New method of online testing and data processing for LED lamps  

LED灯具在线测试和数据处理的新方法（英文）

作　　者：郝剑[1,2] 荆雷[1] 客洪亮 王尧[1,2] 高群[1] 王潇洵[1,2] 孙强[1] 续志军[1] 

机构地区：[1]中国科学院长春光学精密机械与物理研究所,长春130033 [2]中国科学院大学大珩学院,北京100049

出　　处：《Journal of Southeast University(English Edition)》2016年第4期415-419,共5页东南大学学报（英文版）

基　　金：The Cui Can Project of Chinese Academy of Sciences(No.KZCC-EW-102);the National High Technology Research and Development Program of China(863 Program)(No.2015AA03A101,2013AA03A116)

摘　　要：In order to achieve quick and accurate lifetime prediction of LED lighting products under the testing time of 2 000 h, a method of online testing of luminous flux is proposed under the condition of temperature stress.Exponential fitting of lumen maintenance, the Bayesian estimation of failure probability, the Weibull distribution of lifetime and the Arrhenius model of the decay rate are used in combination to acquire the distribution of failure probability over time at the ambient temperatures of 25 ℃. The lifetime test of the same lamps based on the Energy Star standard under the testing time of 6 000 h is also implemented to verify the effectiveness of the method. The errors of lifetimes acquired with the proposed method are 7%, 4%, 3% and 1% at the failure probabilities of 62. 3%, 10%, 5% and 1%,respectively.为实现LED照明产品寿命及其可靠性的快速准确预测,在测试时间为2 000 h和温度应力的条件下,提出了一种加速老化的在线测量光通量的方法.结合使用光通维持率的指数模型、失效概率的贝叶斯估计、威布尔分布和阿伦纽斯模型,以获取25℃条件下的失效概率分布.同时,采用能源之星LM-79-08标准推荐的常温下6 000 h测量方法对相同的产品进行寿命验证.结果表明:当失效概率为62.3%,10%,5%和1%时,所提计算方法得到的寿命误差分别为7%,4%,3%和1%.

关 键 词：online testing accelerated test Bayesian estimation reliability analysis 

分 类 号：O432.2[机械工程—光学工程]