Crops ›› 2023, Vol. 39 ›› Issue (1): 190-195.doi: 10.16035/j.issn.1001-7283.2023.01.028

Previous Articles     Next Articles

Chemical Quality Evaluation of Flue-Cured Tobacco Based on Maximization of Deviation and BP Neural Network

Zhang Yonggang(), Ren Zhiguang, Xu Zhiqiang, Liu Jianguo, Zhang Xiaobing, Liu Huabing, Xia Chen, Cheng Changhe()   

  1. China Tobacco Zhejiang Industrial Co., Ltd., Hangzhou 310024, Zhejiang, China
  • Received:2021-09-01 Revised:2021-12-06 Online:2023-02-15 Published:2023-02-22

RichHTML

2

PDF (PC)

203

Abstract:

Maximizing dispersion and the BP neural network were proposed as potential combined evaluation methods to address the inadequacies of the present combined evaluation methods of tobacco chemical quality. Four typical single evaluation approaches were chosen for the airticle. First, index weights were determined using the enhanced entropy weight method and the AHP method. Next, the combined evaluation value was calculated using the maximum dispersion principle. Finally, the combined evaluation value was inverted using BP neural network. The results showed that the average correlation coefficient between the maximum deviation combination evaluation value and the single evaluation method was 0.9822, which was higher than that of other combination evaluation methods, and the BP neural network had higher prediction accuracy and stability for the combined evaluation value, the relative error between the predicted value and the actual value was less than 3%, and the coefficient of determination was more than 0.9900. It showed that the deviation maximization combination evaluation method had better combination effects on the single evaluation method, and BP neural network improved the convenience of combination evaluation.

Key words: Flue-cured tobacco, Chemical quality, Improved entropy weight method, Maximum deviation, BP neural network

Table 1

Membership functions of chemical compositions"

函数类型
Types of membership functions		 指标
Index		 下限
Lower limits		 最优值下限
Optimal value of lower limits		 最优值上限
Optimal value of upper limits		 上限
Upper limits
抛物线型Parabolic 总糖 (%) 14.00 24.00 31.00 39.00
还原糖 (%) 10.00 22.00 30.00 37.00
烟碱 (%) 1.20 2.10 2.40 3.50
氯 (%) 0.10 0.30 0.80 1.00
总氮 (%) 0.80 1.70 2.00 3.10
糖碱比 6.00 12.50 13.50 18.00
氮碱比 0.45 0.85 0.95 1.35
S型S-shape 钾 (%) 0.80 － － 2.00

Table 2

Comparison of different weight methods"

指标
Index		 总糖
Total
sugar		 还原糖
Reducing
sugar		 烟碱
Nicotine		 糖碱比
Reducing sugar/
nicotine		 氯
Chlorine		 钾
Potassium		 总氮
Total
nitrogen		 氮碱比
Total nitrogen/
nicotine
熵值Entropy value 0.9227 0.9935 0.9810 0.9692 0.9215 0.9957 0.9985 0.9904
传统熵权法Traditional entropy weight method 0.3398 0.0284 0.0834 0.1356 0.3451 0.0190 0.0066 0.0420
改进熵权法Improved entropy weight method 0.2650 0.0621 0.0979 0.1319 0.2684 0.0560 0.0478 0.0709
AHP 0.0508 0.1016 0.2564 0.2351 0.0824 0.0946 0.0795 0.0995
综合赋权Combination weighting 0.1579 0.0819 0.1772 0.1835 0.1754 0.0753 0.0637 0.0852

Table 3

Results of four single evaluation methods"

方法
Method		 均值
Mean		 标准差
Standard deviation		 变异系数
Coefficient of variation		 变幅
Range
CCUI 0.6182A 0.1300 0.2103 0.5876
TOPSIS 0.5009C 0.1270 0.2535 0.6083
CPM 0.5673B 0.1643 0.2896 0.7275
GRDA 0.6396A 0.0991 0.1549 0.4727

Table 4

Pearson correlation analysis among four single evaluation methods"

方法Method CCUI TOPSIS CPM GRDA
CCUI 1.0000 0.9875** 0.9835** 0.9552**
TOPSIS 0.9875** 1.0000 0.9764** 0.9199**
CPM 0.9835** 0.9764** 1.0000 0.9141**
GRDA 0.9552** 0.9199** 0.9141** 1.0000

Table 5

Pearson correlation analysis between combination evaluation method and four single evaluation methods"

方法
Method		 离差最大化法
Maximizing deviation method		 平均值法
Mean value method		 Copeland法
Copeland method		 Borda法
Borda method
CCUI 0.9976** 0.9889** 0.9863** 0.9871**
TOPSIS 0.9897** 0.9734** 0.9736** 0.9742**
CPM 0.9916** 0.9748** 0.9751** 0.9745**
GRDA 0.9500** 0.9465** 0.9329** 0.9363**
平均相关系数Average correlation coefficients 0.9822 0.9709 0.9670 0.9680

Table 6

Prediction error of testing samples"

样品编号
Sample
number		 实测值
Measured
value		 预测值
Predicted
value		 绝对误差
Absolute
error		 相对误差
Relative
error (%)
1 0.5397 0.5378 0.0019 0.3520
2 0.4771 0.4840 0.0069 1.4462
3 0.4721 0.4702 0.0019 0.4025
4 0.6333 0.6239 0.0094 1.4843
5 0.6463 0.6489 0.0026 0.4023
6 0.7056 0.6916 0.0140 1.9841
7 0.3329 0.3373 0.0044 1.3217
8 0.6001 0.6035 0.0034 0.5666
9 0.5013 0.5063 0.0050 0.9974
10 0.4387 0.4396 0.0009 0.2052
11 0.6129 0.6240 0.0111 1.8111
12 0.6345 0.6374 0.0029 0.4571
13 0.4571 0.4582 0.0011 0.2406
14 0.6387 0.6322 0.0065 1.0177
15 0.6864 0.6920 0.0056 0.8159
16 0.6968 0.7008 0.0040 0.5741
17 0.5305 0.5355 0.0050 0.9425
18 0.4662 0.4610 0.0052 1.1154
19 0.6168 0.6148 0.0020 0.3243
20 0.3110 0.3196 0.0086 2.7653
21 0.6696 0.6689 0.0007 0.1045
22 0.3652 0.3641 0.0011 0.3012
23 0.8294 0.8305 0.0011 0.1326
24 0.6416 0.6459 0.0043 0.6702

Table 7

Prediction error and determination coefficient of training and test samples"

指标
Index		 样本量
Sample
size		 平均绝
对误差
Mean of
absolute
error		 平均相
对误差
Mean of
relative
error (%)		 R2 均方
根误差
Error of
root-mean-
square
训练集
Training sample		 71 0.0038 0.6198 0.9985 0.0054
预测集
Test sample		 24 0.0046 0.8514 0.9981 0.0057
[1] 陈征, 任志广, 范艺宽, 等. 基于灰色关联分析模型的烟叶化学成分评价研究进展. 中国农业科技导报, 2017, 19(5):129-137.
doi: 10.13304/j.nykjdb.2016.352
[2] 邓小华, 杨丽丽, 邹凯, 等. 烟稻轮作模式下烤烟增密减氮的主要化学成分效应分析. 植物营养与肥料学报, 2017, 23(4):991-997.
[3] 薛超群, 尹启生, 王信民, 等. 模糊综合评判在化学成分评价烟叶可用性中的应用. 烟草科技, 2007(4):62-64.
[4] 胡钟胜, 陈晶波, 周兴华, 等. 模糊评判与欧氏距离法在烟叶化学成分评价中的应用. 烟草科技, 2012(11):33-37.
[5] 王晓宾, 王军, 刘兰, 等. 广东烟区烤烟主要化学成分可用性评价. 中国烟草科学, 2019, 40(2):67-75.
[6] 郭亚军. 综合评价理论、方法及应用. 北京: 科学出版社, 2007.
[7] 黄瑞寅, 刘永强, 张晓龙, 等. DTOPSIS法在烟叶质量综合评价中的应用. 西南农业学报, 2013, 26(5):1801-1808.
[8] 陈伟. 关于TOPSIS法应用中的逆序问题及消除的方法. 运筹与管理, 2005(3):42-46.
[9] 徐泽桐, 刘亚相, 袁帅, 等. 化学成分指标对感官质量的影响及陕西省烟叶质量综合评价. 西南农业学报, 2018, 31(9):1953-1960.
[10] 李柏洲, 苏屹. 基于改进突变级数的区域科技创新能力评价研究. 中国软科学, 2012(6):90-101.
[11] 张晓兵, 夏琛, 项波卡, 等. 基于灰色关联分析的云南烟叶化学成分适宜性评价. 烟草科技, 2011(10):34-37.
[12] 卢秀萍. 灰色关联度分析和DTOPSIS法对烤烟新品种评价效果比较. 西南农业学报, 2006, 19(6):1014-1018.
[13] 招启柏, 陈晶波, 魏建荣, 等. 组合评价法在烟叶化学质量综合评价中的应用研究. 中国烟草学报, 2013, 13(3):1-6.
[14] 胡钟胜, 周兴华, 招启柏, 等. 典型烤烟产区气候指标的组合评价法. 烟草科技, 2013(6):82-85.
[15] 褚旭, 胡钟胜, 王珂清, 等. 云南植烟土壤肥力状况的组合评价法研究. 中国烟草学报, 2019, 25(2):48-54.
[16] 郭显光. 一种新的综合评价方法——组合评价法. 统计研究, 1995(5):56-59.
[17] 张发明, 刘志平. 组合评价方法研究综述. 系统工程学报, 2017, 32(4):557-569.
[18] 严富来, 张富仓, 范兴科, 等. 基于评价模型的宁夏沙土春玉米最佳灌水施氮量研究. 农业机械学报, 2020, 51(9):258-265.
[19] 李珠瑞, 马溪骏, 彭张林. 基于离差最大化的组合评价方法研究. 中国管理科学, 2013, 21(1):174-179.
[20] Funes E, Allouche Y, G Beltrán, et al. A review:artificial neural networks as tool for control food industry process. Journal of Sensor Technology, 2015(1):28-43.
[21] Ma Y, Li L, Yin Z, et al. Research and application of network status prediction based on BP neural network for intelligent production line. Procedia Computer Science, 2021, 183(20):189-196.
doi: 10.1016/j.procs.2021.02.049
[22] 彭黔荣, 蔡元青, 王东山, 等. 根据常规化学指标识别烟叶品质的BP神经网络模型. 中国烟草学报, 2005, 11(5):19-25.
[23] 汪健, 路晓崇, 王鹏, 等. BP神经网络模型在烟草烘烤过程中叶温变化预测中的应用. 南方农业学报, 2013, 44(8):1351-1354.
[24] 任广伟, 王秀芳, 王新伟, 等. BP神经网络在烟蚜发生程度预测中的应用. 华北农学报, 2008, 23(增2):373-376.
[25] 杨杰, 王昌全, 冯广林, 等. 四川凉山烟区红大烟叶化学成分可用性综合评价. 烟草科技, 2013(11):48-51.
[26] 秦海霞, 张玉顺, 张昆, 等. 基于TOPSIS黄淮海平原井灌区冬小麦调亏灌溉的多目标优化. 作物杂志, 2021(3):202-209.
[27] 宁东贤, 赵玉坤, 闫翠萍, 等. 山西省南部花生品种产量稳定性的模型分析及评价. 作物杂志, 2017(3):39-43.
[28] 李绍飞, 唐宗, 王仰仁, 等. 突变评价法的改进及其在节水型社会评价中的应用. 水力发电学报, 2012(5):51-58.
[29] 张阳, 张伟, 赵威军, 等. 基于主成分与灰色关联分析的饲草小黑麦品种筛选与配套技术研究. 作物杂志, 2020(3):117-124.
[30] 刘文婷, 张新军, 杨才, 等. 裸燕麦营养品质的差异性及形成因子解析. 作物杂志, 2020(5):140-147.
[31] 欧阳森, 石怡理. 改进熵权法及其在电能质量评估中的应用. 电力系统自动化, 2013, 37(21):156-159.
[32] 刘红雨, 刘友存, 孟丽红, 等. 熵权法在水资源与水环境评价中的研究进展. 冰川冻土, 2022, 44(1):299-306.
doi: 10.7522/j.issn.1000-0240.2021.0131
[33] 欧阳森, 刘天马, 杨墨缘. 考虑综合经济损失的电压暂降监测优化配置方法. 广东电力, 2021, 34(4):34-42.
[34] 陈海汉, 陈慧敏. 中国高校区域性科技活动能力组合评价. 科技管理研究, 2016(2):106-111.
[35] 李娒竹. 基于PSO-H-BP神经网络的故障诊断技术研究. 南昌:南昌大学, 2008.
[36] Sadeghi B H M. A BP-neural network predictor model for plastic injection molding process. Journal of Materials Processing Technology, 2000, 103(3):411-416.
doi: 10.1016/S0924-0136(00)00498-2
[37] 范喜林. 一种基于BP神经网络的皮带跑偏检测方法. 能源技术与管理, 2022, 47(3):116-118.
[38] 沈花玉, 王兆霞, 高成耀, 等. BP神经网络隐含层单元数的确定. 天津理工大学学报, 2008, 24(5):13-15.
[39] 李强, 周冀衡, 杨荣生, 等. 曲靖烤烟主要化学成分及其协调性空间分布. 生态学杂志, 2012, 31(4):862-869.
[40] 高远. 四川省烤烟质量研究及综合评价. 郑州:河南农业大学, 2010.
[41] 邓小华, 周冀衡, 李晓忠, 等. 湘南烟区烤烟常规化学指标的对比分析. 烟草科技, 2006(9):22-26.
[42] 褚旭, 王珂清, 魏建荣, 等. 基于综合赋权法的烤烟烟叶质量评价. 烟草科技, 2019, 52(9):31-38.
[43] 周惠成, 张改红, 王国利. 基于熵权的水库防洪调度多目标决策方法及应用. 水利学报, 2007, 38(1):100-106.
[44] 李英海, 周建中. 基于改进熵权和Vague集的多目标防洪调度决策方法. 水电能源科学, 2010, 28(6):32-35.
[45] 张有贤, 李二强, 罗东霞, 等. 基于AHP-熵权法的兰州市水环境安全模糊综合评价. 安全与环境学报, 2020, 20(2):709-718.
[46] 郭亚军, 易平涛. 一种基于整体差异的客观组合评价法. 中国管理科学, 2006, 14(3):60-64.
[47] 孙湛, 马海涛. 基于BP神经网络的京津冀城市群可持续发展综合评价. 生态学报, 2018, 38(12):343-353.
[48] 李丽, 张海涛. 基于BP人工神经网络的小城镇生态环境质量评价模型. 应用生态学报, 2008, 19(12):2693-2698.
[1] Wang Dequan, Liu Yang, Liu Jiang, Chen Keling, Wang Yi, Du Chuanyin, Du Yuhai, Ma Xinghua. Research Progress of Furrow and Ridge Rain-Harvesting Farming Technology and its Application Prospects in Flue-Cured Tobacco Production [J]. Crops, 2023, 39(1): 1-5.
[2] Chen Dong, Zou Jing, Guo Ganggang, Dai Wendian, Song Shaoguang, Huang Ying. Effects of Different Specifications of Seedling Trays on Quality and Main Physiological Characteristics of Tobacco Seedlings [J]. Crops, 2023, 39(1): 129-135.
[3] Li Diqin, Yao Shaoyun, Wang Qing, Yi Ke, Liu Yiyun, Tang Xiaoming, Peng Yuanyuan, Fu Changwu. Effects of Different Nitrogen Sources on the Growth and Development of Tobacco Seedlings [J]. Crops, 2023, 39(1): 201-206.
[4] Wang Yuan, Wang Jiming, Nian Fuzhao, Zheng Yuanxian, Xu Yinlian, Li Cuifen, Cui Yongquan, Zhang Qifu, Zhao Leifeng, Liao Xiaolin, He Yuansheng. Effects of Continuous Cropping with Rice Hull Biochar on Soil Physical and Chemical Properties and Growth of Flue-Cured Tobacco [J]. Crops, 2023, 39(1): 219-225.
[5] Chen Yan, Chen Qiang, He Yi, Yu Huiping, Gao Junyi, Zhao Erwei, Lu Yingang. Effects of Tobacco Planting Ecoregions, Varieties and Their Interactions on Polyphenol Content and Quality of Flue-Cured Tobacco [J]. Crops, 2022, 38(6): 132-138.
[6] Zhang Mingfa, Zhang Sheng, Teng Kai, Chen Qianfeng, Tian Minghui, Jiang Zhimin, Chao Jin, Jian Panfeng, Deng Xiaohua. Effects of Fertilizing with Straw Biochar on Soil pH and Root Growth of Flue-Cured Tobacco in Huayuan, Hunan [J]. Crops, 2022, 38(6): 193-200.
[7] Zhu Lin, Cao Xiang, Deng Xiaohua, Hu Risheng, Pei Xiaodong, Xiang Shipeng, Xiao Zhijun, Wang Weimin, Zhang Cheng, Jiang Zhimin. Characteristics of Water Loss and Pigment Degradation of Xiangyan No.7 Tobacco Leaves during Curing Process [J]. Crops, 2022, 38(5): 174-179.
[8] Jia Guotao, Zhang Junling, Wei Zhuangzhuang, Yuan Qishan, Wang Baolin, Wang Xiaoyu, Ma Shengtao, Yang Xinling, Zhang Ziying, Zhang Shiying, Jia Shiwei, Chen Yang, Liu Huimin. Research on the Regional Characteristics of Contents of Free Amino Acids in Flue-Cured Tobacco Based on Factor Analysis and Cluster Analysis [J]. Crops, 2022, 38(5): 208-214.
[9] Sun Kai, Liang Long, Li Zhongbai. Sustainability Evaluation of the Red Rice and Flue-Cured Tobacco Crop System Based on the Improved Emergy Model——A Case Study of Panzhou City, Guizhou Province [J]. Crops, 2022, 38(4): 146-153.
[10] Liu Xinya, Chen Xiaolong, Feng Yake, Liu Yang, Duan Weidong, An Xueqiang, Chen Fayuan, Cao Xingbing, Zhao Yuanyuan, Shi Hongzhi. Study on the Suitable Harvest Date of High Availability Upper Leaves of Flue-Cured Tobacco in Southwestern Guizhou [J]. Crops, 2022, 38(4): 227-235.
[11] Wei Xiaokai, Jing Yanqiu, He Jixian, Gu Huizhan, Lei Qiang, Yu Shikang, Zhang Qili, Li Junju. Alleviating Effect of Exogenous Spermidine on Flue-Cured Tobacco Seedlings under Drought Stress [J]. Crops, 2022, 38(3): 143-148.
[12] Yang Yingyue, Liu Hui, Wang Longfei, Zhao Zhe, Feng Xiaohu, Lai Miao, Zhao Mingqin. Effects of Different Fertilizer Types on Tobacco Planting Soil and Quality of Flue-Cured Tobacco [J]. Crops, 2022, 38(3): 187-193.
[13] Zhang Xiaoquan, Jia Zhenyu, Li Juxu, Li Hongchen, Wang Baoxiang, Wang Jian, Shi Gang, Wang Chuan, Wu Yunjie. Effects of Different Root-Promoting Practices on Potassium Metabolism at Mature Stage of Flue-Cured Tobacco in Southern Anhui [J]. Crops, 2022, 38(3): 205-210.
[14] Yun Fei, Ren Tianbao, Yin Quanyu, Jin Shuangzhen, Zheng Cong, Jin Lei, Li Jingjing, Liu Guoshun, Yang Xitian. Effects of Calcium by Foliage Spraying on Photosynthesis Physiology Characteristics of Flue-Cured Tobacco under Light Stress [J]. Crops, 2022, 38(2): 143-152.
[15] Wang Chuliang, Song Wenfeng, Guan Luohao, Xie Jin, Huang Hao, Li Wangyang, Wang Wei. Effects of Film Mulching Method and Transplanting Seedling Age on Yield and Quality of Flue-Cured Tobacco in Honghe [J]. Crops, 2021, 37(6): 95-100.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!