基于多层感知机的温室内番茄茎直径变化预测模型

doi:10.6048/j.issn.1001-4330.2020.03.021

新疆农业科学 ›› 2020, Vol. 57 ›› Issue (3): 562-571.DOI: 10.6048/j.issn.1001-4330.2020.03.021

• 植物保护·土壤肥料·农业机械·畜牧兽医 • 上一篇下一篇

基于多层感知机的温室内番茄茎直径变化预测模型

陈毅飞¹, 杨会民¹, 马艳¹, 张新伟², 喻晨¹, 王学农¹

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

收稿日期:2019-10-18 出版日期:2020-03-20 发布日期:2020-03-11
通信作者: 王学农(1964-),男,陕西汉中人,研究员,硕士生导师,研究方向为农业机械化技术装备,(E-mail)xjwxn2010@sina.com
作者简介:陈毅飞(1990-),男,新疆人,助理研究员,硕士,研究方向为农业信息技术,(E-mail)cyfgunman@163.com
基金资助:
国家重点研发计划项目子课题“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);新疆农业科学院青年基金项目“基于WebService的温室异构数据共享研究”(xjnky-2016019)

The Research of the Prediction Model of Stem Diameter Variation Based on Multilayer Perceptron for Greenhouse Tomato

CHEN Yifei¹, YANG Huimin¹, MA Yan¹, ZHANG Xinwei², YU Chen¹, WANG Xuenong¹

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

Received:2019-10-18 Online:2020-03-20 Published:2020-03-11
Correspondence author: WANG Xuenong (1964-),male, Shan Xi Province, Researcher, Research Direction: Agricultural Mechanization Technology and Equipment Research,( E-mail) xjwxn2010@ sina.com
Supported by:
Supported by: National Key R & D Program Project Sub-topic "Vegetable Intelligent Production Technology and Equipment Research and Development"(2017YFD0701301-03); Pre-research Project in the Early Stage of Major Program of Xinjiang Academy of Agricultural Sciences “Research on Intelligent Control Equipment Technology Based on Multi-source Information and Cloud Platform” (xjzdy-002); Outstanding Young Scientific Talent Foundation of Xinjaing Academy of Agricultural Sciences “Research on Greenhouse Heterogeneous Data Sharing Based on WebService" ( xjnky-2016019)

摘要/Abstract

摘要： 【目的】研究温室内番茄茎直径变化量动态预测模型,为番茄需水规律提供一定决策支持。【方法】采用多层感知机算法与植物生理生态信息相融合的方法,建立一个包含空气温湿度、土壤湿度、叶片温度、茎直径变化量及光合有效辐射的基于多层感知机算法的茎直径变化量预测模型。采用3层隐含层神经网络对经过正则化及归一化的6维训练集数据向量,进行全连接式训练后,得出预测模型,验证集数据输入预测模型后得出1维输出向量,对输出向量进行反归一化进而得出茎直径变化量预测值。【结果】建立的基于多层感知机短时番茄茎直径变化量动态预测模型的预测值与实测值的回归系数(R²)为0.901,均方根误差(RMSE)为0.175。【结论】该模型适用于温室番茄短时茎直径变化量动态预测,具有较好的应用场景。

关键词: 多层感知机; 动态调整; 茎直径变化量; 温室番茄; 非线性回归预测

Abstract: 【Objective】 Aiming at the uncertain parameters of tomato water demand law and the non-dynamic analysis of system, the dynamic prediction model of tomato stem diameter change in greenhouse was studied in the hope providing some decision support for tomato water demand. 【Method】This research mainly uses the method of integrating the multi-layer perceptron algorithm with plant physiological and ecological information, established a stem diameter variations prediction model, which contains many types of data ,like air temperature, humidity, soil humidity, leaf temperature, stem diameter variations and photosynthetic effective radiation. In this paper, the three-layer hidden layer neural network is adopted to conduct fully connected training on the data vector of the 6-dimensional training set after regularization and normalization, and then the 1-dimensional output vector is obtained after input the validation set data . Finally, the output vector is inverse normalized to obtain the predicted value of stem diameter variations.【Result】The regression coefficient of the predicated value and the measured value (R²) and the root mean square error (RMSE) were 0.901 and 0.175, respectively, based on the dynamic prediction model of the short-term tomato stem diameter variations on which multilayer perceptron was established. 【Conclusion】The model is applicable to the dynamic prediction of short-term stem diameter variations of greenhouse tomato, and has a good application scenario, which can provide a strong basis for the decision to meet the crop water demand.

Key words: multilayer perceptron; dynamic adjustment; stem diameter variation; greenhouse tomato; nonlinear regression prediction

中图分类号:

S641.2
S12

陈毅飞, 杨会民, 马艳, 张新伟, 喻晨, 王学农. 基于多层感知机的温室内番茄茎直径变化预测模型[J]. 新疆农业科学, 2020, 57(3): 562-571.

CHEN Yifei, YANG Huimin, MA Yan, ZHANG Xinwei, YU Chen, WANG Xuenong. The Research of the Prediction Model of Stem Diameter Variation Based on Multilayer Perceptron for Greenhouse Tomato[J]. Xinjiang Agricultural Sciences, 2020, 57(3): 562-571.

参考文献

[1] 马富裕,刘扬,崔静,等. 水肥一体化研究进展[J]. 新疆农业科学,2019, 56(1): 183-192.
MA Fuyu,LIU Yang,CUI Jing,et al. Review on the Research Progress of Water and Fertilizer Integration [J]. Xinjiang Agricultural Sciences, 2019, 56(1): 183-192.
[2] 田聪华,赵婷,徐忠,等. 基于DEA方法的新疆农业高效节水技术效率分析[J]. 节水灌溉,2017,(1): 90-93.
TIAN Conghua,ZHAO Ting,XU Zhong, et al. Analysis of Technical Efficiency of Agricultural Efficient Water-saving Technology Based on DEA Method in Xinjiang[J]. Water Saving Irrigation, 2017,(1): 90-93.
[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, 161: 225-232.
[4] Kaneda Y, Shibata S, Mineno H. Multi-modal sliding window-based support vector regression for predicting plant water stress [J]. Knowledge-Based Systems. 2017, 134: 135-148.
[5] 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. Effect of alternate partial root-zone irrigation on fruit and stem diameter of tomato [J]. Transactions of the Chinese Society of Agricultural Engineering, 2014, 30(12): 87-95.
[6] 员玉良,程强,Damerow Lutz,等. 基于茎直径和茎流复合测量的植物根压无损观测方法[J]. 农业机械学报,2015, 46(11): 290-295.
YUAN Yuliang,CHENG Qiang,Lutz Damerow,et al. Non-destructive Observation of Plant Root Pressure Based on Combined Measurement of Stem Diameter and Sap Flow [J]. Transactions of the Chinese Society for Agricultural Machinery, 2015, 46(11): 290-295.
[7] WANG X, MENG Z, Chang X, et al. Determination of a suitable indicator of tomato water content based on stem diameter variation [J]. Scientia Horticulturae,2017, 215: 142-148.
[8] 张红梅,余纪柱,金海军. 温室条件下黄瓜生长发育及茎流变化规律研究[J]. 农业工程学报,2005,(S2): 106-108.
ZHANG Hongmei,YU Jizhu,JIN Haijun. Growth and stem flow variation of cucumber in greenhouse [J]. Transactions of the Chinese Society of Agricultural Engineering, 2005,(S2): 106-108.
[9] 林琭,汤昀,闫万丽,等. 基于茎直)径变化的精准灌溉技术研究进展[J]. 农业工程学报,2016, 32(5): 1-13.
LIN Lu,TANG Yun,YAN Wanli, et al. Overview of precise irrigation scheduling based on stem diameter variations[J]. Transactions of the Chinese Society of Agricultural Engineering,2016, 32(5): 1-13.
[10] Rajalakshmi, S. Devi Mahalakshmi. IOT based crop-field monitoring and irrigation automation[C]// 2016 10th International Conference on Intelligent Systems and Control (ISCO). 2016.
[11] 张雪飞,彭凯,王建春,等. 设施蔬菜水肥一体化智能灌溉控制系统的设计及试验[J]. 山西农业科学, 2017, 45(9): 1534-1538.
ZHANG Xuefei,PENG Kai,WANG Jianchun,et al. Design and Test of Intelligent Irrigation Control System for Water and Fertilizer Integration of Facilities Vegetables [J]. Journal of Shanxi Agricultural Sciences, 2017, 45(9): 1534-1538.
[12] 柳长顺,杜丽娟,王红坤. 农户灌溉决策行为影响因素比较研究[J]. 中国水利,2018,(19): 36-38.
LIU Zhangshun,DU Lijuan,WANG Hongkun. Comparative analysis of influential factors on irrigation decision making of farmers [J]. China Water Resources, 2018,(19): 36-38.
[13] 张文宇,曹宏鑫,葛道阔,等. 基于模型的智慧农业平台的构建[J]. 江苏农业科学, 2015, 43(12): 478-481.
ZHANG Wenyu,CAO Hongxin, GE Daokuo, et al. The Construction of Smart Agriculture Platform Based on Model [J]. Jiangsu Agricultural Sciences,2015, 43(12): 478-481.
[14] 王晓森,孟兆江,段爱旺,等. 基于茎直径变化监测番茄水分状况的机理与方法[J]. 农业工程学报,2010, 26(12): 107-113.
WANG Xiaosen,MENG Zhaojiang,DUAN Aiwang,et al. Mechanism and methodology for monitoring tomato water content based on stem diameter variation[J]. Transactions of the Chinese Society of Agricultural Engineering, 2010, 26(12): 107-113.
[15] 王晓森,刘祖贵,刘浩,等. 番茄茎直径MDS的通径分析与数值模拟[J]. 农业机械学报,2012, 43(8): 187-192.
WANG Xiaosen,LIU Zugui,LIU Hao, et al. Path Analysis and Numerical Simulation of MDS of Tomato Stem Diameter [J]. Transactions of the Chinese Society for Agricultural Machinery, 2012, 43(8): 187-192.
[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 of Stem Diameter Variations Based on Principal Component Regression [J]. Transactions of the Chinese Society for Agricultural Machinery, 2015, 46(1): 306-314.
[17] Gallardo M, Thompson R B, Valdez L C, et al. Use of stem diameter variations to detect plant water stress in tomato[J]. Irrigation Science, 2006, 24(4): 241-255.
[18] Ortuo M F, Conejero W, Moreno F, et al. Could trunk diameter sensors be used in woody crops for irrigation scheduling? A review of current knowledge and future perspectives [J]. Agricultural Water Management, 2010, 97(1): 1-11.
[19] Perea R G, Poyato E C, Montesinos P, et al. Prediction of applied irrigation depths at farm level using artificial intelligence techniques [J]. Agricultural water management, 2018, 206: 229-240.
[20] Adeyemi O, Grove I, Peets S, et al. Dynamic modelling of lettuce transpiration for water status monitoring[J]. Computers and Electronics in Agriculture, 2018, 155: 50-57.
[21] Goldstein A, Fink L, Meitin A, et al. Applying machine learning on sensor data for irrigation recommendations: revealing the agronomist’s tacit knowledge[J]. Precision Agriculture, 2018, 19(3): 421-444.
[22] 张毅锋,蒋程,程旭,等. 基于基完备化理论和嵌入多层感知机的深度网络结构设计[J]. 东南大学学报(自然科学版),2018, 48(5): 933-938.
ZHANG Yifeng,JIANG Cheng,CHENG Xu, et al. Deepnetwork structure design based on base completion and embedded multi-layer perceptron [J]. Journal of Southeast University(Natural Science Edition), 2018, 48(5): 933-938.
[23] 衷路生,刘东东. 多级神经网络的轴承故障诊断研究[J]. 计算机工程与应用,2019,(1): 1-8.
ZHONG Lusheng,LIU Dongdong. Research on Bearing Fault Diagnosis of Multi-level Neural Network[J]. Computer Engineering and Applications, 2019,(1): 1-8.
[24] 张鹏程,贾旸旸. 一种基于多层感知器的动态区域联合短时降水预报方法[J]. 计算机应用与软件,2018, 35(11): 153-158.
ZHANG Pengcheng,JIA Yangyang. A Dynamic Regional Combind Short-Term Precipitation Forecasting Approach Based on Multilayer Perceptron [J]. Computer Applications and Software, 2018, 35(11): 153-158.
[25] 丁雪松,黄立群,张步忠,等. 基于多层感知机的蛋白质变性温度预测[J]. 计算机应用研究,2019, 36(8): 2421-2423.
DING Xuesong, HUANG Liqun, ZHANG Buzhong,et al. Using multi-layer perceptron to predict protein melting temperature[J]. Application Research of Computers, 2019, 36(8): 2421-2423.
[26] Perea R G, Poyato E C, Montesinos P, et al. Optimisation of water demand forecasting by artificial intelligence with short data sets [J]. Biosystems Engineering,2019, 177: 59-66.
[27] Perea R G, Poyato E C, Montesinos P, et al. Prediction of applied irrigation depths at farm level using artificial intelligence techniques [J]. Agricultural Water Management, 2018, 206: 229-240.
[28] Huong T T, Thanh N H, Van N T, et al. Water and Energy-Efficient Irrigation based on Markov Decision Model for Precision Agriculture[C]. IEEE, 2018.
[29] Ceppi A, Ravazzani G, Corbari C, et al. Real-time drought forecasting system for irrigation management[J]. Hydrology and Earth System Sciences, 2014, 18(9): 3353-3366.
[30] 高明,崔钶,李昊,等. 基于HCPS多层感知器的污水处理后氨氮浓度测量[J]. 轻工学报,2018, 33(6): 92-100.
GO Ming,CUI Ke,LI Hao,et al. Measurement of ammonia nitrogen concentration after sewage treatment basedon HCPS multilayer perceptrons[J]. Journal of Light Industry, 2018, 33(6): 92-100.
[31] 晏福,徐建中,李奉书. 混沌灰狼优化算法训练多层感知器[J]. 电子与信息学报,2019, 41(4): 872-879.
YAN Fu,XU Jianzhong,LI Fengshu. Training Multi-layer Perceptrons Using Chaos Grey Wolf Optimizer [J]. Journal of Electronics & Information Technology, 2019, 41(4): 872-879.

基于多层感知机的温室内番茄茎直径变化预测模型

The Research of the Prediction Model of Stem Diameter Variation Based on Multilayer Perceptron for Greenhouse Tomato

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics