基于SSA-Elman的日光温室温湿度预测模型的研究

doi:10.13733/j.jcam.issn.2095‑5553.2024.11.011

摘要/Abstract

摘要： 有效获取日光温室的温湿度变化趋势对实现温室环境精准调控至关重要。为提高日光温室温度和湿度的预测精度和可靠性，提出一种基于麻雀搜索算法(SSA)优化Elman神经网络的温室温湿度环境预测模型。研究采用斯皮尔曼相关性分析方法筛选出主要的环境影响因子作为输入变量，以日光温室内未来的温度和湿度分别作为输出变量，利用麻雀搜索优化算法对Elman神经网络模型参数分别进行优化调整，完成对日光温室的温湿度变化趋势预测。以山东地区2022年10月1日—2023年1月1日的冬季设施番茄日光温室的监测数据进行试验验证。结果表明，SSA-Elman模型对温度的预测指标均方根误差、平均绝对误差和决定系数分别为0.592、0.320和0.963；对湿度的预测指标均方根误差、平均绝对误差和决定系数分别为0.120、2.530和0.972，说明所提出的模型可有效用于对日光温室温湿度进行精准预测，可为未来温室环境的精准调控提供可靠的数据支撑和决策依据。

关键词: Elman神经网络, 温室温湿度, 农业物联网, 麻雀搜索算法

Abstract: It is very important for effective acquisition of temperature and humidity change trends in solar greenhouse to realize the accurate control of greenhouse environment. In order to effectively improve the prediction accuracy and reliability of temperature and humidity in sunlight greenhouses, a greenhouse temperature and humidity environmental prediction model of optimized Elman neural network based on the Sparrow Search Algorithm (SSA) is proposed. The study utilizes the main environmental influencing factors selected through Spearman correlation analysis as input variables, with future temperature and humidity inside the sunlight greenhouse as output variables. The Sparrow Search Algorithm is adopted to optimize and adjust the parameters of the Elman neural network model, thus completing the prediction of temperature and humidity trends in the sunlight greenhouse. Experimental validation is conducted by using monitoring data from a winter facility tomato sunlight greenhouse in Shandong Province from October 1, 2022, to January 1, 2023. The results show that the root mean square error, mean absolute error and coefficient of determination of the SSA-Elman model are 0.592, 0.320 and 0.963 for temperature prediction, and 0.120, 2.530 and 0.972, respectively, for humidity prediction, indicating that the proposed model can effectively make an accurate prediction of the temperature and humidity of the solar greenhouse. The proposed model can effectively predict the temperature and humidity of solar greenhouses, which can provide reliable data support and a decision‑making basis for the future accurate regulation of the greenhouse environment.

Key words: Elman neural network, greenhouse temperature and humidity, agriculture Internet of Things, Sparrow Search Algorithm

中图分类号:

S625
TP183

潘纪港, 柳平增, 张艳, 张铭志, 刘传龙, . 基于SSA-Elman的日光温室温湿度预测模型的研究[J]. 中国农机化学报, 2024, 45(11): 69-76.

Pan Jigang, , , Liu Pingzeng, , , Zhang Yan, , , Zhang Mingzhi, , , Liu Chuanlong, , . Research on solar greenhouse temperature and humidity prediction model based on SSA-Elman[J]. Journal of Chinese Agricultural Mechanization, 2024, 45(11): 69-76.

参考文献

[ 1 ] 乔小丹, 郑文刚, 张馨, 等. 基于LSTM-GRU的日光温室环境预测方法研究[J]. 江苏农业科学, 2022, 50(16): 211-218.
[ 2 ] Esmaeli H, Roshandel R. Optimal design for solar greenhouses based on climate conditions [J]. Renewable Energy, 2020, 145: 1255-1265.
[ 3 ] 陈俐均, 杜尚丰, 李嘉鹏, 等. 温室环境温度预测自适应机理模型参数在线识别方法[J]. 农业工程学报, 2017, 33(1): 315-321.
Chen Lijun, Du Shangfeng, Li Jiapeng, et al. Online identification method of parameters for greenhouse temperature prediction self‑adapting mechanism model [J]. Transactions of the Chinese Society of Agricultural Engineering, 2017, 33(1): 315-321.
[ 4 ] Dong Shuyao, Shamim Ahamed Md, Ma Chengwei, et al. A time‑dependent model for predicting thermal environment of mono‑slope solar greenhouses in cold regions [J]. Energies, 2021, 14(18): 1-19.
[ 5 ] 徐立鸿, 苏远平 , 梁毓明. 面向控制的温室系统小气候环境模型要求与现状[J]. 农业工程学报, 2013, 29(19): 1-15.
Xu Lihong, Su Yuanping, Liang Yuming. Requirements and current status of control‑oriented microclimate environment model in greenhouse system [J]. Transactions of the Chinese Society of Agricultural Engineering, 2013, 29(19): 1-15.
[ 6 ] Moon T W, Jung D H, Chang S H, et al. Estimation of greenhouse CO2 concentration via an artificial neural network that uses environmental factors [J]. Horticulture, Environment, and Biotechnology, 2018, 59: 45-50.
[ 7 ] 于玉婷, 徐光丽, 柳平增, 等. 设施番茄温室风口开关时间参数研究[J]. 中国农机化学报, 2022, 43(12): 83-90, 98.
Yu Yuting, Xu Guangli, Liu Pingzeng, et al. Study on time parameters of opening and closing vents in tomato greenhouse [J]. Journal of Chinese Agricultural Mechanization, 2022, 43(12): 83-90, 98.
[ 8 ] 张永芳, 王芳. 基于SSA-RBF网络的日光温室温湿度预测模型研究[J]. 河北农业大学学报, 2021, 44(3): 115-121.
[ 9 ] Castañeda‑Miranda A, Castaño V M. Smart frost control in greenhouses by neural networks models [J]. Computers and Electronics in Agriculture, 2017, 137: 102-114.
[10] Wang Yan, Liu Pingzeng, Zhu Ke, et al. A Garlic‑price‑prediction approach based on combined LSTM and GARCH-Family model [J]. Applied Sciences, 2022, 12(22): 11366.
[11] 刘焕, 杨延杰, 史宇亮, 等. 胶东地区日光温室周年温湿度变化规律分析及预测[J]. 中国农业科技导报, 2021, 23(12): 136-144.
[12] 刘鹏菊. 设施黄瓜生长环境监测与温室风口控制系统研究[D]. 泰安: 山东农业大学, 2021.
[13] Ullah I, Fayaz M, Naveed N. ANN based learning to kalman filter algorithm for indoor environment prediction in smart greenhouse [J]. IEEE Access, 2020, 8: 159371-159388.
[14] 张建超, 单慧勇, 景向阳, 等. 基于Elman神经网络的温室环境因子预测方法[J]. 中国农机化学报, 2021, 42(8): 203-208.
Zhang Jianchao, Shan Huiyong, Jing Xiangyang, et al. Prediction method of greenhouse environmental factors based on Elman neural network [J]. Journal of Chinese Agricultural Mechanization, 2021, 42(8): 203-208.
[15] 刘传龙. 设施番茄温室温湿度智能调控系统研究[D]. 泰安: 山东农业大学, 2022.
[16] Xue J K, Shen B. Novel swarm intelligence optimization approach: Sparrow search algorithm [J]. Systems Science & Control Engineering, 2020, 8(1): 22-34.
[17] 祖林禄, 柳平增, 赵妍平, 等. 基于SSA-LSTM的日光温室环境预测模型研究[J]. 农业机械学报, 2023, 54(2): 351-358.
Zu Linlu, Liu Pingzeng, Zhao Yanping, et al. Study of the greenhouse environment prediction model based on SSA-LSTM [J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(2): 351-358.
[18] 宋成宝, 柳平增, 刘兴华, 等. 基于HSIC的日光温室温度传感器优化配置策略[J]. 农业工程学报, 2022, 38(8): 200-208.
Song Chengbao, Liu Pingzeng, Liu Xinghua, et al. Optimal configuration strategy for temperature sensors in solar greenhouse based on HSIC [J]. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38(8): 200-208.
[19] 敬如雪, 高玉琢. 基于多传感器的数据融合算法研究[J]. 现代电子技术, 2020, 43(10): 10-13.
[20] 刘建伟, 赵会丹, 罗雄麟, 等. 深度学习批归一化及其相关算法研究进展[J]. 自动化学报, 2020, 46(6): 1090-1120.
[21] 许力琴, 周晴, 刘霞. 科技论文“Spearman相关”表达中存在的问题分析与建议[J]. 编辑学报, 2019, 31(4): 398-400.
[22] 郑昊南. 平菇温室温湿度物联网智能测控系统的设计与实现[D]. 泰安: 山东农业大学, 2022.
[23] Zheng Y, Zhang X, Wang X, et al. Predictive study of tuberculosis incidence by time series method and Elman neural network in Kashgar, China [J]. BMJ Open, 2021, 11(1): e041040.
[24] 程陈, 冯利平, 董朝阳, 等. 利用Elman神经网络的华北棚型日光温室室内环境要素模拟[J]. 农业工程学报, 2021, 37(13): 200-208.
Cheng Chen, Feng Liping, Dong Chaoyang, et al. Simulation of inside environmental factors in solar greenhouses using Elman neural network in North China [J]. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37(13): 200-208.
[25] 李雅丽, 王淑琴, 陈倩茹, 等. 若干新型群智能优化算法的对比研究[J]. 计算机工程与应用, 2020, 56(22): 1-12.
[26] 赵雪, 顾伟红. 基于GRA-SSA-Elman的隧洞TBM掘进适应性评价[J]. 隧道建设(中英文), 2022, 42(11): 1879-1888.

[1]	牟远明 , 卓然 , 高飞 . 基于混合改进麻雀搜索算法的农用移动机器人路径规划[J]. 中国农机化学报, 2024, 45(9): 234-243.
[2]	章海亮, 聂训, 黄招娣. 基于麻雀搜索算法优化的模糊PID控制方法研究[J]. 中国农机化学报, 2024, 45(4): 141-148.
[3]	刘可心, 赵爽, 苗玉彬. 基于SSA-Kmeans聚类算法的青菜杂质图像分割[J]. 中国农机化学报, 2024, 45(2): 151-156.
[4]	轩梦辉, 赵思夏, 徐立友, 陈小亮, 李团飞. 改进VMD和LSTM的联合收割机装配质量检测方法[J]. 中国农机化学报, 2023, 44(3): 132-140.
[5]	李井竹, 刘秋菊, 王仲英, . 基于改进SSA算法优化极限学习机模型的土壤供肥量预测[J]. 中国农机化学报, 2023, 44(10): 174-184.
[6]	张建超, 单慧勇, 景向阳, 李晨阳, 张程皓, 刘慧芹, . 基于Elman神经网络的温室环境因子预测方法[J]. 中国农机化学报, 2021, 42(8): 203-208.
[7]	潘敏睿;马军;王杰;张学敏;. 水肥一体化技术发展概述[J]. 中国农机化学报, 2020, 41(8): 204-210.
[8]	程鑫;徐晓辉;宋涛;宋卓研;赵睿;. 基于PSO-SVR模型的温室智能补光系统研究[J]. 中国农机化学报, 2020, 41(6): 64-68+82.
[9]	吴晓强;李理;赵华洋;郝瑞参;. 基于情景感知数据融合的农业物联网监测模型研究[J]. 中国农机化学报, 2019, 40(4): 169-173.