Prognostics-Based LED Qualification Using Similarity-Based Statistical Measure With RVM Regression Model

Light-emitting diodes (LEDs) are widely used for general lighting and display applications. As the demand for LEDs has grown, the need to quickly qualify them has emerged. To address this issue, this paper introduces a prognostics-based qualification method using an efficient relevance vector machine (RVM) regression model that reduces the qualification testing time of LEDs from 6000 h (as recommended by industry standards) to 210 h. The developed method predicts LED remaining useful life (RUL) by calculating the accumulated sum of products of similarity weights and historical LED RUL values at the 210th hour. Specifically, a similarity weight, defined as the degree of affinity between two different LED's degradation trends, is derived from the difference between a test unit's degradation trend and a training unit's degradation trend. Likewise, the RVM is used to represent a unit's degradation behavior and facilitates the reduction of unit-to-unit variations by precisely capturing transient degradation dynamics.

[1]  Bo-Suk Yang,et al.  Intelligent prognostics for battery health monitoring based on sample entropy , 2011, Expert Syst. Appl..

[2]  Bo Guo,et al.  Online Capacity Estimation of Lithium-Ion Batteries Based on Novel Feature Extraction and Adaptive Multi-Kernel Relevance Vector Machine , 2015 .

[3]  Stoyan Stoyanov,et al.  Prognostics and Health Monitoring of High Power LED , 2012, Micromachines.

[4]  Nagi Gebraeel,et al.  Residual life predictions from vibration-based degradation signals: a neural network approach , 2004, IEEE Transactions on Industrial Electronics.

[5]  P. V. Varde,et al.  Light emitting diodes reliability review , 2012, Microelectron. Reliab..

[6]  Sheng-wei Fei,et al.  Fault Diagnosis of Bearing Based on Cauchy Kernel Relevance Vector Machine Classifier with SIWPSO , 2015 .

[7]  Michael R. Krames,et al.  High Power LEDs – Technology Status and Market Applications , 2002 .

[8]  Sheng-wei Fei.  Kurtosis forecasting of bearing vibration signal based on the hybrid model of empirical mode decomposition and RVM with artificial bee colony algorithm , 2015, Expert Syst. Appl..

[9]  Michael E. Tipping.  The Relevance Vector Machine , 1999, NIPS.

[10]  Ye Tao,et al.  A novel health indicator for on-line lithium-ion batteries remaining useful life prediction , 2016 .

[11]  Takeshi Yanagisawa,et al.  Estimation of the degradation of InGaN/AlGaN blue light-emitting diodes , 1997 .

[12]  Sheng-wei Fei,et al.  A Multiple-Kernel Relevance Vector Machine with Nonlinear Decreasing Inertia Weight PSO for State Prediction of Bearing , 2015 .

[13]  George Eastman House,et al.  Sparse Bayesian Learning and the Relevance Vector Machine , 2001 .

[14]  Jianbo Yu,et al.  A similarity-based prognostics approach for Remaining Useful Life estimation of engineered systems , 2008, 2008 International Conference on Prognostics and Health Management.

[15]  John D. Bullough,et al.  What is Useful Life for White Light LEDs , 2001 .

[16]  Maria Gabriella Masi,et al.  A test set for LEDs life model estimation , 2010, 2010 IEEE Instrumentation & Measurement Technology Conference Proceedings.

[17]  Laurent Bechou,et al.  Long‐term Reliability Prediction of 935 nm LEDs Using Failure Laws and Low Acceleration Factor Ageing Tests , 2005 .

[18]  Miran Bürmen,et al.  Accelerated estimation of spectral degradation of white GaN-based LEDs , 2006 .

[19]  Peter W. Tse,et al.  A Relevance Vector Machine-Based Approach with Application to Oil Sand Pump Prognostics , 2013, Sensors.

[20]  M. Pecht,et al.  Physics-of-Failure-Based Prognostics and Health Management for High-Power White Light-Emitting Diode Lighting , 2011, IEEE Transactions on Device and Materials Reliability.

[21]  Peter W. Tse,et al.  Anomaly Detection Through a Bayesian Support Vector Machine , 2010, IEEE Transactions on Reliability.

[22]  Qiang Miao,et al.  Prognostics of lithium-ion batteries based on relevance vectors and a conditional three-parameter capacity degradation model , 2013 .

[23]  Chao Hu,et al.  Online Estimation of Lithium-Ion Battery Capacity Using Sparse Bayesian Learning , 2015, DAC 2015.

[24]  Xiupeng Li,et al.  Degradation modeling of mid-power white-light LEDs by using Wiener process. , 2015, Optics express.

[25]  Kai Goebel,et al.  Comparison of prognostic algorithms for estimating remaining useful life of batteries , 2009 .

[26]  Datong Liu,et al.  Lithium-ion battery remaining useful life estimation with an optimized Relevance Vector Machine algorithm with incremental learning , 2015 .

[27]  M. Pecht,et al.  Lifetime Estimation of High-Power White LED Using Degradation-Data-Driven Method , 2012, IEEE Transactions on Device and Materials Reliability.

[28]  Lei Hu,et al.  Modeling the Relationship between Vibration Features and Condition Parameters Using Relevance Vector Machines for Health Monitoring of Rolling Element Bearings under Varying Operation Conditions , 2015 .

[29]  Yu Peng,et al.  A Health Indicator Extraction and Optimization Framework for Lithium-Ion Battery Degradation Modeling and Prognostics , 2015, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[30]  Byeng D. Youn,et al.  A generic probabilistic framework for structural health prognostics and uncertainty management , 2012 .

[31]  G. Meneghesso,et al.  Analysis of DC current accelerated life tests of GaN LEDs using a Weibull-based statistical model , 2005, IEEE Transactions on Device and Materials Reliability.

[32]  Michael G. Pecht,et al.  Predicting long-term lumen maintenance life of LED light sources using a particle filter-based prognostic approach , 2015, Expert Syst. Appl..

[33]  M. Craford,et al.  Status and Future of High-Power Light-Emitting Diodes for Solid-State Lighting , 2007, Journal of Display Technology.

[34]  Michael Pecht,et al.  Prognostics of Chromaticity State for Phosphor-Converted White Light Emitting Diodes Using an Unscented Kalman Filter Approach , 2014, IEEE Transactions on Device and Materials Reliability.

[35]  Miran Bürmen,et al.  Prediction of intensity and color degradation of LEDs , 2007, SPIE OPTO.

[36]  Michael E. Tipping.  Bayesian Inference: An Introduction to Principles and Practice in Machine Learning , 2003, Advanced Lectures on Machine Learning.

[37]  Yu Guo,et al.  A Hybrid Prognostic Approach for Remaining Useful Life Prediction of Lithium-Ion Batteries , 2016 .

[38]  Pradeep Lall,et al.  Prediction of L70 Life and Assessment of Color Shift for Solid-State Lighting Using Kalman Filter and Extended Kalman Filter-Based Models , 2015, IEEE Transactions on Device and Materials Reliability.

[39]  Vladimir Vapnik,et al.  An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.

[40]  Michael G. Pecht,et al.  Anomaly Detection of Light-Emitting Diodes Using the Similarity-Based Metric Test , 2014, IEEE Transactions on Industrial Informatics.

[42]  Pradeep Lall,et al.  Assessment of Lumen Degradation and Remaining Life of Light-Emitting Diodes Using Physics-Based Indicators and Particle Filter , 2015 .

[43]  Paul S. Martin,et al.  Illumination with solid state lighting technology , 2002 .

[44]  S. Chuang,et al.  Kinetic model for degradation of light-emitting diodes , 1997 .

[45]  Lei Deng,et al.  Performance characteristics of high-power light-emitting diodes , 2004, SPIE Optics + Photonics.

[46]  Jean Paul Freyssinier,et al.  Solid-state lighting: failure analysis of white LEDs , 2004 .

[47]  Bongtae Han,et al.  Hierarchical Life Prediction Model for Actively Cooled LED-Based Luminaire , 2010, IEEE Transactions on Components and Packaging Technologies.