XIE Pingping.Research on forecast of monthly sales volume of new - energy vehicles based on PCA - GRNN model[J].Journal of Yanbian University,2023,(01):77-82.
基于PCA - GRNN模型的新能源汽车月度销售量预测研究
- Title:
- Research on forecast of monthly sales volume of new - energy vehicles based on PCA - GRNN model
- 文章编号:
- 1004-4353(2023)01-0077-06
- Keywords:
- new - energy vehicles; principal component analysis; generalized regression neural network; sales forecast
- 分类号:
- F426.471
- 文献标志码:
- A
- 摘要:
- 为预测新能源汽车的月度销售量,提出了一种基于主成分分析(PCA)和广义回归神经网络(GRNN)相结合的预测模型——PCA - GRNN模型.首先,选取动力电池月份装车量、充电基础设施、电池级碳酸锂平均价格、交通和通信类居民消费价格指数、全国城镇调查失业率、汽车制造业工业生产者出厂价格指数等6个指标作为新能源汽车月度销售量的影响因子; 其次,利用主成分分析方法得到可代表6个影响因子的2个主成分,并利用Matlab神经网络工具箱的GRNN神经网络函数构建了广义回归神经网络模型; 最后,将2020—2022年间27个月度的统计数据分别输入到PCA - GRNN、PCA - BP和PCA - Elman模型中进行预测.结果显示, PCA - GRNN模型预测的新能源汽车月度销售量的平均相对误差(4.00%)低于PCA - BP模型和PCA - Elman模型预测的平均相对误差(分别为4.77%和4.29%),因此PCA - GRNN模型在预测新能源汽车销售量方面具有一定的实用性.
- Abstract:
- To forecast the monthly sales of new - energy vehicles, a prediction model based on the principal component analysis with generalized regression neural network(PCA - GRNN)was proposed.Firstly, six indicators were selected as the influencing factors of monthly sales of new - energy vehicles, such as the monthly load of power batteries, charging infrastructure, the average price of battery - grade lithium carbonate, transportation and communication consumer price index, national urban survey unemployment rate, and industrial producer ex - factory price index of the automobile manufacturing industry.Secondly, two principal components representing most of the information of six influencing factors were obtained by PCA, and a GRNN model was constructed using the GRNN neurnal network function of the Matlab neural network toolbox.Finally, the statistical data of 27 months from 2020 to 2022 were input into PCA - GRNN, PCA - BP(principal component analysis - back propagation)and PCA - Elman models for forecasting, respectively.The results show that the mean relative error of the PCA - GRNN prediction model of monthly new - energy vehicle sales(4.00%)was lower than that of the PCA - BP and PCA - Elman models(4.77% and 4.29%, respectively).Therefore, the PCA - GRNN model is practicability in predicting new - energy vehicle sales.
参考文献/References:
[1] 缪辉,唐晨添,罗露璐.基于ARIMA模型的新能源汽车销量预测[J].企业科技与发展,2020(10):97 - 98.
[2] 张双妮.基于多元回归模型的新能源汽车市场发展趋势预测[J].决策探索(中),2019(1):77.
[3] 余祥宽,廖秋明.我国新能源汽车销售量预测的数学模型研究[J].智库时代,2018(34):142.
[4] KITAPC O, ?ZEKICIO(ˇoverG)LU H, KAYNAR O, et al.The effect of economic policies applied in Turkey to the sale of automobiles: multiple regression and neural network analysis [J].Procedia - Social and Behavioral Sciences, 2014(148):653 - 661.
[5] 周彦福,王红蕾.我国新能源汽车月度销售量预测模型研究[J].软件导刊,2019,18(8):149 - 153.
[6] 张山山.基于PCA - BA - GRNN模型的公共自行车需求预测[D].兰州:兰州大学,2018.
[7] 梁达强.基于神经网络的K公司木浆销量预测[D].上海:上海交通大学,2016.
[8] 王红卫,林健良.基于改进的GRNN的销量预测[J].计算机工程与科学,2010,33(1):153 - 155.
[9] 韩小孩,张耀辉,孙福军,等.基于主成分分析的指标权重确定方法[J].四川兵工学报,2012,33(10):124 - 126.
[10] 缪志刚.基于BP神经网络的销售预测模型[D].苏州:苏州大学,2007.
[11] 于焱,苑鑫艺.我国新能源汽车市场销量预测[J].内燃机与配件,2021(6):179 - 180.
[12] 范萌萌.新能源汽车消费行为影响因素分析[D].济南:齐鲁工业大学,2020.
[13] 彭华.中国新能源汽车产业发展及空间布局研究[D].长春:吉林大学,2019.
[14] 郝建浩,唐德善,尹笋,等.基于广义回归神经网络模型的径流预测研究[J].水电能源科学,2016,34(12):49 - 52.
相似文献/References:
[1]黄焕宗,易晓明.福建省绿色创新驱动发展的综合评价研究[J].延边大学学报(自然科学版),2021,47(04):340.
HUANG Huanzong,YI Xiaoming.Comprehensive evaluation of green innovation driven development in Fujian Province[J].Journal of Yanbian University,2021,47(01):340.
[2]杨远志,黄焕宗.高等职业教育资源配置效率的非参数统计研究[J].延边大学学报(自然科学版),2023,(04):351.
YANG Yuanzhi,HUANG Huanzong.Non parametric statistics research on the efficiency of higher vocational education resource allocation[J].Journal of Yanbian University,2023,(01):351.
备注/Memo
收稿日期: 2022-05-22
基金项目: 福建省教育厅中青年教师教育科研项目(JAT201308); 黎明职业大学科研团队项目(LMTD202001)
作者简介: 谢萍萍(1981—),女,硕士,讲师,研究方向为管理系统工程.