• DocumentCode
    235594
  • Title

    Life prediction and classification of failure modes in solid state luminaires using Bayesian Probabilistic Models

  • Author

    Lall, P. ; Junchao Wei ; Sakalaukus, Peter

  • Author_Institution
    Dept. of Mech. Eng., Auburn Univ., Auburn, AL, USA
  • fYear
    2014
  • fDate
    27-30 May 2014
  • Firstpage
    2053
  • Lastpage
    2062
  • Abstract
    A new method has been developed for assessment of the onset of degradation in solid state luminaires to classify failure mechanisms by using metrics beyond lumen degradation that are currently used for identification of failure. Luminous Flux output, Correlated Color Temperature Data on Philips LED Lamps has been gathered under 85°C/85%RH till lamp failure. The acquired data has been used in conjunction with Bayesian Probabilistic Models to identify luminaires with onset of degradation much prior to failure through identification of decision boundaries between lamps with accrued damage and lamps beyond the failure threshold in the feature space. In addition luminaires with different failure modes have been classified separately from healthy pristine luminaires. It is expected that, the new test technique will allow the development of failure distributions without testing till L70 life for the manifestation of failure.
  • Keywords
    Bayes methods; LED lamps; failure analysis; Bayesian probabilistic models; Philips LED lamps; correlated color temperature data; failure mechanisms; failure mode classification; life prediction; lumen degradation; luminous flux output; solid state luminaires; temperature 85 C; Bayes methods; Degradation; Image color analysis; LED lamps; Maintenance engineering; Solids;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Electronic Components and Technology Conference (ECTC), 2014 IEEE 64th
  • Conference_Location
    Orlando, FL
  • Type

    conf

  • DOI
    10.1109/ECTC.2014.6897585
  • Filename
    6897585