浏览全部资源
扫码关注微信
发光材料与器件国家重点实验室 华南理工大学,广东 广州,510640
纸质出版日期:2015-8-3,
收稿日期:2015-4-27,
修回日期:2015-6-26,
扫 描 看 全 文
黄伟明, 文尚胜, 夏云云. 基于BP神经网络的LED可靠性模型研究[J]. 发光学报, 2015,36(8): 962-968
HUANG Wei-ming, WEN Shang-sheng, XIA Yun-yun. Reliability Model of LEDs Based on Artificial Neural Network[J]. Chinese Journal of Luminescence, 2015,36(8): 962-968
黄伟明, 文尚胜, 夏云云. 基于BP神经网络的LED可靠性模型研究[J]. 发光学报, 2015,36(8): 962-968 DOI: 10.3788/fgxb20153608.0962.
HUANG Wei-ming, WEN Shang-sheng, XIA Yun-yun. Reliability Model of LEDs Based on Artificial Neural Network[J]. Chinese Journal of Luminescence, 2015,36(8): 962-968 DOI: 10.3788/fgxb20153608.0962.
根据LED可靠性与相关参数的映射关系
建立拓扑结构为6-12-1的BP神经网络.以实测白光LED芯片的理想因子、结温、色温漂移等参数为输入量
以寿命为输出量
计算模型精度.研究结果表明
该模型有良好的外推能力及鲁棒性
可在短时间内成功预测LED寿命
神经网络训练结果相关系数为99.8%
检验组误差小于3%.
We proposed the 6-12-1 topology BP neural network according to the LED reliability and relevant element. The ideal factor
junction temperature
color temperature drift of the white LED chip and so on were measured as the input and the life as output to calculate the precision of the model. The model shows a good ability of extrapolation and robustness
and can predict the life of the LED in a short time. The linear correlation of ANN reaches 99.8%
and the inspection group error is less than 3%.
发光二极管可靠性BP神经网络权重分析
LEDreliabilityBP neural networkweight analysis
McPherson J W. Reliability Physics and Engineering: Time-to-failure Modeling [M]. Berlin: Springer, 2010.
Rumyantseva S L, Shur M S. Low frequency noise and long-term stability of noncoherent light sources [J]. J. Appl. Phys., 2004, 96(2):966-969.
Rumyantsev S L, Wetzel C, Shur M S. Wavelength-resolved low-frequency noise of GalnN/GaN green light emitting diodes [J]. J. Appl. Phys., 2006, 100(8):084506-1-5
Qian M H, Lin Y D, Sun Y J, et al. Life prediction model for LEDs based on the photo-electrical-thermal-life theory [J]. Acta Optica Sinica (光学学报), 2012, 32(8):823001-1-6 (in Chinese).
Guo W L, Fan X, Cui D S. Rapid reliability evaluation method of LED based on pseudo-failure lifetime [J]. Chin. J. Lumin.(发光学报), 2013, 34(2):213-217 (in Chinese).
Hu Z F, Zhang L D, Wan J X. Application of BP neural network in predicting winter wheat yield based on thermography technology [J]. Spectrosc. Spect. Anal.(光谱学与光谱分析), 2013, 33(6):1587-1592 (in Chinese).
Zheng L H, Li M Z, Pan L, et al. Estimation of soil organic matter and soil total nitrogen based on NIR spectroscopy and BP neural network [J]. Spectrosc. Spect. Anal.(光谱学与光谱分析), 2008, 28(5):1160-1164 (in Chinese).
Sun Y, Zeng W D, Zhao Y Q, et al. Model prediction of processing-property of TC11 titanium alloy using artificial neural network [J]. Rare Met. Mater. Eng.(稀有金属材料与工程), 2011, 40(11):1951-1955 (in Chinese).
Shen H P. Research on Reliability Prediction Mechanism for High-power LEDs . Hangzhou: Zhejiang University, 2008 (in Chinese).
Keppens A, Ryckaert W R, Deconinck G, et al. High power light-emitting diode junction temperature determination from current-voltage characteristics [J]. J. Appl. Phys., 2008, 104(9):093104-1-6.
Keppens A, Ryckaert W R, Deconinck G, et al. Modeling high power light-emitting diode spectra and their variation with junction temperature [J]. J. Appl. Phys., 2010, 108(4):043104-1-6.
Lee C Y, Su A, Liu Y C, et al. In situ measurement of the junction temperature of light emitting diodes using a flexible micro temperature sensor [J]. Sensors, 2009, 9:5068-5075.
Kang J M, Kim J W, Choi J H, et al. Life-time estimation of high-power blue light-emitting diode chips [J]. Microelectron. Reliab., 2009, 49(9-11):1231-1235.
Chen Z Z, Liu P, Qi S L, et al. Junction temperature and reliability of high-power flip-chip light emitting diodes [J]. Mater. Sci. Semicond. Proc., 2007, 10(4-5):206-210.
Garson G D. Interpreting neural-network connection weights [J]. AI Expert, 1991, 6(7):47-51.
0
浏览量
148
下载量
5
CSCD
关联资源
相关文章
相关作者
相关机构