Ventilation Control Model of Cucumber in Facility Based on Environmental Factors

doi:10.13304/j.nykjdb.2022.0035

Abstract

Abstract:

To precisely control the opening size of the cucumber greenhouse air vents in facilities， this paper studied prediction of temperature change in greenhouse. Taking the opening size and greenhouse tuyere both inside and outside environment factor as input factors， temperature prediction model was built by the method of stepwise regression.The results showed that the minimum determination coefficient R² was 0.941. Principal component analysis was used to establish the expression of cucumber growth potential， and Lasso regression method was used to build the greenhouse cucumber growth model based on environmental factors. Finally， the temperature prediction model was combined with the cucumber growth model to construct special tuyere control model， which realized the automatic control of the tuyere opening size of the greenhouse， and then improved the intelligent management level of the cucumber greenhouse.

Key words: greenhouse tuyere, stepwise regression, predict, Lasso, automatic control

摘要：

为实现设施黄瓜温室风口开度大小的精准控制，对温室内温度变化趋势进行了预测研究。将温室风口开度大小状态和温室内外各环境因子作为输入因子，利用逐步回归的方法构建温室温度预测模型，模型决定系数R² 最小为0.941。采用主成分分析方法建立黄瓜长势关系表达式，然后利用Lasso回归构建基于环境因子的设施黄瓜生长模型。将温室温度预测模型与设施黄瓜生长模型相结合，最终构建了设施黄瓜温室专用风口控制模型，实现了温室风口开度大小的自动控制，提升了设施黄瓜温室的智能化管理水平。

关键词: 温室风口, 逐步回归, 预测, Lasso, 自动控制

CLC Number:

S626

Pengju LIU, Pingzeng LIU, Dalei ZHANG, Yan ZHANG, Hui LI, Lining LIU, Fangjun DING. Ventilation Control Model of Cucumber in Facility Based on Environmental Factors[J]. Journal of Agricultural Science and Technology, 2023, 25(12): 103-110.

刘鹏菊, 柳平增, 张大磊, 张艳, 李辉, 刘力宁, 丁方军. 基于环境因子的设施黄瓜通风控制模型[J]. 中国农业科技导报, 2023, 25(12): 103-110.

Figures/Tables 7

References 28

1	程陈,董朝阳,黎贞发,等.日光温室芹菜外观形态及干物质积累分配模拟模型[J].农业工程学报,2021,37(10):142-151.
	CHENG C, DONG C Y, LI Z F, et al.. Simulation model of external morphology and dry matter accumulation and distribution of celery in solar greenhouse [J].Trans. Chin. Soc. Agric. Eng., 2021,37(10):142-151.
2	JHA U C, BOHRA A, JHA R. Breeding approaches and genomics technologies to increase crop yield under low-temperature stress [J]. Plant Cell Rep., 2017,36:1-35.
3	张川,张亨年,闫浩芳,等.微喷灌结合滴灌对温室高温环境和作物生长生理特性的影响[J].农业工程学报,2018,34(20): 83-89.
	ZHNAG C, ZHANG H N, YAN H F, et al.. Effects of micro-sprinkler irrigation combined with drip irrigation on greenhouse high temperature environment and crop growth physiological characteristics [J]. Trans. Chin. Soc. Agric. Eng., 2018,34(20): 83-89.
4	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 L H, SU Y P, LIANG S M. Requirement and current situation of control-oriented microclimate environmental model in greenhouse system [J]. Trans.Chin. Soc. Agric. Eng., 2013,29(19):1-15.
5	袁洪波,李莉,王俊衡,等.基于温度积分算法的温室环境控制方法[J].农业工程学报,2015,31(11):221-227.
	YUAN H B, LI L, WANG J H, et al.. Control method for greenhouse climate based on temperature integration [J]. Trans. Chin. Soc. Agric. Eng., 2015,31(11): 221-227.
6	WANG L, WANG B, ZHU M. Multi-model adaptive fuzzy control system based on switch mechanism in a greenhouse [J]. Appl. Eng. Agric.,2020,36:549-556.
7	SUN W, KONG F, ZHANG J, et al.. Greenhouse intelligent control system based on indoor and outdoor environmental data fusion [J/OL]. IOP Conf. Seri.: Earth and Environ. Sci., 440(4):042073 [2023-06-16]. .
8	CHENG Y. Research on intelligent control of agricultural greenhouse based on fuzzy PID control [J]. J. Environ. Eng.Sci.,2020,15(3):1-6.
9	BERSANI C, FOSSA M, PRIARONE A, et al.. Model predictive control versus traditional relay control in a high energy efficiency greenhouse [J]. Energies,2021,14(11):1-21.
10	HAMIDANE H, FAIZ S E, LACHHAB A, et al.. Constrained discrete model predictive control of a greenhouse relative humidity [C/OL]// E3S Web of Conferences, 2021, 229: 01001 [2023-06-16]. .
11	吴曼玲,陈一飞,李琦,等.基于灰色预测的温室地源热泵系统温度变频调控及验证[J].农业工程学报,2016,32(16): 183-187.
	WU M L, CHEN Y F, LI Q, et al.. Frequency transformation and its validation of ground source heat pump system based on grey prediction of greenhouse temperature [J]. Trans. Chin. Soc. Agric. Eng., 2016,32(16):183-187.
12	SONG Y E, MOON A, AN S Y, et al.. Prediction of smart greenhouse temperature-humidity based on multi-dimensional LSTMs [J]. J. Korean Soc. Precision Eng., 2019,36(3):239-246.
13	温永菁,李春,薛庆禹,等.基于逐步回归与BP神经网络的日光温室温湿度预测模型对比分析[J].中国农学通报,2018,34:115-125.
	WEN Y J, LI C, XUE Q Y, et al.. Temperature and humidity prediction models in solar greenhouse:comparative analysis based on stepwise regression and BP neural network [J]. Chin. Agric. Sci. Bull., 2018,34:115-125.
14	秦琳琳,马娇,黄云梦,等.基于积温理论的温室温度混杂系统预测控制[J].农业机械学报,2018,49:347-355.
	QIN L L, MA J, HUANG Y M, et al.. Predictive control of greenhouse temperature hybrid system based on crop temperature integration theory [J].Trans. Chin. Soc. Agric. Mach., 2018,49:347-355.
15	ZHANG X, GAO L, ZHAO Z Y, et al.. Modeling and analysis of greenhouse environmental factors in north China based on path analysis and stepwise regression [J]. Semin-Cienc Agrar., 41(6):2587-2596 2020, 41(6):2587-2596.
16	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(S1):315-321. CHEN L J, DU S F, LI J P, et al.. Online identification method of parameters for greenhouse temperature prediction self-adapting mechanism model [J]. Trans. Chin. Soc. Agric. Eng., 2017,33(S1):315-321.
17	张观山,李天华,侯加林.考虑动态吸收率的玻璃温室覆盖层温度预测模型[J].农业工程学报,2020,36:201-211.
	ZHANG G S, LI T H, HOU J L. Model for predicting the temperature of glass greenhouse cover considering dynamic absorptivity [J]. Trans. Chin. Soc. Agric. Eng.,2020,36(5): 201-211.
18	JUNG D H, KIM H J, KIM J Y, et al.. Model predictive control via output feedback neural network for improved Multi-window greenhouse ventilation control [J/OL]. Sensors, 2020,20(6):1756 [2023-06-16]. .
19	秦琳琳,马国旗,储著东,等.基于灰色预测模型的温室温湿度系统建模与控制[J].农业工程学报,2016,32(S1):233-241.
	QIN L L, MA G Q, CHU Z D, et al.. Molding and control of greenhouse temperature-humidity system based on grey prediction model [J]. Trans. Chin. Soc. Agric. Eng.,2016,32(S1):233-241.
20	SUMARUDIN A, ISMANTOHADI E, PUSPANINGRUM A,et al.. Implementation irrigation system using support vector machine for precision agriculture based on IoT [J/OL]. IOP Conf. Ser.: Mater. Sci. Eng., 2021,1098:032098 [2023-06-16]. .
21	KANEDA Y, IBAYASHI H, OISHI N,et al.. Greenhouse environmental control system based on SW-SVR [J]. Procedia Computer Sci., 2015,08(249):860-869.
22	刘浩,孙景生,段爱旺,等.基于AutoCAD软件确定番茄与青椒叶面积的简易方法[J].中国农学通报,2009,25(5):287-293.
	LIU H, SUN J S, DUAN A W, et al.. Simple model for tomato and green pepper leaf area based on auto CAD software [J]. Chin. Agric. Sci. Bull.,2009,25(5):287-293.
23	WOLD S, ESBENSEN K, GELADI P. Principal component analysis [J].Chemom. Intell. Lab. Systs.,1987,2:37-52.
24	张红梅,金海军,丁小涛,等.有机肥无机肥配施对温室黄瓜生长、产量和品质的影响[J].植物营养与肥料学报,2014, 20(1): 247-253.
	ZHANG H M, JIN H J, DING X T, et al.. Effects of application of organic and inorganic fertilizers on the growth,yield and quality of cucumber in greenhouse [J]. Plant Nutr. Fert. Sci.,2014,20(1): 247-253.
25	THOMPSON B. Stepwise regression and stepwise discriminant analysis need not apply here: a guidelines editorial [J]. Edu. Psychol. Measure., 1995,55(4):525-534.
26	REID S, TIBSHIRANI R, FRIEDMAN J. A Study of error variance estimation in Lasso regression [J]. Statistica Sinica,2016(1):453-457.
27	陶惠林,徐良骥,冯海宽,等.基于无人机数码影像的冬小麦株高和生物量估算[J].农业工程学报,2019,35(19):107-116.
	TAO H L, XU L J, FENG H K, et al.. Estimation of plantheight and biomass of winter wheat based on UAV digita image [J]. Trans. Chin. Soc. Agric. Eng., 2019,35(19): 107-116.
28	HAIR J, BLACK W, BABIN B, et al.. Advanced Diagnostics for Multiple Regression: A Supplement to Multivariate Data Analysis [M]. Upper Saddle River, NJ: Pearson Prentice Hall, 2010:87-93.

指标 Index	Y	X₁	X₂	X₃	X₄	X₅	X₆	X₇	X₈	X₉
Y	1
X₁	0.987	1
X₂	-0.819	-0.856	1
X₃	0.738	0.756	-0.704	1
X₄	-0.177	-0.177	-0.021	0.07	1
X₅	0.778	0.789	-0.664	0.513	-0.482	1
X₆	-0.634	-0.657	0.764	-0.555	-0.049	-0.575	1
X₇	0.295	0.297	-0.306	0.271	-0.051	0.281	-0.269	1
X₈	0.109	0.122	-0.154	0.109	-0.022	0.142	-0.177	-0.147	1
X₉	0.842	0.802	-0.806	0.671	-0.013	0.567	-0.567	0.351	0.059	1

指标 Index	Y	X₁	X₂	X₃	X₄	X₅	X₆	X₇	X₈	X₉
Y	1
X₁	0.987	1
X₂	-0.819	-0.856	1
X₃	0.738	0.756	-0.704	1
X₄	-0.177	-0.177	-0.021	0.07	1
X₅	0.778	0.789	-0.664	0.513	-0.482	1
X₆	-0.634	-0.657	0.764	-0.555	-0.049	-0.575	1
X₇	0.295	0.297	-0.306	0.271	-0.051	0.281	-0.269	1
X₈	0.109	0.122	-0.154	0.109	-0.022	0.142	-0.177	-0.147	1
X₉	0.842	0.802	-0.806	0.671	-0.013	0.567	-0.567	0.351	0.059	1

风口开度Opening size/%	回归自变量Regression independent variable
风口开度Opening size/%	X₁	X₂	X₃	X₄	X₅	X₆	X₇	X₈	X₉
0	20.388	5.084	11.127	1.510	14.771	12.126	1.308	1.385	3.542
25	15.705	22.809	5.077	13.338	6.074	20.151	1.423	1.523	7.074
50	14.171	5.278	10.296	2.985	2.357	4.846	1.116	1.177	2.380
75	3.551	6.218	1.835	2.801	2.902	5.543	1.110	1.108	2.275
100	5.978	8.135	2.024	3.564	5.510	6.482	1.054	1.076	2.605

风口开度Opening size/%	回归自变量Regression independent variable
风口开度Opening size/%	X₁	X₂	X₃	X₄	X₅	X₆	X₇	X₈	X₉
0	20.388	5.084	11.127	1.510	14.771	12.126	1.308	1.385	3.542
25	15.705	22.809	5.077	13.338	6.074	20.151	1.423	1.523	7.074
50	14.171	5.278	10.296	2.985	2.357	4.846	1.116	1.177	2.380
75	3.551	6.218	1.835	2.801	2.902	5.543	1.110	1.108	2.275
100	5.978	8.135	2.024	3.564	5.510	6.482	1.054	1.076	2.605

风口开度Opening size/%	变量名称 Variable	非标准化系数Denormalization coefficient		标准化系数Normalization coefficient	显著性 Significance
风口开度Opening size/%	变量名称 Variable	回归系数 Regression coefficient	标准误差 Standard Error	标准化系数Normalization coefficient	显著性 Significance
0	常量Constant	1.772	2.107	—	0.401
	X₁	0.560	0.043	0.557	0.000
	X₃	0.105	0.011	0.311	0.000
	X₅	0.412	0.063	0.231	0.000
	X₆	0.036	0.006	0.204	0.000
	X₉	0.026	0.002	0.253	0.000
	X₂	0.071	0.010	0.157	0.000
	X₄	-0.313	0.057	-0.065	0.000
25	常量Constant	-4.117	0.979	—	0.000
	X₁	0.909	0.026	0.898	0.000
	X₉	0.054	0.003	0.364	0.000
	X₂	0.070	0.006	0.284	0.000
50	常量Constant	-0.217	0.815	—	0.490
	X₁	0.799	0.013	0.800	0.000
	X₉	0.085	0.003	0.305	0.000
	X₂	0.102	0.007	0.241	0.000
	X₅	-0.061	0.008	-0.130	0.000
	X₄	-0.077	0.012	-0.058	0.000
	X₈	0.003	0.001	0.033	0.000
75	常量Constant	-0.799	0.651	—	0.220
	X₁	0.842	0.012	0.787	0.000
	X₉	0.066	0.002	0.319	0.000
	X₂	0.054	0.005	0.143	0.000
	X₇	-0.134	0.025	-0.044	0.000
	X₈	-0.002	0.001	-0.034	0.000
	X₄	-0.035	0.009	-0.040	0.000