合预测方法的比较研究[J].科学情报,2007(11):1672-1678.
[11]Granger C W J,Ramanathan R.Improved Methods of Forecasting[J].Journal of Forecasting,1984,3(2):197-204.
[12]刘静,朱达荣.考虑自变及因变影响的农机总动力组合预测模型[J].农机化研究,2015,37(4):230-236.
[13]Shapley L S.A value for n-persons games[J].Annals of Mathematics Studies,1953,28:307-317.
[14]雷勋平,Robin Q.Shapley值法的改进及其应用研究[J].计算机工程与应用,2012,48(7):23-25.
[15]张淑娟,冯屾,介邓飞,等.基于Shapley值的农机装备水平组合预测[J].农业工程学报,2008,24(6):160-164.
[16]张淑娟,赵飞.基于Shapley值的农机总动力组合预测方法[J].农业机械学报,2008,39(5):60-64.
[17]Jeong R K K.Combining forecasts using optimal combination weight and generalized autoregression[J].Journal of Forecasting,2010,27(5):419-432.
[18]Poncela P,Rodriguez J,Sanchez M R,et al.Forecast combination through dimension reduction techniques[J].International Journal of Forecasting,2011,27(2):224-237.
[19]Costantini M,Pappalardo C.A hierarchical procedure for the combination of forecasts[J].International Journal of Forecasting,2010,26(4):725-743.
[20]Kolassa S.Combining exponential smoothing forecasts using Akaike weight[J].International Journal of Forecasting,2011,27(2):238-251.
[21]Yager R R.Induced aggregation operators[J].Fuzzy Sets and Systems,2003,137:59-69.
[22]林德花,袁振洲.基于IOWA算子的短时交通流预测方法研究[J].科学技术与工程,2013,13(25):7596-7600.
[23]陈华友,盛昭翰.一类基于IOWGA算子的组合预测新方法[J].管理工程学报,2005,19(4):39-42.
[24]施泽军,李凯.基于灰色模型和指数平滑法的集装箱吞吐量预测[J].重庆交通大学学报,2008,27(2):302-304.
[25]鞠金艳,王金武,王金峰.基于BP神经网络的农机总动力组合预测方法[J].农业机械学报,2010,41(6):87-92.
[26]徐梅,晏福,刘振忠,等.灰色GM(1,1)-小波变换-GARCH组合模型预测松花江流域水质[J].农业工程学报,2016,32(10):137-142.
[27]莫颂娟,杨桂元,罗阳.基于IOWGA算子的中国GDP总量的组合预测[J].统计与决策,2015(16):4-7.
[28]胡彦,李秀美,陈华友.基于IOWA算子的税收组合预测模型[J].统计与决策,2009(10):33-35.