基于随机森林模型的真空玻璃保温性能预测*

doi:10.13385/j.cnki.vacuum.2023.05.08

真空 ›› 2023, Vol. 60 ›› Issue (5): 55-59.doi: 10.13385/j.cnki.vacuum.2023.05.08

基于随机森林模型的真空玻璃保温性能预测^*

王元麒¹, 胡杨刚², 王磊²

1.航麒科技（深圳）有限公司,广东深圳 518000;
2.海南大学信息与通信工程学院南海海洋资源利用国家重点实验室,海南海口 570228

收稿日期:2021-10-28 出版日期:2023-09-25 发布日期:2023-09-26
作者简介:王元麒（1995-）,男,辽宁大连人,硕士。通讯作者：王磊,教授。
基金资助:
*国家自然科学基金（62163010）,海南省重点研发计划（ZDYF2022SHFZ026）

Prediction of Vacuum Glass Insulation Performance Based on Random Forest

WANG Yuan-qi¹, HU Yang-gang², WANG Lei²

1. Funky-tech(Shenzhen) Co., Ltd., Shenzhen 518000, China;
2. State Key Lab of Marine Resource Utilisation in South China Sea, College of Information and Communication Engineering, Hainan University, Haikou 570228, China

Received:2021-10-28 Online:2023-09-25 Published:2023-09-26

摘要/Abstract

摘要： 真空玻璃的保温性能与传热系数密切相关,但由于环境因素、测量仪器热源温度等不确定因素的干扰,工业领域真空玻璃的传热系数难以测量,大大降低了生产效率和生产精度。通过构建随机森林算法模型预测了真空玻璃的传热系数,通过均方误差（MSE）对结果做了评估。结果表明,MSE为0.004148,随机森林算法是适合本实验的算法,对于真空玻璃传热系数的预测效果良好。通过特征重要性分析,得出了环境因素和主导因素对预测结果的影响,通过将智能算法应用于真空玻璃的生产中,可使测量时间从几小时缩短到5min。

关键词: 真空玻璃, 保温性能, 传热系数, 随机森林

Abstract: The thermal insulation performance of vacuum glass is closely related to the heat transfer coefficient. However, due to the interference of various uncertain factors such as environmental factors and the heat source temperature of measuring instruments, the thermal conductivity of vacuum glass in industrial circles is difficult to measure, which greatly reduces the production efficiency and production accuracy. By constructing the random forest algorithm model, the heat transfer coefficient of vacuum glass was predicted, and the results were evaluated by mean squared error(MSE). The results show that the MSE is 0.004148, the random forest algorithm is the most suitable algorithm for this experiment, and has a good prediction effect on the heat transfer coefficient of vacuum glass. The effects of environmental factors and dominant factors on the predicted results are obtained through the analysis of characteristic importance. By applying the intelligent algorithm to the production of vacuum glass, the measurement time is shortened from a few hours to 5min.

Key words: vacuum glass, thermal insulation performance, heat transfer coefficient, random forest

中图分类号: TB43;TB71⁺3

王元麒, 胡杨刚, 王磊. 基于随机森林模型的真空玻璃保温性能预测^*[J]. 真空, 2023, 60(5): 55-59.

WANG Yuan-qi, HU Yang-gang, WANG Lei. Prediction of Vacuum Glass Insulation Performance Based on Random Forest[J]. VACUUM, 2023, 60(5): 55-59.

参考文献

[1] 杜萍, 王磊, 王元麒. 基于思维进化优化灰色神经网络在真空玻璃需求中的研究[J]. 真空, 2016, 53(5): 25-28.
[2] WANG L, GASTRO O, WANG Y Q, et al.Computational fluid-dynamics-based simulation of heat transfer through vacuum glass[J]. The European Physical Journal Plus, 2019, 134(7): 351.
[3] YIN H L, LIU S Q, ZHAO L C, et al.Vacuum infiltration molding and mechanical property of short carbon fiber reinforced Ti-based metallic glass matrix composite[J]. Journal of Materials Processing Technology, 2021, 295: 117151.
[4] WANG L, GASTRO O, WANG Y Q, et al.Intelligent modelling to predict heat transfer coefficient of vacuum glass insulation based on thinking evolutionary neural network[J]. Artificial Intelligence Review, 2020, 53(8): 5907-5928.
[5] ALSAIHATI A, ELKATATNY S, MAHMOUD A, et al.Early anomaly detection model using random forest while drilling horizontal wells with a real case study[C]// SPE/IADC Middle East Drilling Technology Conference and Exhibition. OnePetro, 2021.
[6] XUE L, LIU Y T, XIONG Y F, et al.A data-driven shale gas production forecasting method based on the multi-objective random forest regression[J]. Journal of Petroleum Science and Engineering, 2021, 196: 107801.
[7] 张亮, 王磊, 王元麒. 基于RBF神经网络的真空玻璃传热过程建模[J]. 真空, 2017, 54(1): 38-41.
[8] PHAM D T, LIU X.Neural networks for identification, prediction and control[M]. London: Springer-Verlag London Limited, 1995.
[9] 张亮, 王磊, 王元麒. 基于主元分析与RBFNN的真空玻璃传热过程预测[J]. 真空, 2017, 54(3): 66-70.
[10] GUO J W, WANG J, LI Q L, et al.Construction of prediction model of neural network railway bulk cargo floating price based on random forest regression algorithm[J]. Neural Computing and Applications, 2019, 31(12): 8139-8145.
[11] FAREED H, SINGLER J R.Error analysis of an incremental proper orthogonal decomposition algorithm for PDE simulation data[J]. Journal of Computational and Applied Mathematics, 2020, 368: 112525.
[12] HU Y G, WANG L.Prediction of heat transfer of vacuum glass based on intelligent algorithm modeling[C]// 2021 International Conference on Electronic Information Engineering and Computer Science(EIECS). IEEE, 2021: 406-410.
[13] LIU C X, ZHAO R B, PANG M Y.A fully automatic segmentation algorithm for CT lung images based on random forest[J]. Medical Physics, 2020, 47(2): 518-529.
[14] 裴磊. 真空玻璃保温性能检测和真空寿命预测算法研究[D]. 海口: 海南大学, 2017.
[15] 张亮, 王磊, 王元麒, 等. 基于模糊信息粒化和 LSSVM 真空玻璃保温性能预测研究[J]. 广西大学学报(自然科学版), 2017, 42(6): 2230-2238.

相关文章 15

[1]	张哲, 李建昌. 微阵列结构柔性压力传感器研究进展^*[J]. 真空, 2023, 60(5): 13-16.
[2]	李灿民, 张心凤, 魏荣华. 等离子增强磁控溅射制备TiCr基纳米复合涂层的耐冲蚀耐腐蚀性能[J]. 真空, 2023, 60(5): 37-41.
[3]	孙振华, 赵哲, 王丁, 张帆. 连续带钢真空蒸发镀膜设备设计[J]. 真空, 2023, 60(5): 42-46.
[4]	刘文丽, 刘旭, 尹翔. 动态磁场矩形平面磁控靶开发[J]. 真空, 2023, 60(5): 47-50.
[5]	周彤, 李鹏, 曹宏利, 张海龙. 某石英器件内部封闭孔道的等离子清洗技术[J]. 真空, 2023, 60(5): 51-54.
[6]	张以忱. 第二十二讲化学气相沉积（CVD）技术[J]. 真空, 2023, 60(5): 102-104.
[7]	林松盛, 刘若愚, 田甜, 吕亮, 苏一凡, 汪云程, 石倩, 云海涛, 唐鹏, 郑彩凤, 易出山. Cr-CrN-Cr-CrAlN多层膜厚度对结构和性能的影响^*[J]. 真空, 2023, 60(4): 1-7.
[8]	张艳鹏, 曹志强, 付强, 曹磊, 刘旭. 卷绕镀铜工艺对复合集流体电学性能影响研究[J]. 真空, 2023, 60(4): 8-12.
[9]	任冬雪, 孙小杰, 陈兰兰. 功能性PET复合膜的制备及性能研究^*[J]. 真空, 2023, 60(4): 18-23.
[10]	张以忱. 第二十二讲化学气相沉积（CVD）技术[J]. 真空, 2023, 60(4): 85-88.
[11]	孙彬, 刘兴龙, 徐乘远, 王庆, 蔺增. 真空镀膜助力低碳制造与可持续发展^*[J]. 真空, 2023, 60(3): 12-17.
[12]	张以忱. 第二十二讲化学气相沉积（CVD）技术[J]. 真空, 2023, 60(3): 86-88.
[13]	罗军文, 李志方. 印制电路板清洁化镀膜生产线的研制[J]. 真空, 2023, 60(2): 26-29.
[14]	赵文君, 刘玉琢, 蔡妍, 王立哲, 李建平, 牟仁德, 何利民. 扩散处理对低温粉末渗铝涂层组织及硬度的影响研究^*[J]. 真空, 2023, 60(2): 30-33.
[15]	张汉焱, 郑丹旭, 沈奕, 陈玉云. 中频磁控反应溅射氧化硅（SiOx）薄膜绝缘性的研究^*[J]. 真空, 2023, 60(2): 34-38.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于随机森林模型的真空玻璃保温性能预测^*

Prediction of Vacuum Glass Insulation Performance Based on Random Forest

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0