Research articles

Construction of LM-BP Neural Network Prediction Model for the Softness of Flue-cured Tobacco Leaves Based on Fresh Leaf Appearance Parameters

  • 刘舜旗,柳 强,潘 洪,张洪霏,匡鹏飞,艾复清
Expand
  • (1. College of Agriculture, Guizhou University, Guiyang 550025, Guizhou China; 2. Guizhou Tobacco Company Qiandongnan Tobacco Branch Company, Kaili 556000, Guizhou China; 3. Guizhou Tobacco Company Zunyi Tobacco Branch Company, Zunyi 563000, Guizhou China; 4. Tobacco College, Guizhou University, Guiyang 550025, Guizhou China)

Received date: 2024-02-04

  Accepted date: 2024-03-25

  Online published: 2024-05-27

Abstract

In order to predict the softness of tobacco leaves by using the appearance parameters of fresh tobacco leaves, a LM-BP neural network prediction model was established by studying the relationship between the field ripening appearance parameters such as lightness and darkness (L), redness value (a), yellowness value (b), color saturation (C), hue angle (H), SPAD value, etc. and the softness of post-roasted leaves of YUNYU 87 with different retention numbers of the upper leaves. The results showed that the appearance characteristic parameters of upper leaves with different numbers of retained leaves were different, and the softness of tobacco leaves after baking was also different, and the value of softness after baking was lower in the number of retained leaves of 19 leaves than that in the number of leaves of 16-18 leaves, which ranged from 5.62 to 13.29 mN; There was a correlation between the parameters of tobacco appearance characteristics and the softness of post-roasted tobacco; stepwise regression analysis screened out the factors with greater influence on the softness of post-roasted tobacco as the number of retained leaves, L, H and SPAD value; The LM algorithm was used to replace the gradient algorithm to create the LM-BP neural network prediction model, and the training results showed that the prediction accuracy R2 was close to 1, the average absolute percentage error MAPE<5%, and the root-mean-square error RMSE<2. Properly retaining more leaves increases the softness of the tobacco after roasting; There was a correlation between the maturation appearance characteristics of tobacco leaves in the field and the softness of the tobacco after roasting; The LM-BP neural network was used to create a prediction model with high accuracy, which can be used for intelligent judgement of tobacco maturity in the field.

Cite this article

刘舜旗,柳 强,潘 洪,张洪霏,匡鹏飞,艾复清 . Construction of LM-BP Neural Network Prediction Model for the Softness of Flue-cured Tobacco Leaves Based on Fresh Leaf Appearance Parameters[J]. Subtropical Plant Science, 2024 , 53(2) : 152 -159 . DOI: 10.3969/j.issn.1009-7791.2024.02.008

References

[1] 高宪辉, 王松峰, 孙帅帅, 孙福山, 王勇, 程森, 卢晓华, 殷红, 高峻, 孙阳阳, 周平, 闫凯龙. 鲜烟成熟度颜色值指标及其判别函数研究[J]. 中国烟草学报, 2017, 23(1): 77–85.
[2] 张军刚, 王永利, 吕国新, 孙福山, 王耀斌, 徐秀红, 王爱华, 张国超, 任杰, 王松峰, 朱佩, 董淑君. 烤烟成熟过程中鲜烟颜色值与色素含量变化及相关分析[J]. 中国烟草科学, 2014,35(1): 54–60.
[3] 李悦, 符云鹏, 甄焕菊, 魏春阳, 王改丽, 唐浩. 烤烟烟叶颜色值和外观颜色变化分析[J]. 中国烟草科学, 2017,38(1): 78–84.
[4] 张世芬, 张德康, 孙武, 张东东, 秦言敏, 耿红梅, 余仕东, 王改丽, 张军刚, 韩家宝. 不同香型风格烤烟力学特性对烟叶外观质量的影响[J]. 河南农业科学, 2021,50(02): 58–65.
[5] 周立新, 陈丽平, 徐向丽, 魏新亮, 王雪云, 周文辉, 夏金元, 陈刚. 中间香型烟叶柔软性与烟叶质量的相关性研究[J]. 湖南农业科学, 2016(11): 67–70.
[6] 路登杰, 王轶, 李茹冰, 刘学超, 宋贺萱, 丁鼎, 刘畅, 栗翔, 李曼曼, 梁晓燕, 潘蕾. 不同部位烟叶化学成分与烟叶柔软度的关系[J]. 湖南文理学院学报(自然科学版), 2021,33(3):81–85.
[7] 付秋娟, 孙婷婷, 窦玉青, 程森, 蔡宪杰. 初烤烟叶柔软度及其与烟叶主要理化指标的关系[J]. 烟草科技, 2021,54(5):77–81.
[8] 常安然, 占俊文, 何宽信, 梁淑平, 吕果, 于建军. 烤烟烟叶柔软度与物理指标的关系[J]. 湖南农业大学学报(自然科学版), 2016,42(4):365–369.
[9] 张子颖, 过伟民, 徐文韬, 常乃杰, 许衡, 彭玉富, 张书伟. 基于偏最小二乘回归的烤烟感官品质关键外观特征指标筛选[J]. 轻工学报, 2023,38(4):90–97.
[10] 占俊文, 罗昭标, 何宽信, 王念磊, 秦言敏, 徐婧, 于建军. 烤烟柔软度与外观质量的关系分析[J]. 山东农业科学, 2017,49(6):26–29.
[11] 徐向丽, 宋卫武, 周文辉, 王雪云, 管杰, 周立新. 初烤烟叶柔软性检测及细胞结构比较[J]. 湖南农业科学, 2019(3):76–79.
[12] 刘梦红, 张巩亮, 李红宇, 杜俊, 赵海成, 吕坦, 钱永德. 基于BP人工神经网络的寒地水稻抗旱性综合评价[J]. 江苏农业科学, 2023,51(10):91–99.
[13] 赵丙秀, 董宁. 基于WOA-BP神经网络下马铃薯产量预测分析模型[J]. 农机化研究, 2024,46(3):47–51.
[14] 马兆务. 基于HP滤波和BP神经网络的小麦产量预测与可视化系统[D]: 河南农业大学农业工程与信息技术, 2021.
[15] 江显群, 陈武奋. BP神经网络与GA-BP农作物需水量预测模型对比[J]. 排灌机械工程学报, 2018,36(8):762–766.
[16] 柯丽华, 赵羡波, 周易, 胡钰萍, 兰立娟, 张星, 董桂全, 胡智予, 卢彬荣. 基于RGB偏态参数的烟草叶片氮含量估测[J]. 江苏农业科学, 2023,51(19):209–214.
[17] 张勇刚, 任志广, 徐志强, 刘建国, 张晓兵, 刘化冰, 夏琛, 程昌合. 离差最大化结合BP神经网络评价烟叶化学品质[J]. 作物杂志, 2023(1):190–195.
[18] 李峥, 王建峰, 程小强, 段史江, 史文强, 胡蓉花, 肖荣贵, 申洪涛. 基于BP神经网络的烤烟外观质量预测模型[J]. 西南农业学报, 2019,32(3):653–658.
[19] 顾金梅, 吴雪梅, 龙曾宇, 袁奎, 张磊. 基于BP神经网络的烟叶颜色自动分级研究[J]. 中国农机化学报, 2016,37(4):110–114.
[20] 芮雪,吴德佩. 基于LM-BP神经网络的采煤机液压系统故障诊断研究[J]. 煤炭技术, 2023, 42(7): 187–189.
[21] 许景辉,王雷,王一琛,等. 基于LM算法的土壤表层含水率遥感监测[J]. 农业机械学报, 2019, 50(6): 233–240.
[22] 陈志浩, 王建华, 龙拥兵, 兰玉彬, 刘军和, 熊弘依, 肖方军, 肖艺铭. 基于Spark的WOA-BP水稻产量预测[J]. 华南农业大学学报, 2023,44(4):613–618.
[23] 朱光耀, 谢方平, 陈凯乐, 代振维. 基于PSO-BP算法的油菜籽干燥工艺参数的优化[J]. 湖南农业大学学报(自然科学版), 2017,43(2):222–225.
[24] 黄艳雁, 姚健. 基于PSO-GA-BP神经网络的大米水分含量预测[J]. 粮食与饲料工业, 2023(3):56–60.
[25] 管钰晴, 唐冬梅, 傅云霞, 孙佳媛, 韩志国, 张波, 孔明, 曹程明, 雷李华. 穆勒椭偏标定方法中LM算法研究[J]. 红外与激光工程, 2020,49(08):168–176.
[26] 武圣江, 张长云, 郭亮, 谢良文, 朱广兵, 杨志晓, 涂永高, 谢已书. 贵州烤烟色素含量和颜色值随生育期的变化及其相关性[J]. 中国烟草科学, 2014,35(4):64–69.
[27] 关罗浩, 战磊, 张玺, 饶宇宁, 刘秋红, 高攀, 刘建书, 刘程炜. 响应面法和BP神经网络在烟叶拉力测定中的应用[J]. 广东农业科学, 2023,50(11):146–154.
[28] 樊闯, 赵子皓, 张雪松, 杨沈斌. 基于BP神经网络的一季稻发育期预测模型[J]. 浙江农业学报, 2023,35(2):434–444.
[29] 尹健康, 陈昌华, 邢小军, 谭俊, 姚进. 基于BP神经网络的烟田土壤水分预测[J]. 电子科技大学学报, 2010,39(6):891–895.
[30] 占俊文, 沈雪婷, 何宽信, 梁淑平, 李立新, 焦绍赫, 于建军. 江西烤烟柔软度与物理特性的关系分析及适宜区间研究[J]. 中国农业科技导报, 2017,19(1):131–137.
[31] 陈立军, 姚雪梅, 戴永强, 梁鹏程, 周锂, 阮彬洲, 彭田伟, 朱伟. 烤烟上部烟叶带茎烘烤对烟叶质量的影响[J]. 湖南农业科学, 2023(8):65–68.
[32] 詹军, 周芳芳, 张晓龙, 朱海滨, 何永菊, 王涛, 王柱石. 密集烤房与普通烤房烘烤过程中环境和烟叶颜色的变化[J]. 河南农业大学学报, 2015,49(1):17–21.
Outlines

/