Prediction and control method of moisture content after cutting based on machine learning

Authors

GAO Li-xiu, Qujing Cigarette Factory, Hongyun Honghe Tobacco 〔Group〕 Co., Ltd., Qujing, Yunnan 655001, China
CHEN De-li, Qujing Cigarette Factory, Hongyun Honghe Tobacco 〔Group〕 Co., Ltd., Qujing, Yunnan 655001, China
WAN Xing-miao, Qujing Cigarette Factory, Hongyun Honghe Tobacco 〔Group〕 Co., Ltd., Qujing, Yunnan 655001, China
WANG Xing-hao, Qujing Cigarette Factory, Hongyun Honghe Tobacco 〔Group〕 Co., Ltd., Qujing, Yunnan 655001, China
ZHU Zhi-yuan, Qujing Cigarette Factory, Hongyun Honghe Tobacco 〔Group〕 Co., Ltd., Qujing, Yunnan 655001, China
LI Yong-hua, Qujing Cigarette Factory, Hongyun Honghe Tobacco 〔Group〕 Co., Ltd., Qujing, Yunnan 655001, China
SHE Di, Qujing Cigarette Factory, Hongyun Honghe Tobacco 〔Group〕 Co., Ltd., Qujing, Yunnan 655001, China
KONG WEI-xi, Qujing Cigarette Factory, Hongyun Honghe Tobacco 〔Group〕 Co., Ltd., Qujing, Yunnan 655001, China

Abstract

In order to improve the stability of the moisture content after cutting in the production process of silk making, the matching degree of the indexes between the moisture content at the outlet of loose moisture return, the moisture content at the outlet of moistening leaf feeding and the moisture content after cutting was guaranteed. The steady state data samples of “Yunyan (A)” brand silk production process was selected and the influence variables of the model were analyzed by Recursive Feature Elimination Method (RFE). Based on the temperature and humidity prediction model of the workshop, Monte Carlo simulation, Neural Network algorithm and XGBoost algorithm were used to establish the moisture content control model after cutting. The model was tested by comparing the predicted value with the actual value. Within the error range of ±0.15% of the process standard value, the accuracy of moisture content after cutting increased from 62.57% to 86.49%. CPK compliance rate increased from 91.44% to 97.30%. The prediction and control method of the moisture content after cutting based on machine learning can realize the coordination and accurate control of the process parameters before and after cutting, and effectively ensure the stability of the moisture content after cutting in the process of silk making.

Publication Date

4-28-2021

First Page

189

Last Page

194,211

DOI

10.13652/j.issn.1003-5788.2021.04.035

Recommended Citation

Li-xiu, GAO; De-li, CHEN; Xing-miao, WAN; Xing-hao, WANG; Zhi-yuan, ZHU; Yong-hua, LI; Di, SHE; and WEI-xi, KONG (2021) "Prediction and control method of moisture content after cutting based on machine learning," Food and Machinery: Vol. 37: Iss. 4, Article 35.
DOI: 10.13652/j.issn.1003-5788.2021.04.035
Available at: https://www.ifoodmm.cn/journal/vol37/iss4/35

References

[1] 钟文焱, 陈晓杜, 马庆文, 等. 基于多因素分析的烘丝机入口含水率预测模型的建立与应用[J]. 烟草科技, 2015, 48(5): 67-73.
[2] 李贵川, 谭科军, 唐毅, 等. 一种设定烘丝水分值的方法: 103750528A[P]. 2014-04-30.
[3] 王晓娟. 基于模糊综合与神经网络的制丝工艺多因素评价模型[J]. 食品与机械, 2017, 33(5): 204-210.
[4] 张亮. Python机器学习基础教程[M]. 北京: 人民邮电出版社, 2018: 161-213.
[5] 唐军, 唐丽, 文里梁, 等. 烟叶松散回潮工艺参数和出料质量的贝叶斯网络模型构建与预测[J]. 食品与机械, 2020, 36(9): 207-210.
[6] 庄嘉盛. 特征工程入门与实践[M]. 北京: 人民邮电出版社, 2019: 42-70.
[7] 闰星宇, 顾汉明, 肖逸飞, 等. XGBoost算法在致密砂岩气储层测井解释中的应用[J]. 石油地球物理勘探, 2019, 54(2): 447-455.
[8] 张家棋, 杜金. 基于XGBoost与多种机器学习方法的房价预测模型[J]. 现代信息科技, 2020(10): 15-18.
[9] 景钦隆, 吴琦琳, 鲁影, 等. 手足口病流行时间序列模型及其与气象因素联合预测研究[J]. 中国卫生统计, 2020, 37(3): 354-358.
[10] NARI S A, DIANE A, MICHAEL F. Application of SARIMAX model to forecast daily sales in food retail industry[J]. International Journal of Operations Research and Information Systems, 2016, 7(2): 1-21.
[11] 李自娟, 刘博, 高杨, 等. 卷烟制丝环节关键工序水分预测模型的建立与检验[J]. 食品与机械, 2020, 36(10): 190-196.
[12] 田润泽. 基于多种机器学习算法的波士顿房价预测[J]. 中国新通信, 2019, 21(11): 228-230.
[13] 许明燕. 基于ARIMA模型和BP神经网络模型的江苏省GDP预测分析[D]. 济南: 山东大学, 2020: 18-21.
[14] 刘承子, 刘丽英. 基于蒙特卡洛仿真在确定标准工作量中的仿真过程及分析[J]. 物流工程与管理, 2019, 41(11): 94-95.