Performance analysis of insulation blanket application based on machine learning

doi:10.14088/j.cnki.issn0439-8114.2025.01.026

Abstract

Abstract: To satisfy the nighttime insulation needs of prefabricated greenhouses and to develop novel insulation materials, the use of machine learning for evaluating greenhouse environments was investigated and the insulation efficacy of two new types of blankets was compared, one with camel hair and the other with rubber-plastic board as the core material. The findings indicated that both the Gaussian process regression and neural network algorithm held promise for predicting greenhouse temperatures. Compared to the camel hair blanket, the rubber-plastic insulation blanket increased the average night-time inner film surface temperature by 0.8 ℃ and the average minimum night-time temperature by 0.6 ℃. For the rubber-plastic board material, it was necessary to implement measures to mitigate wind resistance in greenhouses to guarantee the insulation’s effectiveness.

Key words: insulation blanket, film inner surface temperature, machine learning, Gaussian regression process, neural network algorithm

CLC Number:

S626

ZHU Yin-bin, LUO Qian-liang, LEI Xi-hong, NIU Man-li, WANG Ping-zhi, CHENG Jie-yu, ZHAO Shu-mei. Performance analysis of insulation blanket application based on machine learning[J]. HUBEI AGRICULTURAL SCIENCES, 2025, 64(1): 162-167.

References

[1] NAHAR N M,MARSHALL R H,BRINKWORTH B J.Investigations of flat plate collectors using transparent insulation materials[J]. International journal of solar energy,1995,17(2-3):117-134.
[2] GARZOLI K, BLACKWELL J.An analysis of the nocturnal heat loss from a single skin plastic greenhouse[J]. Journal of agricultural engineering research, 1981, 26:203-214.
[3] 陈端生, 郑海山, 刘步洲. 日光温室气象环境综合研究Ⅰ.墙体、覆盖物热效应研究初报[J]. 农业工程学报, 1990,6(2): 77-81.
[4] 周长吉, 高贺昌, 李艳, 等. 周博士考察拾零(一百二十七) 一种自防水无拼缝橡塑保温被围护的主动储放热组装结构日光温室——记北京华美沃龙农业科技有限公司的创新[J]. 农业工程技术, 2022,42(10): 36-45.
[5] 刘河敬, 席时春. 新型保温材料——橡塑海绵在海洋石油平台及FPSO上的应用[J]. 中国造船, 2007, 48(S):151-154.
[6] 马承伟, 王平智, 赵淑梅, 等. 日光温室保温被材料及保温性能评价[J]. 农业工程技术, 2018,38(31): 12-16.
[7] 张俊芳, 马承伟, 覃密道, 等. 温室覆盖材料传热系数测试台的研究开发[J]. 农业工程学报, 2005(11): 149-153.
[8] 刘晨霞, 马承伟, 张锡玉. 山东寿光代表性保温被保温性能测试分析[J]. 绿色科技, 2019(24): 232-235.
[9] 刘晨霞. 日光温室保温被传热模型的建立及保温性影响因素分析[D]. 北京:中国农业大学, 2015.
[10] WANG D C, WANG M H, QIAO X J.Support vector machines regression and modeling of greenhouse environment[J]. Computers and electronics in agriculture, 2009,66(1): 46-52.
[11] ESCAMILLA-GARCIA A,SOTO-ZARAZUA G M, TOLEDANO-AYALA M, et al. Applications of artificial neural networks in greenhouse technology and overview for smart agriculture development[J]. Applied sciences-basel, 2020,10(11):3835.
[12] 宗成骥, 王建玉, 宋卫堂, 等. 基于天气预报的日光温室夜间逐时气温预测模型构建[J]. 农业工程学报, 2022,38(S1): 218-225.
[13] LIU Y, LI D, WAN S, et al.A long short-term memory-based model for greenhouse climate prediction[J]. International journal of intelligent systems, 2021(1):135-151.
[14] GREENER J G, KANDATHIL S M, MOFFAT L, et al.A guide to machine learning for biologists[J]. Nature reviews molecular cell biology, 2022,23(1): 40-55.
[15] 郑佳运. 模块化植物工厂内环境智能控制模型研究与系统设计[D]. 陕西杨凌:西北农林科技大学, 2023.
[16] 刘晨霞, 马承伟, 王平智, 等. 日光温室保温被传热的理论解析及验证[J]. 农业工程学报, 2015,31(2): 170-176.
[17] 张军华, 陈丹艳, 张仲雄, 等. 多因子约束的卷帘机揭盖被决策方法与控制系统研究[J]. 农业机械学报, 2022,53(9): 354-364.
[18] SNEE R.Regression diagnostics: Identifying influential data and sources of collinearity[J]. Journal of quality technology,1983, 15(3):149-153.
[19] CHAN J Y, LEOW S M, BEA K T, et al.Mitigating the multicollinearity problem and its machine learning approach: A review[J]. Mathematics, 2022, 10(8):1-17.
[20] WEISBERG S.Applied linear regression[M]. Wiley, 2013.368.
[21] 刘晨霞, 马承伟, 王平智, 等. 日光温室保温被保温性能影响因素的分析[J]. 农业工程学报, 2015,31(20): 186-193.
[22] 张俊芳, 马承伟, 覃密道, 等. 温室覆盖材料传热系数测试台的研究开发[J]. 农业工程学报, 2005(11): 149-153.
[23] 马承伟, 苗香雯. 农业生物环境工程[M]. 北京:中国农业出版社, 2005.