基于神经网络MIV算法的烟叶加料均匀性预测分析

doi:10.16180/j.cnki.issn1007-7820.2019.10.008

摘要/Abstract

摘要：

为了预测分析不同工况下烟叶加料的均匀性,文中提出一种基于神经网络MIV算法的烟叶加料工艺参数优化方法。通过对烟叶加料的工艺参数进行神经网络训练,利用MIV计算出各参数与加料均匀性的相关性,确定影响加料均匀性的关键工艺指标。文中进行了相应的试验证明,结果显示相对误差被控制在5%以内。由此结果推出影响加料均匀性的关键工艺指标为:排潮开度、工艺流量、气体压力及料液流量。其中,排潮开度、工业流量及料液流量与加料均匀性负相关,气体压力与加料均匀性正相关;经过MIV进行变量剔除的神经网络的预测性较好。

关键词: 神经网络, MIV, 预测, 均匀性, 烟叶加料, MATLAB

Abstract:

In order to predict and analyze the uniformity of tobacco leaf feeding under different working conditions, a method based on MIV algorithm was proposed in this paper. The neural network training was carried out on the process parameters of tobacco leaf feeding, and the correlation between each parameter and feeding uniformity was calculated by using MIV. The key index influencing the uniformity of feeding was found, and the error was less than 5%. The key indexes that affected the uniformity of feeding were the opening of discharge, process flow, gas pressure and feed liquid flow. The discharge opening, industrial flow and feed liquid flow were negatively correlated with the feeding uniformity. The gas pressure was positively related to the uniformity of feed. The neural network obtained by MIV method was more predictive.

Key words: neural network, MIV, prediction, feeding uniformity, tobacco feeding, MATLAB

中图分类号:

TP183

陈霖,袁锐波. 基于神经网络MIV算法的烟叶加料均匀性预测分析[J]. 电子科技, 2019, 32(10): 39-42.

CHEN Lin,YUAN Ruibo. Forecast and Analysis of Tobacco Leaf Feeding Uniformity Based on Neural Network MIV Algorithm[J]. Electronic Science and Technology, 2019, 32(10): 39-42.

图/表 7

图1

图2

图3

表1

图4

图5

图6

参考文献 16

[1]	孙志涛, 魏明杰, 王东 , 等. 叶丝加料和片烟加料对一、二、三类卷烟感官质量的影响[J]. 烟草科技, 2017,50(1):74-79.
	Sun Zhitao, Wei Mingjie, Wang Dong , et al. Effects of cut strip casing and strip casing on sensory quality of cigarettes of Category Ⅰ, Ⅱ and Ⅲ[J]. Tobacco Science & Technology, 2017,50(1):74-79.
[2]	刘泽, 何邦华, 陈林 , 等. 基于料液施加效果的加料工序关键工艺参数优化[J]. 烟草科技, 2015,48(4):71-75.
	Liu Ze, He Banghua, Chen Lin , et al. Optimization of key parameters in casing process based on casing effect[J]. Tobacco Science & Technology, 2015,48(4):71-75.
[3]	白万明, 潘峰, 杨全忠 , 等. 复烤加料加香工艺的设计与应用[J]. 中国烟草学报, 2017,23(4):15-21.
	Bai Wanming, Pan Feng, Yang Quanzhong , et al. Design and application of rebaking and adding materials and aroma[J]. Acta Tabacaria Sinica, 2017,23(4):15-21.
[4]	赵俊 . 卷烟制丝加料工序强度对烟叶质量影响研究[D]. 昆明:昆明理工大学, 2016.
	Zhao Jun . Study on the influence of the strength of the process of tobacco silk processing on the quality of tobacco leaves[D]. Kunming:Kunming University Science and Technology, 2016.
[5]	韩子健, 李浙昆 . KAS松散回潮加料机的改进研究[J]. 机械制造, 2016,54(1):26-28.
	Han Zijian, Li Zhekun . Study on the improvement of KAS loose moisture regain feeder[J]. Journal of Machinery, 2016,54(1):26-28.
[6]	郑飞, 李媛, 刘德强 , 等. 基于图像处理的烟片加料均匀性评价方法[J]. 烟草科技, 2015,48(11):65-68.
	Zheng Fei, Li Yuan, Liu Deqiang , et al. Method for evaluating casing uniformity of tobacco strips based on image processing[J]. Tobacco Science & Technology, 2015,48(11):65-68.
[7]	樊杰, 王菊, 夏莺莺 , 等. 方差分析法在批内烟叶化学成分均匀性评价中的应用[J]. 烟草科技, 2013,46(1):26-32.
	Fan Jie, Wang Ju, Xia Yingying , et al. Application of variance analysis in the evaluation of uniformity of chemical composition of tobacco leaves in batch[J]. Tobacco Science & Technology, 2013,46(1):26-32.
[8]	颜克亮, 武怡, 曾晓鹰 , 等. 二次加料技术在烤烟型卷烟工艺中的应用[J]. 烟草科技, 2012,45(5):5-9.
	Yan Keliang, Wu Yi, Zeng Xiaoying , et al. Application of secondary feed technology in flue-cured tobacco rolling process[J]. Tobacco Science & Technology, 2012,45(5):5-9.
[9]	朱东华, 来备战, 刘跃忠 , 等. 改进烟叶制丝工艺的加料系统[J]. 华东科技:学术版, 2014(8):324-324.
	Zhu Donghua, Lai Beizhan, Liu Yuezhong , et al. Improved feeding system of tobacco leaf silk making process[J]. East China Science and Technology:Academic Edition, 2014(8):324-324.
[10]	袁娜, 杨鹏, 刘作军 . 利用平均影响值和概率神经网络的步态识别[J]. 哈尔滨工程大学学报, 2015(2):181-185.
	Yuan Na, Yang Peng, Liu Zuojun . Gait recognition using average influence value and probability neural network[J]. Journal of Harbin Engineering University, 2015(2):181-185.
[11]	张金国, 王小君, 朱洁 , 等. 基于MIV的BP神经网络磷酸铁锂电池寿命预测[J]. 电源技术, 2016,40(1):50-52.
	Zhang Jinguo, Wang Xiaojun, Zhu Jie , et al. Life prediction of iron-phosphate lithium battery in BP neural network based on MIV[J]. Power Technology, 2016,40(1):50-52.
[12]	何邦华, 罗璟, 刘泽 , 等. 烟丝物理质量的制丝工艺神经网络模型及其评价[J]. 云南农业大学学报:自然科学版, 2016,31(5):874-879.
	He Banghua, Luo Jing, Liu Ze , et al. Silk processing neural network model of physical quality of tobacco and its evaluation[J]. Journal of Yunnan Agricultural University: Natural Science Edition, 2016,31(5):874-879.
[13]	崔金魁, 胡国兵, 于新刚 . 模拟电路故障诊断的神经网络优化方法综述[J]. 电子科技, 2014,27(2):134-137.
	Cui Jinkui, Hu Guobing, Yu Xingang . Overview of neural network optimization methods for analog circuit fault diagnosis[J]. Electronic Science and Technology, 2014,27(2):134-137.
[14]	邓玉梅 . 基于蚁群优化的BP神经网络目标威胁估计方法[J]. 电子科技, 2016,29(7):33-35.
	Deng Yumei . Target threat estimation method of BP neural network based on ant colony optimization[J]. Electronic Science and Technology, 2016,29(7):33-35.
[15]	高丽媛, 董甲 . 基于改进BP神经网络的洪峰预测模型[J]. 电子科技, 2015,28(3):41-43.
	Gao Liyuan, Dong Jia . Flood peak prediction model based on improved BP neural network[J]. Electronic Science and Technology, 2015,28(3):41-43.
[16]	崔智全, 付旭云, 钟诗胜 , 等. 小波网络平均影响值的航空发动机自变量筛选[J]. 计算机集成制造系统, 2013,19(12):3062-3067.
	Cui Zhiquan, Fu Xuyun, Zhong Shisheng , et al. Screening of aero engine independent variables for the average impact value of wavelet networks[J]. Computer Integrated Manufacturing System, 2013,19(12):3062-3067.

	排潮开度	滚筒转速	工艺流量	气体温度	气压	料液温度	料液流量
均匀性1	-1.56	-0.14	-1.18	0.10	1.12	0.09	-0.98
均匀性2	-1.24	-0.09	-1.23	0.12	1.08	0.06	-0.89
均匀性3	-1.01	-0.09	-0.91	0.05	0.89	0.03	-0.12
均匀性4	-1.22	-0.18	-1.45	0.16	1.69	0.11	-1.02
均匀性5	-1.60	-0.11	-1.22	0.20	1.02	0.08	-0.97