基于有限元算法和人工神经网络结合的多芯片LED光源多物理场分析

刘宏伟; 于丹丹; 牛萍娟; 张赞允; 郭凯; 王迪; 张建新; 郏成奎; 王闯; 吴超瑜

doi:10.3788/fgxb20194006.0795

您当前的位置：

首页 >

文章列表页 >

基于有限元算法和人工神经网络结合的多芯片LED光源多物理场分析

发光学应用及交叉前沿 | 更新时间：2020-08-12

- 基于有限元算法和人工神经网络结合的多芯片LED光源多物理场分析
- Multi-physics Analysis of Multi-chip LED Light Source Based on Finite Element Method and Artificial Neural Network
- 发光学报 2019年40卷第6期页码：795-802
- 作者机构：
  
  1. 天津工业大学电子与信息工程学院, 天津 300387
  2. 天津工业大学天津市光电检测与系统重点实验室天津,300387
  3. 飞利浦(中国)投资有限公司天津,300010
  4. 天津三安光电有限公司天津,300384
- 作者简介：
- 基金信息：
  
  国家自然科学基金（61575144，61504093）();天津市科技计划（16YFXTGX00230，18JCYBJC85400）();天津市教委科研计划（2017Z
- DOI：10.3788/fgxb20194006.0795
  中图分类号： O472+.3
- 纸质出版日期：2019-6-5，
  
  网络出版日期：2018-11-8，
  
  收稿日期：2018-8-16，
  
  修回日期：2018-10-19，
扫描看全文
刘宏伟, 于丹丹, 牛萍娟等. 基于有限元算法和人工神经网络结合的多芯片LED光源多物理场分析[J]. 发光学报, 2019,40(6): 795-802

LIU Hong-wei, YU Dan-dan, NIU Ping-juan etc. Multi-physics Analysis of Multi-chip LED Light Source Based on Finite Element Method and Artificial Neural Network[J]. Chinese Journal of Luminescence, 2019,40(6): 795-802
刘宏伟, 于丹丹, 牛萍娟等. 基于有限元算法和人工神经网络结合的多芯片LED光源多物理场分析[J]. 发光学报, 2019,40(6): 795-802 DOI： 10.3788/fgxb20194006.0795.

LIU Hong-wei, YU Dan-dan, NIU Ping-juan etc. Multi-physics Analysis of Multi-chip LED Light Source Based on Finite Element Method and Artificial Neural Network[J]. Chinese Journal of Luminescence, 2019,40(6): 795-802 DOI： 10.3788/fgxb20194006.0795.

摘要

多芯片LED光源的可靠性分析涉及到光、电、热多个物理场，高精度的多场分析结果会导致计算资源过多、计算时间过长、计算难度大等问题。为解决上述问题，本文分别利用传统的有限元算法（FEM）和高效的人工神经网络方法（ANN）进行LED光源温度分析，并讨论两种方法的优劣性。最后，通过将FEM分析单一传热物理场的优势与ANN计算时间短、计算资源需求低的优势相结合，归纳出一种更为高效的方法来进行多芯片LED光源的散热分析。利用该方法，ANN的预测数据与训练数据之间的相关系数达到了0.997 79，预测结果与实际热分布图有良好的匹配，计算资源相比传统的FEM方法节约了59%。该方法的应用能够在满足精度的前提下耗费更少的计算资源和时间，同时提高了分析的灵活性。除此之外，该方法对求解大功率LED光源寿命等可靠性问题也具有一定的参考价值。

Abstract

The reliability analysis of multi-chip LED light sources involves multiple physical fields of light

electricity and heat. The high-precision analysis results will lead to too many calculation resources

too long calculation time and difficult calculation. To solve the above problems

the traditional finite element method(FEM) and efficient artificial neural network(ANN) method are used to analyze the temperature of LED light source

and the advantages and disadvantages of both are discussed. Finally

by combining the advantages of FEM analysis in a single heat transfer physics field with the advantages of ANN in little calculation time and low computational resource requirements

a more efficient method for heat dissipation analysis of multi-chip LED light sources is summarized. Using this method

the correlation coefficient between the prediction data and the training data of ANN reaches 0.997 79

and the prediction result has a good match with the actual heat distribution. The computational resource saves 59% compared with the traditional FEM method. The application of this method can consume fewer computing resources and time based on satisfying the accuracy

while improving the flexibility of analysis. In addition

this method has certain reference value for solving the reliability problems such as the lifetime of high-power LED light source.

关键词

多芯片LED光源多场耦合散热分析有限元算法人工神经网络

Keywords

multi-chip LED light sourcemultiphysics field couplingthermal analysisfinite element methodartificial neural network

references

KRAMES M R, SHCHEKIN O B, MUELLER-MACH R, et al.. Status and future of high-power light-emitting diodes for solid-state lighting[J]. J. Disp. Technol., 2007, 3(2):160-175.

KIM J K, SCHUBERT E F. Transcending the replacement paradigm of solid-state lighting[J]. Opt. Express, 2008, 16(26):21835-21842.

王明亮, 程广斌, 郑志满, 等. 心电监护仪显示屏幕采用LED背光的改造与应用[J]. 医疗卫生装备, 2016, 37(7):163-164. WANG M L, CHENG G B, ZHENG Z M, et al.. The retrofit and application of LED backlight in display screen of ECG monitor[J]. Chin. Med. Equip. J., 2016, 37(7):163-164. (in Chinese)

CHUIN L H, OMAR A F, ABDULLAH M Z, et al.. Characterization and evaluation of PIV illumination system using high power light emitting diodes for watertank applications[J]. Instrum. Exp. Tech., 2018, 61(3):436-444.

BOROWIK B, BOROWIK B, KARPINSKYI V, et al.. Microcontroller PIC based traffic light system with collision detection[C]. Proceedings of The 20179th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems:Technology and Applications, Bucharest, Romania, 2017:118-123.

KUKHTA M S, SIDORENKO E V, SIMUTKIN G G, et al.. LED-technologies for bright light therapy[J]. J. Phys.:Conf. Ser., 2018, 1015:032075-1-5.

杨凯. 大功率LED及其灯具的光热结构设计和环境可靠性分析[D]. 杭州:浙江大学, 2016. YANG K. Optical and Thermal Structure Design and Environmental Reliability Analysis of High Power Light-emitting Diodes[D]. Hangzhou:Zhejiang University, 2016. (in Chinese)

晏建宇, 王双喜, 刘高山, 等. 大功率LED散热技术研究进展[J]. 照明工程学报, 2013, 24(5):84-89. YAN J Y, WANG S X, LIU G S, et al.. Development of cooling technology for high-power light emitting diode[J]. China Illum. Eng. J., 2013, 24(5):84-89. (in Chinese)

LEI W D, LIU C, QIN X F, et al.. Iterative coupling of precise integration FEM and TD-BEM for elastodynamic analysis[J]. Struct. Eng. Mech., 2018, 67(4):317-326.

MIYAZAKI T, INOUE T, NODA N A. Practical method for analyzing singular index and intensity of singular stress field for three dimensional bonded plate[C]. Proceedings of Material Strength and Applied Mechanics, Kitakyushu City, Japan, 2018:1-8.

ALBERDI-PAGOLA M, POULSEN S E, LOVERIDGE F, et al.. Comparing heat flow models for interpretation of precast quadratic pile heat exchanger thermal response tests[J]. Energy, 2018, 145:721-733.

陈锡栋, 杨婕, 赵晓栋, 等. 有限元法的发展现状及应用[J]. 中国制造业信息化, 2010, 39(11):6-8. CHEN X D, YANG J, ZHAO X D, et al.. The status and development of finite element method[J]. Manuf. Inf. Eng. China, 2010, 39(11):6-8. (in Chinese)

OSORIO J C, CERROLAZA M, PEREZ M. Optimising the stiffness matrix integration of n-noded 3D finite elements[J]. Int. J. Comput. Sci. Eng., 2018, 16(2):173.

韩力群. 人工神经网络理论、设计及应用[M]. 北京:化学工业出版社, 2002. HAN L Q. Artificial Neural Network Theory, Design and Application[M]. Beijing:Chemical Industry Press, 2002. (in Chinese)

SHIN B R, SON H S, LEE S P, et al.. A gesture recognition system using a flexible epidermal tactile sensor based on artificial neural network[C]. Proceedings of The 2017 International Conference on Robotics and Automation Sciences, Hong Kong, China, 2017:195-198.

DEY R, GHOSHAL A, TUDU B. Electromyogram (EMG) signal categorization in parkinson's disease tremor detection by applying MLP (Multilayer perceptron) technique:a review[M]. KONKANI A, BERA R, PAUL S. Advances in Systems, Control and Automation, Singapore:Springer, 2018:693-699.

NADIRI A A, GHAREKHANI M, KHATIBI R, et al.. Groundwater vulnerability indices conditioned by Supervised Intelligence Committee Machine(SICM)[J]. Sci. Total Environ., 2017, 574:691-706.

NAJAFI B, ARDABILI S F, MOSAVI A, et al.. An Intelligent artificial neural network-response surface methodology method for accessing the optimum biodiesel and diesel fuel blending conditions in a diesel engine from the viewpoint of exergy and energy analysis[J]. Energies, 2018, 11(4):860-1-18.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

室内可见光通信高精度定位系统设计