Identifying Optimal Prognostic Parameters from Data: A Genetic Algorithms Approach

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Mar 26, 2021
Jamie Coble J. Wesley Hines

Abstract

The ultimate goal of most prognostic systems is accurate prediction of the remaining useful life of individual systems or components based on their use and performance. This class of prognostic algorithms is termed Effects-Based or Type III Prognostics. Traditional individual- based prognostics involve identifying an appropriate degradation measure to characterize the system's progression to failure. These degradation measures may be sensed measurements, such as temperature or vibration level, or inferred measurements, such as model residuals or physics-based model predictions using other sensed measurements. Often, it is beneficial to combine several measures of degradation to develop a single parameter, called a prognostic parameter. A parametric model is fit to this parameter and then extrapolated to some predefined critical failure threshold to estimate the system's remaining useful life. Commonly, identification of a prognostic parameter is accomplished through visual inspection of the available information and engineering judgment. However, a set of metrics to characterize the suitability of prognostic parameters has been proposed. These metrics include monotonicity, prognosability, and trendability. Monotonicity characterizes a parameter's general increasing or decreasing nature. Prognosability measures the spread of the parameter's failure value for a population of systems. Finally, trendability indicates whether the parameters for a population of systems have the same underlying trend,and hence can be described by the same parametric function. This research formalizes these metrics in a way that is robust to the noise found in real world systems. The metrics are used in conjunction with a Genetic Algorithms optimization routine to identify an optimal prognostic parameter for the Prognostics and Health Management (PHM) Challenge data from the 2008 PHM conference.

 

How to Cite

Coble, J., & Hines, . J. W. (2021). Identifying Optimal Prognostic Parameters from Data: A Genetic Algorithms Approach. Annual Conference of the PHM Society, 1(1). Retrieved from https://papers.phmsociety.org/index.php/phmconf/article/view/1404
Abstract 1423 | PDF Downloads 830

##plugins.themes.bootstrap3.article.details##

Keywords

feature extraction, machine learning

References
(Chinnam, 1999) Chinnam, R.B., "On-line Reliability Estimation of Individual Components, Using Degradation Signals", IEEE Transactions on Reliability, Vol 48, No 4, Dec 1999, pp. 403-412.
(Coble and Hines, 2009) Coble, J. and J.W. Hines, "Fusing Data Sources for Optimal Prognostic Parameter Selection." Sixth American Nuclear Society International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies NPIC&HMIT 2009, Knoxville, Tennessee, April 5-9, 2009.
(Gelman et al, 2004) Gelman, A., J. Carlin, H. Stern, and D. Rubin, Bayesian Data Analysis 2nd ed. Boca Raton: Chapman and Hall/CRC: 2004.
(Girish et al, 2003) Girish, T., S.W. Lam, J.S.R. Jayaram, "Reliability Prediction Using Degradation Data – A Preliminary Study Using Neural Network- based Approach," Proc. European Safety and Reliability Conference (ESREL 2003), Maastricht, The Netherlands, Jun. 15-18, 2003.
(Haupt and Haupt, 2004) Haupt and Haupt. Practical Genetic Algorithms, John Wiley & Sons Ltd, Hoboken, New Jersey: 2004.
(Hines et al, 2006) Hines, J.W., R. Seibert, S.A. Arndt, "Technical Review of On-Line Monitoring Techniques for Performance Assessment (NUREG/CR-6895) V ol. 1, State-of-the-Art." Published January, 2006.
(Hines et al, 2007) Hines, J.W., J. Garvey, J. Preston, and A. Usynin, “Empirical Methods for Process and Equipment Prognostics,” Reliability and Maintainability Symposium RAMS, 2007.
(Lindely and Smith, 1972) Lindely, D.V. and A.F. Smith, "Bayes Estimates for Linear Models," Journal of the Royal Statistical Society (B), Vol 34, No 1, 1972, pp. 1-41.
(Lu and Meeker, 1993) Lu, C.J. and W.Q. Meeker, "Using Degradation Measures to Estimate a Time-to- Failure Distribution," Technometrics, Vol 35, No 2, May 1993, pp. 161-174.
(Meeker et al, 1998) Meeker, W.Q., L.A. Escobar, and C.J. Lu, “Accelerated degradation tests: modeling and analysis,” Technometrics, vol. 40, no. 2, pp. 89-99, 1998.
(Robinson and Crowder, 2000) Robinson, M.E. and M.T. Crowder, "Bayesian Methods for a Growth- Curve Degradation Model with Repeated Measures," Lifetime Data Analysis, Vol 6, 2000, pp. 357-374.
(Saxena et al, 2008) Saxena, A., K. Goebel, D. Simon, N. Eklund, "Prognostics Challenge Competition Summary: Damage Propagation Modeling for Aircraft Engine Run-to-Failure Simulation," PHM '08, Denver CO, Oct 6-9, 2008.
(Upadhyaya et al, 1994) Upadhyaya, B.R., M. Naghedolfeizi, and B. Raychaudhuri, "Residual Life Estimation of Plant Components," P/PM Technology, June 1994, pp. 22-29.
(Wald, 1945) Wald, A. "Sequential Tests of Statistical Hypotheses." Annals of Mathematical Statistics 16 (2): 117–186.
(Wang and Coit, 2004) Wang, P. and D.W. Coit, "Reliability Prediction based on Degradation Modeling for Systems with Multiple Degradation Measures," Proc. of the 2004 Reliability and Maintainability Symposium, 2004, pp. 302-307.
Section
Poster Presentations