|
|
Parameter sensitivity analysis of fin based on neural network
in heat exchanger |
XIAO Bao-lan1,2, YU Xiao-li1, HAN Song1, LU Guo-dong3, XIA Li-feng3 |
1. Power Machinery and Vehicular Engineering Institute, Zhejiang University, Hangzhou 310027, China;
2. Mechanical Engineering Department, Zhejiang University City College, Hangzhou 310015, China;
3. Zhejiang Yinlun Machinery Limited Company, Tiantai 317200, China |
|
|
Abstract Two different 3-layer back propagation (BP) neural network models were established in order to explore the feasibility of applying neural network technology to analyze the parametric effect on performance in heat exchanger (HX). The models were trained and optimized to predict the heat transfer performance and flow resistance of a plate-fin HX. The parameter sensitivity analysis of fin was conducted according to the prediction results. The data of train and test samples were from many wind tunnel tests and simulation results. The models had two and six hidden layer neurons irrespectively after optimized. The transfer functions of hidden and output layers were tansig and purelin function irrespectively, and the train function was based on LevenbergMarquardt (L-M) method. Results show that neural network can predict the effect of fin parameter on HX performance. The results of fin parameter sensitivity analysis accorded well with the engineering experience.
|
Published: 03 March 2011
|
|
基于神经网络的换热器翅片参数灵敏度分析
为了探索将人工神经网络技术应用于翅片参数对换热器(HX)性能影响研究的可行性,建立2个结构不同的3层反向传播(BP)神经网络进行训练及优化.分别对流动阻力特性和传热特性进行性能预测,根据预测结果进行翅片参数的灵敏度分析.训练和测试样本数据来源于大量的风洞实验和数值仿真结果.经过优化后的预测传热和流动阻力的网络隐层神经元个数分别为2和6,隐层和输出层的传递函数分别为tansig和purelin函数,采用基于LevenbergMarquardt(LM)算法的训练函数.网络性能测试结果表明,人工神经网络以优越的非线性映射能力,能够很好地预测翅片参数变化对换热器性能的影响.翅片参数灵敏度分析结果与实践工程经验比较吻合.
|
|
[1] KAYS W M, LONDON A L.紧凑式热交换器[M]. 宣益民,张后雷,译. 北京:科学出版社,1997:45-57.
[2] HACHEMI A. Experimental study of thermal performance of offset rectangular plate fin absorberplates [J]. Renewable Energy, 1999, 17(3): 371-384.
[3] DIDARUL I M, OYAKAWA K, YAGA M, et al. Study on heat transfer and fluid flow characteristics with short rectangular plate fin of different pattern [J]. Experimental Thermal and Fluid Science, 2007, 31(4): 367-379.
[4] AZHARUL K M D, HAWLADER M N A. Performance investigation of flat plate, vcorrugated and finned air collectors [J]. Energy, 2006, 31(4): 452-470.
[5] YOUCEFALI S, DESMONS J Y. Numerical and experimental study of a solar equipped with offset rectangular plate fin absorber plate [J]. Renewable Energy, 2006, 31(13): 2063-2075.
[6] WEN Jian, LI Yanzhong, ZHOU Aimin, et al. An experimental and numerical investigation of flow patterns in the entrance of platefin heat exchanger [J]. International Journal of Heat and Mass Transfer, 2006, 49(9/10): 1667-1678.
[7] FOLI K, OKABE T, OLHOFER M, et al. Optimization of micro heat exchanger: CFD, analytical approach and multiobjective evolutionary algorithms [J]. International Journal of Heat and Mass Transfer, 2006, 49(5/6): 1090-1099.
[8] 王晓萍, 孙继洋, 金鑫. 基于BP神经网络的钱塘江水质指标的预测[J]. 浙江大学学报: 工学版, 2007, 41(2): 361-364.
WANG Xiaoping, SUN Jiyang, JIN Xin. Prediction of water quality index in Qiantang River based on BP neural network model [J]. Journal of Zhejiang University: Engineering Science, 2007, 41(2): 361-364.
[9] 陈太聪, 韩大建, 苏成. 参数灵敏度分析的神经网络方法及其工程应用[J]. 计算力学学报, 2004, 21(6): 752-756.
CHEN Taicong, HAN Dajian, SU Cheng. Neural network method in parameter sensitivity analysis and its application in engineering [J]. Chinese Journal of Computational Mechanics, 2004, 21(6): 752-756.
[10] 赵亮, 胡旭晓, 潘双夏, 等. 基于动态模糊神经网络的产品成本估算[J]. 浙江大学学报: 工学版, 2006, 40(2): 304-308.
ZHAO Liang, HU Xuxiao, PAN Shuangxia, et al. Product cost estimation based on dynamic fuzzy neural network [J]. Journal of Zhejiang University: Engineering Science, 2006, 40(2): 304-308.
[11] KEMAL C M, MASAYOSHI T. Friction modeling and compensation for motion control using hybrid neural network models [J]. Engineering Applications of Artificial Intelligence, 2007, 20(7): 898-911.
[12] ADNAN S, TAYFUN M, SINAN U. Determination of efficiency of flatplate solar collectors using neural network approach [J]. Expert Systems with Applications, 2008, 35(4): 1533-1539.
[13] TCHABAN T, TAYLOR M J, GRIFFIN A. Establishing impacts of the inputs in a feedforward neural network [J]. Neural Compute Application, 1998, 7(4): 309-317. |
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
|
Shared |
|
|
|
|
|
Discussed |
|
|
|
|