Methods for binning and density estimation of load parameters for prognostics and health management

Nikhil M. Vichare, Peter Rodgers, Michael G. Pecht

    Research output: Contribution to journalArticlepeer-review

    27 Scopus citations

    Abstract

    Environmental and usage loads experienced by a product in the field can be monitored in-situ and used with prognostic models to assess and predict the reliability of the product. This paper presents an approach for recording in-situ monitored loads in a condensed form without sacrificing the load information required for subsequent prognostic assessments. The approach involves optimally binning data in a manner that provides the best estimate of the underlying probability density function of the load parameter. The load distributions were developed using non-parametric histogram and kernel density estimation methods. The use of the proposed binning and density estimation techniques with a prognostic methodology were demonstrated on an electronic assembly.

    Original languageBritish English
    Pages (from-to)149-161
    Number of pages13
    JournalInternational Journal of Performability Engineering
    Volume2
    Issue number2
    StatePublished - Apr 2006

    Keywords

    • Condition monitoring
    • Density estimation
    • Electronic prognostics
    • Health and usage monitoring system (HUMS)
    • Optimal binning
    • Reliability

    Fingerprint

    Dive into the research topics of 'Methods for binning and density estimation of load parameters for prognostics and health management'. Together they form a unique fingerprint.

    Cite this