[1]赵 鑫,毋 涛,宋 田,等.基于组合模型的服装定制面辅料预测方法[J].计算机技术与发展,2023,33(01):214-220.[doi:10. 3969 / j. issn. 1673-629X. 2023. 01. 032]
　ZHAO Xin,WU Tao,SONG Tian,et al.Prediction Method of Garment Customized Surface Accessories Based on Combination Model[J].,2023,33(01):214-220.[doi:10. 3969 / j. issn. 1673-629X. 2023. 01. 032]
点击复制

基于组合模型的服装定制面辅料预测方法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
33
期数:
2023年01期
页码:
214-220
栏目:
新型计算应用系统
出版日期:
2023-01-10

文章信息/Info

Title:
Prediction Method of Garment Customized Surface Accessories Based on Combination Model
文章编号:
1673-629X(2023)01-0214-07
作者:
赵 鑫1 ; 毋 涛1 ; 宋 田2 ; 甘 霖3
1. 西安工程大学 计算机科学学院,陕西 西安 710600;
2. 山东如意毛纺服装集团股份有限公司,山东 济宁 272000;
3. 陕西服装工程学院,陕西 咸阳 712046
Author(s):
ZHAO Xin1 ; WU Tao1 ; SONG Tian2 ; GAN Lin3
1. School of Computer Science,Xi’an Polytechnic University,Xi’an 710600,China;
2. Shandong Ruyi Woolen Garment Group Co. ,Ltd. ,Jining 272000,China;
3. Shaanxi Institute of Garment Engineering,Xianyang 712046,China
关键词:
Prediction Method of Garment Customized Surface AccessoriesBased on Combination Model
Keywords:
clothing customization surface materials; demand forecast; ARIMA; GARCH; grid search; time series
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2023. 01. 032
摘要:
针对服装定制企业中根据工作人员个人经验采购面辅料造成面辅料过剩与不足的问题,以及仓库库存资源被过剩面辅料长期占用所导致仓库利用率过低的问题,构建了基于 GS-ARIMA-GARCH 　的服装定制面辅料需求量预测模型,将网格搜索、ARIMA 模型和 GARCH 模型相互组合在一起,进一步提升服装定制面辅料预测模型的预测精度。 实验结果表明,引入 GARCH 模型可以很好地　消除面辅料残差序列中出现的异方差现象;通过对 GS-ARIMA 预测模型和 GS-ARIMA-GARCH 预测模型进行精确性对比分析,利用评价指标 RMSE 值和 MAE 值对其进行判断,从结果可以看出 GS-ARIMA-GARCH 模型的预测准确精度相对于 GS-ARIMA 模型更加精准,面辅料需求量预测效果更好;通过对实际面辅料时间序列进行预测分析,从结果看出预测值与实际值的相对误差值在 　0. 5% ~ 2. 5% 范围内并且 R2 值结果为 0. 905 504,可以准确地预测出短期内面辅料的需求量,为企业制定合理的面辅料采购计划,从而提升仓库库存资源的利用率。
Abstract:
Aiming at the problem of surplus and shortage of surface materials caused by purchasing surface materials based on personal experience of staff in garment customization enterprises, and the problem of low utilization rate of warehouse caused by long - termoccupation of warehouse inventory resources by surplus surface materials, we construct the demand prediction model of garmentcustomization surface materials based on GS-ARIMA-GARCH. Grid search,ARIMA model and GARCH model are combined togetherto further improve the prediction accuracy of clothing customization surface and accessories prediction model. The experimental resultsshow that GARCH model can eliminate heteroscedasticity phenomenon in residue sequence of surface and auxiliary materials. Theaccuracy of GS-ARIMA prediction model and GS-ARIMA-GARCH prediction model was compared and analyzed,and the evaluationindexes RMSE value and MAE value were used to judge them. It can be seen from the results that the accuracy of GS-ARIMA-GARCHmodel is more accurate than that of GS-ARIMA model. The demand forecasting effect of flour and auxiliary materials is better. Throughanalyzing actual surface materials time sequence forecast,seen from the results and the actual and estimated values of the relative errorvalue is within 0. 5% ~ 2. 5% and R2 value is the result of 0. 905 504. It can accurately predict the short - term demand for surfacematerials,which formulate reasonable surface materials purchasing plan for the enterprise,so as to further enhance the utilization of thewarehouse inventory resources.
更新日期/Last Update: 2023-01-10