Uncertainty in Prognostics and Health Management : An Overview

This paper presents an overview of various aspects of uncertainty quantification in prognostics and health management. Since prognostics deals with predicting the future behavior of engineering systems and it is almost practically impossible to precisely predict future events, it is necessary to account for the different sources of uncertainty that affect prognostics, and develop a systematic framework for uncertainty quantification and management in this context. Researchers have developed computational methods for prognostics, both in the context of testing-based health management and conditionbased health management. However, one important issue is that, the interpretation of uncertainty for these two different types of situations is completely different. While both the frequentist (based on the presence of true variability) and Bayesian (based on subjective assessment) approaches are applicable in the context of testing-based health management, only the Bayesian approach is applicable in the context of condition-based health management. This paper explains that the computation of the remaining useful life is more meaningful in the context of condition-based monitoring and needs to be approached as an uncertainty propagation problem. Numerical examples are presented to illustrate the various concepts discussed in the paper.

[1]  Distribution type uncertainty due to sparse and imprecise data , 2013 .

[2]  Kai Goebel,et al.  Remaining Useful Life Estimation in Prognosis: An Uncertainty Propagation Problem , 2013 .

[3]  J. Celaya,et al.  Uncertainty Representation and Interpretation in Model-Based Prognostics Algorithms Based on Kalman Filter Estimation , 2012 .

[4]  B. Saha,et al.  Uncertainty Management for Diagnostics and Prognostics of Batteries using Bayesian Techniques , 2008, 2008 IEEE Aerospace Conference.

[5]  Sankaran Mahadevan,et al.  Uncertainty quantification and model validation of fatigue crack growth prediction , 2011 .

[6]  Sankaran Mahadevan,et al.  Uncertainty Quantification in Fatigue Crack Growth Prognosis , 2011 .

[7]  K. Goebel,et al.  Analytical algorithms to quantify the uncertainty in remaining useful life prediction , 2013, 2013 IEEE Aerospace Conference.

[8]  Donald L. Iglehart,et al.  Importance sampling for stochastic simulations , 1989 .

[9]  Huairui Guo,et al.  Predicting remaining useful life of an individual unit using proportional hazards model and logistic regression model , 2006, RAMS '06. Annual Reliability and Maintainability Symposium, 2006..

[10]  Armen Der Kiureghian,et al.  MEASURES OF STRUCTURAL SAFETY UNDER IMPERFECT STATES OF KNOWLEDGE , 1989 .

[11]  P. E. James T. P. Yao,et al.  Probability, Reliability and Statistical Methods in Engineering Design , 2001 .

[12]  C. Bucher.  Adaptive sampling — an iterative fast Monte Carlo procedure , 1988 .

[13]  Colas Schretter,et al.  Monte Carlo and Quasi-Monte Carlo Methods , 2016 .

[14]  M. Eldred,et al.  Efficient Global Reliability Analysis for Nonlinear Implicit Performance Functions , 2008 .

[15]  George Vachtsevanos,et al.  Methodologies for uncertainty management in prognostics , 2009, 2009 IEEE Aerospace conference.

[16]  Charles R Farrar,et al.  Damage prognosis: the future of structural health monitoring , 2007, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[17]  Matthew Daigle,et al.  An Efficient Deterministic Approach to Model-based Prediction Uncertainty Estimation , 2012 .

[18]  Kai Goebel,et al.  Uncertainty in prognostics: Computational methods and practical challenges , 2014, 2014 IEEE Aerospace Conference.

[19]  Hugh McManus,et al.  A framework for understanding uncertainty and its mitigation and exploitation in complex systems , 2006, IEEE Engineering Management Review.

[20]  Jie Gu,et al.  Uncertainty Assessment of Prognostics of Electronics Subject to Random Vibration , 2007, AAAI Fall Symposium: Artificial Intelligence for Prognostics.

[21]  S Sankararaman,et al.  Likelihood-based representation of imprecision due to sparse point data and/or interval data , 2011 .

[22]  R. Rackwitz,et al.  First-order concepts in system reliability , 1982 .

[23]  K. Goebel,et al.  Prognostics approach for power MOSFET under thermal-stress aging , 2012, 2012 Proceedings Annual Reliability and Maintainability Symposium.

[24]  Kai Goebel,et al.  A Novel Computational Methodology for Uncertainty Quantification in Prognostics Using The Most Probable Point Concept , 2013 .

[25]  Matthew Daigle,et al.  Model-based prognostics under limited sensing , 2010, 2010 IEEE Aerospace Conference.

[26]  Raphael T. Haftka,et al.  Uncertainty Reduction of Damage Growth Properties Using Structural Health Monitoring , 2010 .

[27]  Kai Goebel,et al.  Why is the Remaining Useful Life Prediction Uncertain , 2013 .

[28]  A. Kiureghian,et al.  Second-Order Reliability Approximations , 1987 .

[29]  Stephen J. Engel,et al.  Prognostics, the real issues involved with predicting life remaining , 2000, 2000 IEEE Aerospace Conference. Proceedings (Cat. No.00TH8484).

[30]  K. Doliński,et al.  First-order second-moment approximation in reliability of structural systems: Critical review and alternative approach , 1982 .

[31]  Sankaran Mahadevan,et al.  Separating the contributions of variability and parameter uncertainty in probability distributions , 2013, Reliab. Eng. Syst. Saf..

[32]  Wei-Liem Loh.  On Latin hypercube sampling , 1996 .

[33]  G. Kacprzynski,et al.  Advances in uncertainty representation and management for particle filtering applied to prognostics , 2008, 2008 International Conference on Prognostics and Health Management.