新疆农业科学 ›› 2022, Vol. 59 ›› Issue (2): 485-492.DOI: 10.6048/j.issn.1001-4330.2022.02.027
• 农业装备工程与机械化·设施农业·畜牧兽医 • 上一篇 下一篇
韩坤林1(), 王钊英2, 杨会民3, 陈毅飞3, 蒋永新3(), 张佳喜1
收稿日期:
2021-01-02
出版日期:
2022-02-20
发布日期:
2022-03-22
通信作者:
蒋永新
作者简介:
韩坤林(1997-),男,四川通江人,硕士研究生,研究方向为农业信息技术,(E-mail) 228574983@qq.com
基金资助:
HAN Kunlin1(), WANG Zhaoying2, YANG Huimin3, CHEN Yifei3, JIANG Yongxin3(), ZHANG Jiaxi1
Received:
2021-01-02
Online:
2022-02-20
Published:
2022-03-22
Correspondence author:
JIANG Yongxin
Supported by:
摘要:
【目的】 研究温室番茄果实直径变化量的动态预测模型,为番茄所需水肥规律提供数据支持。【方法】 选择番茄果实横径为研究对象,以5株番茄果实膨大期的数据建立模型,采用主成分分析法对植物生理生态信息和环境信息进行分析,提取主要成分,以主成分为自变量,输出变量为因变量,建立一个包含空气温度、空气湿度、土壤含水率、叶片温度及果实横径的BP神经网络回归动态预测模型,并以3株番茄果实膨大期内所测的数据作为测试数据进行预测,比较预测值和实测值。【结果】 第1株番茄预测值与实测值的决定系数为(R2)0.964,均方根误差(RMSE)为0.238,第2株番茄预测值与实测值的决定系数(R2)为0.960,均方根误差(RMSE)为0.051,第3株番茄预测值与实测值的决定系数(R2)为0.951,均方根误差(RMSE)为0.047。【结论】 该模型可以预测温室短时内番茄果实直径变化量,可以用于新疆连栋温室内的秋季番茄果实直径变化预测,可根据预测量与实测量之间差值对水肥实行微调。
中图分类号:
韩坤林, 王钊英, 杨会民, 陈毅飞, 蒋永新, 张佳喜. 基于PCA-BPNN的温室番茄果实直径预测模型[J]. 新疆农业科学, 2022, 59(2): 485-492.
HAN Kunlin, WANG Zhaoying, YANG Huimin, CHEN Yifei, JIANG Yongxin, ZHANG Jiaxi. Prediction Model of Tomato Fruit Diameter in Greenhouses Based on PCA-BPNN[J]. Xinjiang Agricultural Sciences, 2022, 59(2): 485-492.
测量参数 Measurement Value | 型号 Type | 精度 Precision | 分辨率 Resolution | 测量范围 Measurement Range |
---|---|---|---|---|
空气温度Air Temperature | ATH-3ZT | ±0.5℃ | 0.1℃ | -40~60℃ |
空气湿度Air Relative Humidity | ATH-3ZH | ±2%RH | 0.1%RH | 3%~100%RH |
土壤湿度Soil Moisture | SMTE-3Z | ±2%VWC | 0.1%VWC | 0~100%VWC |
叶片温度Leaf Temperature | LT-4Z | 0.1℃ | ±0.2%℃ | 0~50℃ |
果实直径Fruit Diameter | FI-MZ | ±0.1% | 0.003 8 mm | 15~90 mm |
表1 植物生理生态数据采集系统性能指标
Table 1 The Performance index of Plant physiological an ecological data collection system
测量参数 Measurement Value | 型号 Type | 精度 Precision | 分辨率 Resolution | 测量范围 Measurement Range |
---|---|---|---|---|
空气温度Air Temperature | ATH-3ZT | ±0.5℃ | 0.1℃ | -40~60℃ |
空气湿度Air Relative Humidity | ATH-3ZH | ±2%RH | 0.1%RH | 3%~100%RH |
土壤湿度Soil Moisture | SMTE-3Z | ±2%VWC | 0.1%VWC | 0~100%VWC |
叶片温度Leaf Temperature | LT-4Z | 0.1℃ | ±0.2%℃ | 0~50℃ |
果实直径Fruit Diameter | FI-MZ | ±0.1% | 0.003 8 mm | 15~90 mm |
因子 Factor | 主成分Principal Component | ||
---|---|---|---|
1 | 2 | 3 | |
T | 0.972 7 | -0.148 0 | -0.103 9 |
RH | -0.882 9 | 0.083 2 | -0.102 1 |
V1 | 0.434 9 | 0.730 7 | 0.509 2 |
V2 | 0.100 6 | 0.870 2 | -0.476 4 |
LT | 0.921 5 | -0.203 8 | -0.173 0 |
表2 初始因子载荷矩阵
Table 2 Initial component matrix
因子 Factor | 主成分Principal Component | ||
---|---|---|---|
1 | 2 | 3 | |
T | 0.972 7 | -0.148 0 | -0.103 9 |
RH | -0.882 9 | 0.083 2 | -0.102 1 |
V1 | 0.434 9 | 0.730 7 | 0.509 2 |
V2 | 0.100 6 | 0.870 2 | -0.476 4 |
LT | 0.921 5 | -0.203 8 | -0.173 0 |
主成分 Principal Component | 初始特征值 Initial Eigenvalue | 提取平方和载加入 Extraction Sums of Squared Loadings | ||||
---|---|---|---|---|---|---|
合计 Total | 方差贡献率 Variance Contribution Rate(%) | 累计贡献率 Accumulated Variance Contribution Rate(%) | 合计 Total | 方差贡献率 Variance Contribution Rate(%) | 累计贡献率 Accumulated Variance Contribution Rate(%) | |
1 | 2.774 0 | 55.48 | 55.48 | 2.774 0 | 55.48 | 55.48 |
2 | 1.361 5 | 27.23 | 82.71 | 1.361 5 | 27.23 | 82.71 |
3 | 0.538 1 | 10.76. | 93.47 | 0.538 1 | 10.76 | 93.47 |
4 | 0.308 8 | 6.176 | 99.65 | |||
5 | 0.017 6 | 0.352 | 100.0 |
表3 主成分提取
Table 3 Principal component extraction and analysis
主成分 Principal Component | 初始特征值 Initial Eigenvalue | 提取平方和载加入 Extraction Sums of Squared Loadings | ||||
---|---|---|---|---|---|---|
合计 Total | 方差贡献率 Variance Contribution Rate(%) | 累计贡献率 Accumulated Variance Contribution Rate(%) | 合计 Total | 方差贡献率 Variance Contribution Rate(%) | 累计贡献率 Accumulated Variance Contribution Rate(%) | |
1 | 2.774 0 | 55.48 | 55.48 | 2.774 0 | 55.48 | 55.48 |
2 | 1.361 5 | 27.23 | 82.71 | 1.361 5 | 27.23 | 82.71 |
3 | 0.538 1 | 10.76. | 93.47 | 0.538 1 | 10.76 | 93.47 |
4 | 0.308 8 | 6.176 | 99.65 | |||
5 | 0.017 6 | 0.352 | 100.0 |
时序Time | 样本1Sample 1 | 样本2Sample 2 | 样本3Sample 3 | |||
---|---|---|---|---|---|---|
预测值 Predicted Value | 实测值 Measured Value | 预测值 Predicted Value | 实测值 Measured Value | 预测值 Predicted Value | 实测值 Measured Value | |
1 | 56.775 | 56.770 | 57.037 | 57.080 | 57.271 | 57.270 |
2 | 56.791 | 56.790 | 57.054 | 57.090 | 57.284 | 57.280 |
3 | 56.817 | 56.810 | 57.057 | 57.120 | 57.288 | 57.290 |
4 | 56.841 | 56.820 | 57.085 | 57.160 | 57.298 | 57.300 |
5 | 56.849 | 56.840 | 57.088 | 57.160 | 57.306 | 57.310 |
6 | 56.874 | 56.850 | 57.105 | 57.170 | 57.306 | 57.320 |
7 | 56.879 | 56.880 | 57.197 | 57.210 | 57.333 | 57.340 |
8 | 56.897 | 56.890 | 57.237 | 57.230 | 57.352 | 57.350 |
表4 样本1、2和3的预测值与实测值样本对比
Table 4 Comparison between the predicted and measured values of samples 1,2 and 3
时序Time | 样本1Sample 1 | 样本2Sample 2 | 样本3Sample 3 | |||
---|---|---|---|---|---|---|
预测值 Predicted Value | 实测值 Measured Value | 预测值 Predicted Value | 实测值 Measured Value | 预测值 Predicted Value | 实测值 Measured Value | |
1 | 56.775 | 56.770 | 57.037 | 57.080 | 57.271 | 57.270 |
2 | 56.791 | 56.790 | 57.054 | 57.090 | 57.284 | 57.280 |
3 | 56.817 | 56.810 | 57.057 | 57.120 | 57.288 | 57.290 |
4 | 56.841 | 56.820 | 57.085 | 57.160 | 57.298 | 57.300 |
5 | 56.849 | 56.840 | 57.088 | 57.160 | 57.306 | 57.310 |
6 | 56.874 | 56.850 | 57.105 | 57.170 | 57.306 | 57.320 |
7 | 56.879 | 56.880 | 57.197 | 57.210 | 57.333 | 57.340 |
8 | 56.897 | 56.890 | 57.237 | 57.230 | 57.352 | 57.350 |
[1] | 谢桂云, 张飞云. 新疆农业水土资源时空匹配研究[J]. 中国农村水利水电, 2020,(6):58-62. |
XIE Guiyun, ZHANG Feiyun. Research on spatio-temporal matching of Agricultural Water and Soil resources in Xinjiang[J]. China Rural Water Conservancy and Hydropower, 2020,(6):58-62. | |
[2] | 江景涛, 杨然兵, 鲍余峰, 等. 水肥一体化的研究进展与发展趋势[J]. 农机化研究, 2021, 43(5):1-9. |
JIANG Jingtao, YANG Ranbing, BAO Yufeng, et al. Research progress and development trend of water and fertilizer integration[J]. Agricultural Mechanization Research, 2021, 43(5):1-9. | |
[3] | Kale A P, Sonavane S P. IoT based smart Farming: Feature subset selection for optimized high-dimensional data using improved GA based approach for ELM[J]. Computers and Electronics in Agriculture, 2019, 56(1):225-232. |
[4] | 王艳丹, 方海东, 李建查, 等. 不同水肥管理对番茄品质和产量的影响[J]. 农学学报, 2016,(6):39-45. |
WANG Yandan, FANG Haidong, LI Jianzha, et al. Effects of different water and fertilizer management on tomato quality and yield[J]. Acta Agronomica Sinica, 2016,(6):39-45. | |
[5] | 卢晶晶, 刘广会, 赵义平, 等. 不同水肥处理对碱地番茄产量与品质的影响[J]. 园艺与种苗, 2020,(4):28-30. |
LU Jingjing, LIU Guanghui, ZHAO Yiping, et al. Effects of different water and fertilizer treatments on yield and quality of tomato in alkaline land[J]. Horticulture and Seedling, 2020,(4):28-30. | |
[6] | 陈思, 牛晓丽, 周振江, 等. 水肥供应对番茄糖酸含量的影响[J]. 节水灌溉, 2013,(9):18-22. |
CHEN Si, NIU Xiaoli, ZHOU Zhenjiang, et al. Effect of water and fertilizer supply on the content of tomato glycolic acid[J]. Water Saving Irrigation, 2013,(9):18-22. | |
[7] | 张传帅, 徐岚俊, 李小龙, 等. 日光温室主要环境参数对番茄本体长势的影响[J]中国农业大学学报, 2019,(10):118-124. |
ZHANG Chuanshuai, XU Lanjun, LI Xiaolong, et al. Effects of major environmental parameters on tomato growth in solar greenhouse[J] Journal of China Agricultural University, 2019,(10):118-124. | |
[8] | 吕天远. 基于株高和茎直径的温室番茄营养生长期水肥供应决策研究[D]. 镇江:江苏大学, 2017: 27-30. |
LÜ Tianyuan. Study on water and fertilizer supply decision during vegetative growth period of greenhouse tomatoes based on plant height and stem diameter[D]. Zhenjiang: Jiangsu University, 2017: 27-30. | |
[9] | 程智慧, 陈学进, 赖琳玲, 等. 设施番茄果实生长与环境因子的关系[J]. 生态学报, 2011, 31(3):742-748. |
CHENG Zhihui, CHEN Xuejin, LAI Linling, et al. Relationship between plant tomato fruit growth and environmental factors[J]. Chinese journal of ecology, 2011, 31(3):742-748. | |
[10] | 李慧霞, 尚春明, 杨瑞, 等. 增施CO2和补光对番茄生长和果实品质的影响[J]. 北方园艺, 2020,(1):1-6. |
LI Huixia, SHANG Chunming, YANG Rui, et al. Effects of CO2 and light supplementation on tomato growth and fruit quality[J]. Northern Horticulture, 2020,(1):1-6. | |
[11] | 胡笑涛, 王振昌, 马黎华. 番茄果实及茎秆微变化对分根区交替灌溉的响应[J]. 农业工程学报, 2014, 30(12):87-95. |
HU Xiaotao, WANG Zhenchang, MA Lihua. Response of Minor changes of tomato fruit and stem to Alternate Root Zone irrigation[J]. Journal of Agricultural Engineering, 2014, 30(12):87-95. | |
[12] | Heuvelink E. Tomato growth and yield: Quantitativeanalysisand syhthesis [D]. Netherlands: Phd Dissertation,Wageningen Agriculture University, 1996. |
[13] | 李邵, 苏炜宣, 宋少恒, 等. 光温耦合对日光温室番茄生长、产量与品质的影响[J]. 中国农学通报, 2019, 35(6):122-128. |
LI Shao, SU Weixuan, SONG Shaoheng, et al. Effects of light-temperature coupling on the growth, yield and quality of Tomato in solar greenhouse[J]. Chinese Journal of Agriculture, 2019, 35(6):122-128. | |
[14] | 武利明, 张喜春, 肖光辉, 等. 环境因子对番茄生长发育的影响[J]. 中国农学通报, 2014, 30(13):214-219. |
WU Liming, ZHANG Xichun, XIAO Guanghui, et al. Effects of environmental factors on tomato growth and development[J]. Chinese Agricultural Science Bulletin, 2014, 30(13):214-219. | |
[15] | 何晓群, 刘文卿. 应用回归分析[M]. 北京: 中国人民大学出版社, 2011:188-203. |
HE Xiaoqun, LIU Wenqing. Applied regression analysis [M]. Beijing: Renmin University of China Press, 2011:188-203. | |
[16] | 员玉良, 盛文溢. 基于主成分回归的茎直径动态变化预测方法[J]. 农业机械学报, 2015, 46(1):306-314. |
YUAN Yuliang, SHENG Wenyi. Prediction method of dynamic change of stem diameter based on principal component regression[J]. Journal of agricultural machinery, 2015, 46(1):306-314. | |
[17] | 朱晓林, 魏小红, 冯悦, 等. 基于多元统计分析的番茄性状研究[J]. 江苏农业科学, 2020,(7):174-181. |
ZHU Xiaolin, WEI Xiaohong, FENG Yue, et al. Studies on tomato traits based on multivariate statistical analysis[J]. Jiangsu Agricultural Sciences, 2020,(7):174-181. | |
[18] | 殷鉴, 刘新英, 张漫, 等. 春秋茬温室番茄光合速率预测模型通用性研究[J]. 农业机械学报, 2017,(S1):327-333. |
YIN Jian, LIU Xinying, ZHANG Man, et al. Study on generality of tomato photosynthetic rate Prediction Model in Spring and Autumn Stubble Greenhouse[J]. Journal of Agricultural Machinery, 2017,(S1):327-333. | |
[19] | 王何柱, 朱勇, 朱怡, 等. 基于主成分分析法的贵州芸豆品质评价[J]. 食品与机械, 2020, 36(3):48-53. |
WANG Hezhu, ZHU Yong, ZHU Yi, et al. Quality evaluation of Guizhou Kidney bean based on principal component analysis[J]. Food and Machinery, 2020, 36(3):48-53. | |
[20] | Yipeng Song, Johan A, Westerhuis Age K, et al. Logistic principal component analysis via non-convex singular value thresholding[J]. Chemometrics and Intelligent Laboratory Systems, 2020, (204):1-9. |
[21] | Hinojosa-Nava, R,. Mejía-Uriarte, E.V,. Sato-Berrú R.Y. Ammonia borane structural study by temperature through high-resolution Raman spectroscopy and principal component analysis[J]. Journal Pre-proof, 2020,(241):1-24. |
[22] | 孙浪涛, 田炜, 柴旭阳, 等. 基于BP神经网络的棉织物透气性能预测[J]. 武汉纺织大学学报, 2020,(4):15-18. |
SUN Langtao, TIAN Wei, CHAI Xuyang, et al. Prediction of cotton fabric breathability based on BP neural network[J]. Journal of Wuhan Textile University, 2020,(4):15-18. | |
[23] | 刘凇月, 冯禹菲, 张建海. 基于位移速率小波去噪的开挖事件判别方法[J]. 工程技术研究, 2018,(5):128-129. |
LIU Songyue, FENG Yufei, ZHANG Jianhai. Identification method of Excavation Event based on Displacement rate Wavelet Denoising[J]. Engineering Technology Research, 2018,(5):128-129. | |
[24] | 焦斌, 叶明星. BP神经网络隐层单元数确定方法[J]. 上海电机学院学报, 2013, 16(3):113-124. |
JIAO bin, YE Xingming. Method for determining the number of hidden layer units in BP neural network[J]. Journal of Shanghai University of Electrical Engineering, 2013, 16(3):113-124. | |
[25] | Xiao Li, Shier Dong, Hazem Samih Mohamed, et al. Prediction of Tubular T/Y-Joint SIF by GA-BP Neural Network[J]. Structural Engineering, 2020, 24(9):2706-2715. |
[26] | Bo Wang, Bowen Chen, Gongqing Wang, et al. Back propagation (BP) neural network prediction and chaotic characteristics analysis of free falling liquid film fluctuation on corrugated plate wall[J]. Annals of Nuclear Energy, 2020, (148):11-18. |
[27] | Daniel, A,., Baalamurugan, K M. A novel approach to minimize classifier computational overheads in Big Data using neural networks[J]. Physical Communication, 2020, (42):1-8. |
[28] | Yuan He, Zhiyi Meng, Hong Xu, et al. A dynamic model of evaluating differential automatic method for solving plane problems based on BP neural network algorithm[J]. Journal Pre-proof, 2020, (556):1-16. |
[29] | 张漫, 李婷, 季宇寒, 等. 基于BP神经网络算法的温室番茄CO2增施策略优化[J]. 农业机械学报, 2015, 46(8):235-245. |
ZHANG Man, LI Ting, JI Yuhan, et al. Optimization of greenhouse Tomato CO2 Application Strategy based on BP Neural Network Algorithm[J]. Journal of Agricultural Machinery, 2015, 46(8):235-245. | |
[30] | 沈沉, 赵文灿, 施金海, 等. 多隐层BP神经网络在模式预报中的简化应用[J]. 气象与环境科学, 2019, 42(4):127-132. |
SHEN Chen, ZHAO Wencan, SHI Jinhai, et al. Simplified application of BP neural network with multiple hidden layers in model prediction[J]. Meteorology and Environmental Sciences, 2019, 42(4):127-132. |
[1] | 赵连佳, 李淦, 徐麟, 颜国荣, 刘宁, 王帆, 邓超宏, 阿布都克尤木·阿不都热孜克, 王聪, 王威. 不同大豆品种在新疆生态区主要农艺性状表现及产量的相关分析[J]. 新疆农业科学, 2023, 60(7): 1663-1670. |
[2] | 方杰, 张杰, 马娟, 田翔, 于秀针, 冯斌. 基于神经网络PID算法的优化饲料配制系统[J]. 新疆农业科学, 2023, 60(4): 1003-1010. |
[3] | 杨明花, 刘强, 廖必勇, 彭云承, 布阿依夏木·那曼提, 达吾来·杰克山. 不完全双列杂交玉米组合抗倒伏综合评价[J]. 新疆农业科学, 2023, 60(4): 832-840. |
[4] | 刘敏, 靳娟, 阿布都卡尤木·阿依麦提, 樊丁宇, 郝庆, 杨磊, 赵晓梅, 耿文娟. 新疆3个鲜食枣品种的抗寒性评价[J]. 新疆农业科学, 2023, 60(4): 916-924. |
[5] | 郭阳, 郭俊先, 史勇, 刘丽, 方文艳, 刘彦岑. 特征波长筛选结合PCA-LSSVM对甜瓜叶片SPAD值的预测[J]. 新疆农业科学, 2023, 60(3): 616-623. |
[6] | 马旭, 赵英, 韩炜, 武胜利, 韩晓燕. 14种沙棘果实中氨基酸组成的主成分分析与综合评价[J]. 新疆农业科学, 2023, 60(2): 378-388. |
[7] | 曹艺洁, 史智勇, 玉苏甫·阿不力提甫, 艾沙江·买买提. 库尔勒香梨粗皮果矿质元素和氨基酸的含量分析[J]. 新疆农业科学, 2023, 60(2): 407-415. |
[8] | 杨明花, 王倩, 周新丽, 艾合买提江·马合木提, 彭云承, 艾尔居玛·吐卢汗, 布阿依夏木·那曼提, 侯丽丽, 刘强. 玉米杂交组合性状及产量的多重分析[J]. 新疆农业科学, 2022, 59(9): 2114-2122. |
[9] | 李春雨, 谭占明, 程云霞, 束胜, 何涛, 靳钰婕, 马新超, 杜佳庚, 张婧. 水肥耦合对沙培番茄生长发育及品质的影响[J]. 新疆农业科学, 2022, 59(9): 2158-2169. |
[10] | 由佳辉, 高林, 冯琳骄, 买迪妮阿依·买买提, 周龙, 李树德. 17个葡萄砧木品种叶片解剖结构与抗旱性分析[J]. 新疆农业科学, 2022, 59(8): 1896-1906. |
[11] | 樊丁宇, 靳娟, 阿布都卡尤木·阿依麦提, 杨磊, 赵晓梅, 郝庆. 5个鲜食枣品种果实品质特性的综合评价[J]. 新疆农业科学, 2022, 59(8): 1956-1964. |
[12] | 白世践, 户金鸽, 李超, 蔡军社, 王勇, 赵荣华, 陈光. 葡萄砧木苗期对混合盐碱的生理响应及耐盐碱性评价[J]. 新疆农业科学, 2022, 59(7): 1666-1679. |
[13] | 布哈丽且木·阿不力孜, 袁杰, 张燕红, 赵志强, 文孝荣, 贾春平, 康民泰, 唐福森, 王奉斌. 不同粳稻品种(系)稻米品质性状分析[J]. 新疆农业科学, 2022, 59(6): 1347-1355. |
[14] | 张哲, 热比耶·玉荪, 买买提·莫明, 吾买尔江·库尔班, 艾先涛, 高山. 新疆棉花生产品种机采农艺性状分析[J]. 新疆农业科学, 2022, 59(5): 1084-1092. |
[15] | 马越, 李玉姗, 赵连佳, 郭雅文, 宋羽, 许红军. 15份番茄种质资源在新疆适应性综合评价[J]. 新疆农业科学, 2022, 59(5): 1099-1109. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||