木质地采暖地板蓄热性能检测及反演方法

doi:10.11707/j.1001-7488.20181103

林业科学 ›› 2018, Vol. 54 ›› Issue (11): 14-19.doi: 10.11707/j.1001-7488.20181103

木质地采暖地板蓄热性能检测及反演方法

周世玉¹, 杜光月², 曹正彬², 刘晓平², 周玉成²

1. 山东建筑大学热能工程学院济南 250101;
2. 山东建筑大学信息与电气工程学院济南 250101

收稿日期:2018-04-02 修回日期:2018-10-29 出版日期:2018-11-25 发布日期:2018-12-04
基金资助:
泰山学者优势特色学科人才团队（2015162）；山东建筑大学校内博士基金（X18006Z）。

Measurement and Inverse Prediction Methods of Heat Storage Performance for Wood Flooring with Geothermal System

Zhou Shiyu¹, Du Guangyue², Cao Zhengbin², Liu Xiaoping², Zhou Yucheng²

1. School of Thermal Engineering, Shandong Jianzhu University Jinan 250101;
2. School of Information and Electrical Engineering, Shandong Jianzhu University Jinan 250101

Received:2018-04-02 Revised:2018-10-29 Online:2018-11-25 Published:2018-12-04

摘要/Abstract

摘要： [目的]基于传热反问题研究方法，采用BP神经网络对地采暖地板蓄热性能进行反演计算，为地采暖地板蓄热性能分析提供理论和方法支撑。[方法]基于CFD软件构建检测腔体数值模型，模拟获取结构单一样本在不同初始温度（50~130℃范围内每间隔5℃设定一个模拟工况）下散热形成的温度场分布数据，并将初始温度为50、60、70、80、90、100、110、120和130℃的温度场分布数据作为神经网络模型的训练集，初始温度为55、65、75、85、95、105、115和125℃的温度场分布数据作为神经网络模型的测试集。[结果]经反复训练比较，获取较优的神经网络模型，其测试集的平均相对误差（MRE）=0.68%，最大相对误差（MAE）=19.51%，均方误差（MSE）=1.18%，拟合度（R²）=0.98。基于该神经网络模型，选取白桦、水曲柳、西南桦、柞木4种典型实木地采暖地板样本进行蓄热性能反演计算，结果显示4种实木地采暖地板的蓄热性能表现为柞木 > 西南桦 > 水曲柳 > 白桦。[结论]经训练的神经网络模型可有效预测不同地采暖地板的蓄热性能，基于BP神经网络反演地采暖地板蓄热性能的方法可行。

关键词: 地采暖地板, 蓄热性能, 传热反问题, 神经网络

Abstract: [Objective] Based on the study method for the inverse heat transfer problem, BP neural network technique is adopted for the inverse calculation of the heat storage of wood flooring with geothermal system. Therefore, provides theoretical and method ological support for the analysis of heat storage performance of wood floor.[Method] Firstly, the numerical model of the testing cavity is established by CFD software. The temperature field data of a single structure sample under different initial temperature range of 50-130℃ are obtained by simulation (different simulation conditions are divided by interval of 5℃). The data are divided into training set and testing set of neural network model. The data of the initial temperature of 50,60,70,80,90,100,110,120,130℃ are used as the training set, while the data of the initial temperature of 55,65,75,85,95,105,115,125℃ are used as the testing set.[Result] After repeated training, a better neural network model is obtained. The average values of the calculation error and the fitting degree of the testing set are:mean relative error (MRE)=0.68%, maximum relative error (MAE)=19.51%, mean square error (MSE)=1.18%, fitting degree (R²)=0.98. Based on this model, Betula platyphylla, Fraxinus mandshurica, Betula alnoides and Quercus mongolica are selected as the four typical solid wood floor samples for the inversion calculation of the heat storage. The results showed that the heat storage performances of the four kinds of solid wood floor are as follows:Quercus mongolica > Betula alnoides > Fraxinus mandshurica > Betula platyphylla.[Conclusion] It can be concluded that the well trained neural network model could effectively predict out the heat storage performance of different wood floor samples, verifying the feasibility of the method based on BP neural network technology to retrieve the thermal storage performance of the wood floor.

Key words: wood flooring with geothermal system, heat storage performance, heat transfer inverse problem, neural network

中图分类号:

S772
TU111

周世玉, 杜光月, 曹正彬, 刘晓平, 周玉成. 木质地采暖地板蓄热性能检测及反演方法[J]. 林业科学, 2018, 54(11): 14-19.

Zhou Shiyu, Du Guangyue, Cao Zhengbin, Liu Xiaoping, Zhou Yucheng. Measurement and Inverse Prediction Methods of Heat Storage Performance for Wood Flooring with Geothermal System[J]. Scientia Silvae Sinicae, 2018, 54(11): 14-19.

参考文献

陈清华,庞立,孟利民,等. 2014. 基于传热反问题的固体材料热扩散系数测算方法, 北京化工大学学报:自然科学版, 41(5):76-82.
(Chen Q H, Pang L, Meng L M, et al. 2014. A method for calculation of the thermal diffusivity of a solid material based on inverse heat conduction problem analysis. Journal of Beijing University of Chemical Technology Natural Science Edition, 41(5):76-82.[in Chinese])
韩雯雯,吴健,刘长亮,等. 2015. 基于导热反问题的二维圆管内壁面第三类边界条件的反演, 机械工程学报, 51(16):171-176.
(Han W W, Wu J, Liu C L, et al. 2015. Inversion of the third boundary condition on the inner wall of a two-dimensional pipe based on inverse heat conduction problems. Journal of Mechanical Engineering, 51(16):171-176.[in Chinese])
沈斌华,姜俊,孙伟圣,等. 2012. 我国地采暖用木质地板的现状.中国人造板,(11):5-8.
(Shen B H, Jiang J, Sun W S, et al. 2012. Status review of heating flooring in China. China Wood-Based Panels,(11):5-8.[in Chinese])
宋馨,张有为,马巨印.2016. 反演高温腔体内壁面温度波动的辐射边界导热反问题,热科学与技术,15(2):104-108.
(Song X, Zhang Y W, Ma J Y. 2016. Inverse heat conduction problem for inner wall temperature fluctuation inversion of high temperature chamber, Journal of Thermal Science and Technology, 15(2):104-108.[in Chinese])
Ahamad S I, Balaji C. 2016. Inverse conjugate mixed convection in a vertical substrate with protruding heat sources:a combined experimental and numerical study. Heat & Mass Transfer, 52(6):1243-1254.
Kumar A, Balaji C. 2010. A principal component analysis and neural network based non-iterative method for inverse conjugate natural convection. International Communications in Heat & Mass Transfer, 53(21/22):4684-4695.
Montana D J, Davis L. 1989. Training feed-forward neutral networks using genetic algorithms. Proceeding of the International Joint Conference on Artificial Intelligence, Los Altos, 762-767.
Ozgur A S, Demir H, Agra O. 2010. Application of artificial neural networks for prediction of natural convection from a heated horizontal cylinder. International Communications in Heat & Mass Transfer, 37(1):68-73.
Rajeev R M, Balaji C. 2008. Optimization of the location of multiple discrete heat sources in a ventilated cavity using artificial neural networks and genetic algorithm. International Communications in Heat & Mass Transfer, 51(9/10):2299-2312.
Rumelhart D E, Hinton G E, Williams R J. 1986. Learning internal representations by error propagation. Parallel distributed processing:Explorations in macrostructure of cognition. Cambridge:Badford Books.
Tahavvor A R, Yaghoubi M. 2008. Natural cooling of horizontal cylinder using artificial neural network(ANN). International Communications in Heat & Mass Transfer, 35(9):1196-1203.

[1]	谢文, 赵小敏, 郭熙, 叶英聪, 孙小香, 匡丽花. 基于RBF组合模型的山地红壤有机质含量光谱估测[J]. 林业科学, 2018, 54(6): 16-23.
[2]	杜光月, 周世玉, 刘大伟, 周玉成. 实木地采暖地板蓄热性能检测技术[J]. 林业科学, 2018, 54(11): 7-13.
[3]	杜光月, 周世玉, 刘大伟, 刘晓平, 周玉成. 基于限幅模糊PID算法的蓄热性能检测仪密闭绝热双腔体温度控制研究[J]. 林业科学, 2018, 54(11): 37-44.
[4]	曹正彬, 刘晓平, 杜光月, 褚鑫, 刘大伟, 周玉成. 基于TWSVM和模糊的木质采暖地板蓄热温度预测模型[J]. 林业科学, 2018, 54(11): 45-52.
[5]	褚鑫, 周世玉, 刘大伟, 杜光月, 曹正彬, 刘晓平, 周玉成. 基于ANFIS的木质采暖地板温度场预测分析[J]. 林业科学, 2018, 54(11): 53-58.
[6]	徐平平, 周玉成, 虞宇翔, 杨科研, 常建民. 耐热增韧型硼酸/热解油共改性酚醛树脂合成工艺[J]. 林业科学, 2018, 54(11): 87-95.
[7]	陈龙现, 葛浙东, 罗瑞, 刘传泽, 刘晓平, 周玉成. 基于CNN的木材内部CT图像缺陷辨识[J]. 林业科学, 2018, 54(11): 127-133.
[8]	周世玉, 杜光月, 褚鑫, 刘晓平, 周玉成. 地采暖木地板释热温度场的BP神经网络预测[J]. 林业科学, 2018, 54(11): 158-163.
[9]	刘大伟, 杜光月, 褚鑫, 曹正彬, 刘晓平, 周玉成. 木质地板蓄热性能温度场实时并行采集方法[J]. 林业科学, 2018, 54(11): 180-186.
[10]	刘存根, 周世玉, 葛浙东, 杜光月, 周玉成. 地采暖地板蓄热性能模型构建与验证[J]. 林业科学, 2018, 54(10): 125-131.
[11]	田静, 邢艳秋, 姚松涛, 曾旭婧, 焦义涛. 基于元胞自动机和BP神经网络算法的Landsat-TM遥感影像森林类型分类比较[J]. 林业科学, 2017, 53(2): 26-34.
[12]	李文敏, 魏虹, 李昌晓, 陈存根. 基于高光谱参数的枫杨叶绿素含量估算模型优化[J]. 林业科学, 2014, 50(4): 55-59.
[13]	马晓君, 齐英杰, 胡万明. 基于BP神经网络算法的木门锁孔槽加工机床热误差建模方法[J]. 林业科学, 2013, 49(12): 121-125.
[14]	李永亮;张怀清;林辉. 基于红边参数与PCA的GA-BP神经网络估算叶绿素含量模型[J]. 林业科学, 2012, 48(9): 22-29.
[15]	王强;胡海清. 基于岭回归和人工神经网络估测森林可燃物负荷量[J]. 林业科学, 2012, 48(9): 108-114.

木质地采暖地板蓄热性能检测及反演方法

Measurement and Inverse Prediction Methods of Heat Storage Performance for Wood Flooring with Geothermal System

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

作者中心

期刊获奖

引证指标

联系方式