基于Stacking集成学习的枣树智能灌溉系统设计与试验

doi:10.13733/j.jcam.issn.2095-5553.2024.06.040

摘要/Abstract

摘要：

南疆降雨量少，气候干燥，农业用水紧张，水资源节约尤为重要，针对此问题设计一套智能灌溉系统。系统使用阿里云服务器作为上位机，树莓派作为下位机，并搭建相应的操作页面。根据PenmanMonteith公式中需要的气象数据、过去7天需水量以及前1天气象数据为输入向量，作物需水量为输出向量，构建基于随机森林、BP神经网络与岭回归的Stacking集成学习预测模型。结果表明Stacking集成学习预测模型拟合系数R2为0.973，且MAE、RMSE、MAPE三类误差更小，Stacking集成学习预测模型预测效果更强。灌溉试验中自动灌溉决策正确，系统运行稳定，为新疆地区农业提高水资源利用问题提供思路。

关键词: 枣树, 智能灌溉系统, Stacking集成学习, 随机森林, BP神经网络, 岭回归

Abstract:

In the south of Xinjiang, the rainfall is low, the climate is dry, agricultural water is scarce, and water conservation is particularly important. An intelligent irrigation system is designed to solve this problem. The system uses Alibaba Cloud server as the upper computer and raspberry pie as the lower computer, and sets up corresponding operation pages. In this paper, according to the meteorological data required in PenmanMonteith formula, the water demand of the past seven days and the meteorological data of the previous day as the input vector, and the crop water demand as the output vector, the Stacking integrated learning prediction model based on random forest, BP neural network and ridge regression is constructed. The results show that the fitting coefficient R2 of Stacking integrated learning prediction model is 0.973, and the three types of errors of MAE, RMSE and MAPE are smaller. The prediction effect of Stacking integrated learning prediction model is stronger. In the irrigation experiment, the automatic irrigation decision is correct, and the system operates stably, which provides ideas for improving the utilization of water resources in agriculture in Xinjiang.

Key words: jujube, intelligent irrigation system, Stacking integrated , learning, random , forest, BP neural network, , ridge regression

中图分类号:

S274.2
TP183

窦文豪, 孙三民, 徐鹏翔. 基于Stacking集成学习的枣树智能灌溉系统设计与试验[J]. 中国农机化学报, 2024, 45(6): 270-276.

Dou Wenhao, Sun Sanmin, Xu Pengxiang. Design and experiment of jujube intelligent irrigation system based on Stacking integrated learning[J]. Journal of Chinese Agricultural Mechanization, 2024, 45(6): 270-276.

参考文献

［1］　刘建军. 南疆地区水资源保障问题和对策分析［J］. 水资源开发与管理, 2022, 8(8): 8-11， 5.

Liu Jianjun. Problems and countermeasures of water resources guarantee in Southern Xinjiang ［J］. Water Resources Development and Management, 2022, 8(8):8-11， 5.

［2］　杨文忠. 农业节水灌溉技术现状与发展趋势探讨［J］. 农业科技与信息, 2021(4): 92, 97.

［3］　潘晓燕. 物联网技术的农业智能灌溉系统设计与应用研究［J］. 科学技术创新, 2021(26): 176-177.

［4］　陈艳丽, 谢芳. 基于ZigBee的农田智能节水灌溉系统的设计［J］. 中国农机化学报, 2017, 38(2): 81-83, 129.

Chen Yanli, Xie Fang. Design of intelligent watersaving farmland irrigation system based on ZigBee ［J］. Journal of Chinese Agricultural Mechanization, 2017, 38(2): 81-83, 129.

［5］　程章翔, 辛元芳, 姚勇, 等. 基于NBIoT的智能灌溉系统设计［J］. 集成电路应用, 2021, 38(6): 44-45.Cheng Zhangxiang, Xin Yuanfang, Yao Yong, et al. Design of intelligent irrigation system based on NBIoT ［J］. Integrated Circuit Applications, 2021, 38(6): 44-45.

［6］　蓝宇, 黄中舟, 朱彦博, 等. 基于STM32和树莓派智能灌溉系统的设计与实现［J］. 物联网技术, 2021, 11(7): 114-117.

［7］　张吉圭. 基于STC15W单片机农田智能灌溉无线监控系统的实现［J］. 智慧农业导刊, 2021, 1(5): 33-35.Zhang Jigui. Realization of intelligent farmland irrigation wireless monitoring system based on STC15W single chip microcomputer ［J］ Journal of Smart Agriculture, 2021, 1(5): 33-35.

［8］　赵苏徽, 陈晓. 基于树莓派和云平台的智能灌溉系统［J］. 计算机系统应用, 2022, 31(4): 123-129.

Zhao Suhui, Chen Xiao. Intelligent irrigation system based on Raspberry Pi and cloud platform ［J］. Computer System & Application, 2022, 31(4): 123-129.

［9］　谭燕, 秦风元. 基于Raspberry Pi的室内智能灌溉系统设计与研究［J］. 节水灌溉, 2019(7): 105-108.

Tan Yan, Qin Fengyuan. Design and research of indoor intelligent irrigation system based on Raspberry Pi ［J］. Water Saving Irrigation, 2019(7): 105-108.

［10］　许铭鋆. 基于Raspberry Pi的智能灌溉系统设计及其研究［D］. 广州: 广州大学, 2019.Xu Mingyun. Design and research of intelligent irrigation system based on Raspberry Pi ［D］. Guangzhou: Guangzhou University, 2019.

［11］　刘振奎. 基于模糊控制的节水智能灌溉系统设计［J］. 安徽农学通报, 2021, 27(23): 138-140.

Liu Zhenkui. Design of watersaving intelligent irrigation system based on fuzzy control ［J］. Anhui Agricultural Science Bulletin, 2021, 27(23): 138-140.

［12］　尹起. 机器学习预测参考作物蒸散量在智能灌溉系统中的应用研究［D］. 乌鲁木齐: 新疆大学, 2021.Yin Qi. Research on the application of machine learning to predict reference crop evapotranspiration in intelligent irrigation system ［D］. Urumqi: Xinjiang University, 2021.

［13］　谢佩军, 张育斌. 阻尼累加离散灰色预测的Smith预估智能灌溉系统［J］. 中国农机化学报, 2022, 43(8): 158-165.

Xie Peijun, Zhang Yubin. Smith predictive intelligent irrigation system based on damping accumulated discrete grey prediction ［J］. Journal of Chinese Agricultural Mechanization, 2022, 43(8): 158-165.

［14］　Badi H, Hamza A, Hasan S. New method for optimization of static hand gesture recognition ［J］. IEEE, 2017: 542-544.

［15］　吕孙云, 许银山, 熊莹, 等. 组合预测方法在需水预测中的应用［J］. 武汉大学学报(工学版), 2011, 44(5):565-570.

Lü Sunyun, Xu Yinshan, Xiong Ying, et al. Combined forecasting method for forecasting water demand ［J］. Engineering Journal of Wuhan University, 2011, 44(5): 565-570.

［16］　Li Yujie, Zhongmin Liang, Yiming Hu, et al. A multimodel integration method for monthly streamflow prediction: Modified stacking ensemble strategy ［J］. Journal of Hydroinformatics, 2020, 22(2).

［17］　Bo Qiuyu, Cheng Wuqun. Intelligent control of agricultural irrigation through water demand prediction based on artificial neural network ［J］. Computational Intelligence and Neuroscience, 2021.

［18］　张智韬, 许崇豪, 谭丞轩, 等. 基于无人机热红外遥感的玉米地土壤含水率诊断方法［J］. 农业机械学报, 2020, 51(3): 180-190.

Zhang Zhitao, Xu Chonghao, Tan Chengxuan, et al. Diagnosis method of soil moisture content in corn field based on thermal infrared remote sensing of UAV ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(3): 180-190.

［19］　张振华, 蔡焕杰, 杨润亚. 红外遥感估算春小麦农田土壤含水率的试验研究［J］. 农业工程学报, 2006(3): 84-87.

Zhang Zhenhua, Cai Huanjie, Yang Runya. Experiment on estimating soil moisture content of spring wheat field with infrared remote sensing ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2006(3): 84-87.

［20］　鲍海波, 吴阳晨, 张国应, 等. 基于特征加权Stacking集成学习的净负荷预测方法［J］. 电力建设, 2022, 43(9): 104-116.

Bao Haibo, Wu Yangchen, Zhang Guoying, et al. Net load forecasting method based on featureweighted Stacking ensemble learning ［J］. Electric Power Construction, 2022, 43(9): 104-116.

［21］　杨冰清, 高珊. 基于Stacking集成学习的蘑菇毒性判别研究［J］. 淮北师范大学学报(自然科学版), 2022, 43(3): 17-21.

Yang Bingqing, Gao Shan. A research on the toxicity of mushroom based on Stacking ensemble learning ［J］. Journal of Huaibei Normal University (Natural Sciences), 2022, 43(3): 17-21.

［22］　孙明喆, 毕瑶家, 孙驰. 改进随机森林算法综述［J］. 现代信息科技, 2019, 3(20): 28-30.

Sun Mingzhe, Bi Yaojia, Sun Chi. A survey of improved random forest algorithms ［J］. Modern Information Technology, 2019, 3(20): 28-30.

［23］　王锦程, 郁芸, 杨坤, 等. 基于BP神经网络的脑肿瘤MRI图像分割［J］. 生物医学工程研究, 2016, 35(4): 290-293.Wang Jincheng, Yu Yun, Yang Kun, et al. Brain tumor segmentation of MRI based on BP neural network ［J］. Journal of Biomedical Engineering Research, 2016, 35(4): 290-293.

［24］　马志昂, 盖艾鸿, 程久苗. 基于BP人工神经网络的区域土地生态安全评价研究——以安徽省为例［J］. 中国农学通报, 2014, 30(23): 289-295.

Ma Zhiang, Gai Aihong, Cheng Jiumiao. Evaluation on ecological security of regional land based on BP artificial neural Network: A case of Anhui Province ［J］. Chinese Agricultural Science Bulletin, 2014, 30(23): 289-295.

［25］　曾津, 周建军. 高维数据变量选择方法综述［J］. 数理统计与管理, 2017, 36(4): 678-692.Zeng Jin, Zhou Jianjun. Variable selection for highdimensional data model: A survey ［J］. Mathematical Statistics and Management, 2017, 36(4): 678-692

［26］　王则玉, 谢香文, 刘国宏, 等. 干旱区绿洲滴灌成龄枣树耗水规律及作物系数［J］. 新疆农业科学, 2015, 52(4): 675-680.

Wang Zeyu, Xie Xiangwen, Liu Guohong, et al. Jujube drip irrigation water consumption and its crop coefficient in oasis of arid areas ［J］. Xinjiang Agricultural Sciences, 2015, 52(4): 675-680.

［27］　孙博瑞. 基于LSTM神经网络的智能灌溉系统开发［D］. 阿拉尔: 塔里木大学, 2022.

Sun Borui. Development of intelligent irrigation system based on LSTM neural network ［D］. Alaer: Tarim University, 2022

［28］　周少梁, 孙三民, 姚宝林, 等. 弥雾灌对枣园冠层环境和光合特性及产量品质的影响［J］. 农业机械学报, 2021, 52(5): 249-257.

Zhou Shaoliang, Sun Sanmin, Yao Baolin, et al. Effects of mist irrigation on canopy environment, photosynthetic characteristics, yield and quality of jujube orchard ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(5): 249-257.

[1]	梁秋艳, 张晓玲, 葛宜元, 迟佳. 超级稻定量供种预测模型研究[J]. 中国农机化学报, 2023, 44(8): 148-154.
[2]	佟敏, 史昌明, 马善为, 崔亚茹, 李凯. 基于互信息参数优化BP神经网络的生物质发电量预测研究[J]. 中国农机化学报, 2023, 44(2): 126-131.
[3]	李慧燕, 张淑荣, 江智伟. 现代都市型农业背景下生鲜乳价格波动预警研究——以天津市为例[J]. 中国农机化学报, 2023, 44(2): 222-229.
[4]	黄帅, 孙浩翔, 王廷超, 舒坤良, 王青蓝, 盖嘉慧. 基于透过强度光谱红边特征的辣椒叶片叶绿素含量诊断模型研究[J]. 中国农机化学报, 2023, 44(11): 109-114.
[5]	郭伟, 高春凤, 乔红波, 李成伟, 张枫, 张慧. 基于无人机数码影像的棉叶螨严重度监测[J]. 中国农机化学报, 2022, 43(8): 143-150.
[6]	谢佩军, 张育斌 . 阻尼累加离散灰色预测的Smith预估智能灌溉系统[J]. 中国农机化学报, 2022, 43(8): 158-165.
[7]	孙逸飞, 柳平增, 张艳, 宋长青, 张大雷, 马学文. 基于Sentinel-2A遥感影像的潍坊市冬小麦种植面积提取研究[J]. 中国农机化学报, 2022, 43(7): 98-105.
[8]	洪苗, 柳平增, 张艳, 马学文, 郑勇, 柳建增. 基于主要环境因子的设施黄瓜生长模型研究[J]. 中国农机化学报, 2022, 43(4): 32-37.
[9]	孙博瑞, 孙三民, 蒋敏, 薛山. 基于LSTM神经网络的智能灌溉系统设计与试验#br# #br# [J]. 中国农机化学报, 2022, 43(4): 116-123.
[10]	蒋柏春, 李德仑, 韦克苏, 张富贵, 王杰, 刘红芸. 基于高光谱的烤烟叶绿素含量估算模型研究[J]. 中国农机化学报, 2022, 43(3): 104-110.
[11]	罗兵, 张建敏. 基于BP神经网络的农机安全评价敏感性分析[J]. 中国农机化学报, 2022, 43(3): 120-126.
[12]	孙浩楠, 仝志民, 谢秋菊, 李嘉熙. 基于BP神经网络猪咳嗽声识别[J]. 中国农机化学报, 2022, 43(2): 148-154.
[13]	朱永乐, 马征, 陈树人, Souleymane Nfamoussa Traore, 李耀明, 姜晟, . BP神经网络预测变振幅防堵筛分性能研究——基于EDEM-RecurDyn仿真[J]. 中国农机化学报, 2022, 43(11): 75-80.
[14]	宋卓研, 徐晓辉, 宋涛, 崔迎港, 司玉龙, . 基于PSO-BP优化PID模型的水肥控制系统研究[J]. 中国农机化学报, 2021, 42(9): 83-89.
[15]	安小宇;赵复兴;柳海涛;. 土壤墒情预测相关性数据耦合性试验分析[J]. 中国农机化学报, 2021, 42(4): 134-141.