Prediction Model of Tomato Fruit Diameter in Greenhouses Based on PCA-BPNN

doi:10.6048/j.issn.1001-4330.2022.02.027

Xinjiang Agricultural Sciences ›› 2022, Vol. 59 ›› Issue (2): 485-492.DOI: 10.6048/j.issn.1001-4330.2022.02.027

• Agricultural Equipment Engineering and Mechanization·Facility Agriculture·Animal Husbandry Veterinarian • Previous Articles Next Articles

Prediction Model of Tomato Fruit Diameter in Greenhouses Based on PCA-BPNN

HAN Kunlin¹(), WANG Zhaoying², YANG Huimin³, CHEN Yifei³, JIANG Yongxin³(), ZHANG Jiaxi¹

1. College of Mechanical and Electrical Engineering,Xinjiang Agricultural University,Urumqi 830052, China
2. Xinjiang Academy of Agricultural Sciences, Urumqi 830091, China
3. Research Institute of Agricultural Mechanization,Xinjiang Academy of Agricultural Sciences, Urumqi 830091, China

Received:2021-01-02 Online:2022-02-20 Published:2022-03-22
Correspondence author: JIANG Yongxin
Supported by:
National Key R & D Program “Research and Development of Intelligent Fine Production Technology and Equipment for Vegetables”(2017YFD0701301-03);Pre-Research of Key Program of Xinjiang Academy of Agricultural Sciences “Research on Intelligent Control Equipment for Facilities Based on Multi-source Information and Cloud Platform”(xjzdy-002)

基于PCA-BPNN的温室番茄果实直径预测模型

韩坤林¹(), 王钊英², 杨会民³, 陈毅飞³, 蒋永新³(), 张佳喜¹

1.新疆农业大学机电工程学院,乌鲁木齐 830052
2.新疆农业科学院,乌鲁木齐 8300091
3.新疆农业科学院农业机械化研究所,乌鲁木齐 830091

通讯作者: 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:
国家重点研发计划“蔬菜智能化精细生产技术与装备研发”(2017YFD0701301-03);新疆农业科学院重点项目前期预研专项“基于多源信息及云平台的设施智能化管控装备技术研究”(xjzdy-002)

Abstract

Abstract:

【Objective】 To study the dynamic prediction model of tomato fruit diameter variation in greenhouse, which can provide certain decision support for the law of water and fertilizer required by tomatoes. 【Methods】 Based on the fruit diameter as the research object, with five of tomato fruit enlargement period data as a model, using principal component analysis (PCA) to perform the plant physiological ecology and environment information analysis, extract the main ingredients, again with the principal components as independent variables, output variables as the dependent variable, to establish BP neural network regression dynamic prediction model including air temperature, air humidity, soil moisture content, leaf temperature and fruit diameter. In addition, the data measured in the fruit expansion period of 3 tomato plants were used as the test data to predict and compare the predicted and measured values. 【Results】 The first decision coefficient for tomato plant predicted and the measured values (R²) was 0.964, and the root mean square error (RMSE) was 0.238; The second tomato plant decision coefficient of the predicted values and the measured values (R²) was 0.960, and the root mean square error (RMSE) was 0.051; The first three decision coefficient of tomato predicted and the measured values (R²) was 0.951, and the root mean square error (RMSE) was 0.047. 【Conclusion】 The model can predict the change of tomato fruit diameter in the greenhouse in a short time, and it can be used to predict the change of tomato fruit diameter in the autumn in the greenhouse in Xinjiang. The water and fertilizer can be fine-tuned according to the difference between the predicted value and the actual measurement.

Key words: principal component analysis; regression model; neural network; greenhouse tomato

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。

关键词: 主成分分析, 回归模型, 神经网络, 温室番茄

CLC Number:

S164.2
S12

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.

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.

Figures/Tables 7

References 30

[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.

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

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
因子 Factor	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

因子 Factor	主成分Principal Component
因子 Factor	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
主成分 Principal Component	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

Prediction Model of Tomato Fruit Diameter in Greenhouses Based on PCA-BPNN

基于PCA-BPNN的温室番茄果实直径预测模型

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 7

References 30

Related Articles 15

Recommended Articles

Metrics

时序Time	样本1Sample 1		样本2Sample 2		样本3Sample 3
时序Time	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]	ZHAO Lianjia, LI Gan, XU Lin, YAN Guorong, LIU Ning, WANG Fan, DENG Chaohong, Abudukeyoumu Abudurezike, WANG Cong, WANG Wei. Analysis of the main characters of soybean varieties in Xinjiang and their correlation with yield [J]. Xinjiang Agricultural Sciences, 2023, 60(7): 1663-1670.
[2]	LU Tao, ZENG Qingtao, ZHANG Wen, WANG Wenbo, WANG Zhengyang, YANG Rui, SUN Yuyan. Comprehensive evaluation of cotton yield and quality by principal component analysis and grey correlation analysis [J]. Xinjiang Agricultural Sciences, 2023, 60(5): 1099-1109.
[3]	FANG Jie, ZHANG Jie, MA Juan, TIAN Xiang, YU Xiuzhen, FENG Bin. Research and optimization of feed preparation system based on neural network PID algorithm [J]. Xinjiang Agricultural Sciences, 2023, 60(4): 1003-1010.
[4]	YANG Minghua, LIU Qiang, LIAO Biyong, PEN Yuncheng, Buayxam Namat, Dawulai Jiekeshan. Comprehensive evaluation of lodging resistance of NCII maize combinations [J]. Xinjiang Agricultural Sciences, 2023, 60(4): 832-840.
[5]	LIU Min, JIN Juan, Abudoukayoumu Ayimaiti, FAN Dingyu, HAO Qing, YANG Lei, ZHAO Xiaomei, GENG Wenjuan. Evaluation of cold resistance of three fresh edible jujube cultivars in Xinjiang [J]. Xinjiang Agricultural Sciences, 2023, 60(4): 916-924.
[6]	GUO Yang, GUO Junxian, SHI Yong, LIU Li, FANG Wenyan, LIU Yancen. Prediction of SPAD Value in Melon Leaves by Characteristic Wavelength Screening Combined with PCA-LSSVM [J]. Xinjiang Agricultural Sciences, 2023, 60(3): 616-623.
[7]	MA Xu, ZHAO Ying, HAN Wei, WU Shengli, HAN Xiaoyan. Principal Component Analysis and Cluster Analysis of Amino Acids in Seabuckthorn Fruit [J]. Xinjiang Agricultural Sciences, 2023, 60(2): 378-388.
[8]	CAO Yijie, SHI Zhiyong, Yusup Ablitip, Aisajan Mamat. Analysis of Amino Acid and Mineral Elements in the Rough-skinned Fruits of Korla Pear [J]. Xinjiang Agricultural Sciences, 2023, 60(2): 407-415.
[9]	YANG Minghua, WANG Qian, ZHOU Xinli, Aihemaitijiang Mahemuti, PEN Yuncheng, Aierjuma Tuluhan, Buayxam Namat, HOU Lili, LIU Qiang. Multiple Analysis on Character and Yield of Maize Hybrid Combinations [J]. Xinjiang Agricultural Sciences, 2022, 59(9): 2114-2122.
[10]	LI Chunyu, TAN Zhanming, CHENG Yunxia, SHU Sheng, HE Tao, JIN Yujie, MA Xinchao, DU Jiageng, ZHANG Jing. The Influence of Water and Fertilizer Coupling on the Growth-development and Quality of Sand Culture Tomato [J]. Xinjiang Agricultural Sciences, 2022, 59(9): 2158-2169.
[11]	YOU Jiahui, GAO Lin, FENG Linjiao, Maimaiti Maidiniayi, ZHOU Long, LI Shude. Analysis of Leaf Anatomical Structure and Drought Resistance of 17 Grape Rootstock Varieties [J]. Xinjiang Agricultural Sciences, 2022, 59(8): 1896-1906.
[12]	FAN Dingyu, JIN Juan, Abudoukayoumu Ayimaiti, YANG Lei, ZHAO Xiaomei, HAO Qing. Comprehensive Evaluation of Fruit Quality Characteristics of 5 Fresh Jujube Varieties [J]. Xinjiang Agricultural Sciences, 2022, 59(8): 1956-1964.
[13]	BAI Shijian, HU Jinge, LI Chao, CAI Junshe, WANG Yong, ZHAO Ronghua, CHEN Guang. Physiological Response to Complex Saline-alkali and Its Tolerance Capacity Evaluation of Grape Rootstocks at Seedling Stage [J]. Xinjiang Agricultural Sciences, 2022, 59(7): 1666-1679.
[14]	XU Junfeng, YANG Rong, ZHAN Faqiang, HOU Min, BAO Huifang, WANG Ning, LONG Xuanqi, ZHANG Zhidong, CUI Weidong. Screening of Functional Bacteria of Organic-Inorganic Liquid Compound Fertilizers and Its Effect on the Quality and Physiological Activity of Greenhouse Tomato [J]. Xinjiang Agricultural Sciences, 2022, 59(7): 1758-1766.
[15]	Buhaliqem Abliz, YUAN Jie, ZHANG Yanhong, ZHAO Zhiqiang, WEN Xiaorong, JIA Chunping, KANG Mintai, TANG Fusen, WANG Fengbin. Analysis of Rice Quality Traits of Different Japonica Rice Varieties (Lines) [J]. Xinjiang Agricultural Sciences, 2022, 59(6): 1347-1355.