Abstract
The performance of many engineering systems is gradually degraded, and eventually, the systems will fail under repeated usage conditions. Consider that a through-the-thickness center crack exists in an infinite plate under mode I fatigue loading condition.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
All MATLAB codes in this book can be found in the companion website http://www2.mae.ufl.edu/nkim/PHM/. The naming convention is functionname.m. For example, the MATLAB code for least squares method is LS.m.
- 2.
In this text, many data are generated from the assumed true parameters. This is useful to check if the identified parameters are accurate or not, compared to the true parameters.
- 3.
More specifically, the following condition is required: \( {\mathbf{y}}^{\text{T}} {\bar{\mathbf{y}}} = {\mathbf{z}}^{\text{T}} {\bar{\mathbf{y}}} \), where \( {\bar{\mathbf{y}}} \) is the constant vector all of whose elements are the mean data and \( {\mathbf{z}} \) is a vector of model predictions at \( x_{k} \).
- 4.
More detailed information on the variance of the parameters are found in Montgomery et al. (1982).
- 5.
A sample mean of \( n_{y} \) data from the population \( A \) is not the same if another \( n_{y} \) data are collected, which means the sample mean is also a random variable and denoted by \( \bar{A} \). In this case, the mean and standard deviation of \( \bar{A} \) is \( \mu \) and \( \sigma /\sqrt {n_{y} } \), respectively. See a book by Haldar and Mahadevan (2000).
- 6.
The confidence/prediction intervals are meaningful under the assumption that the model form is correct. If most degradation data are obtained only at early stage, the intervals will be narrow, but the error of degradation prediction at future cycles can be large when the prediction performed based on a different model form from true behavior. Usually, however, more data reflect more degradation behavior, which means the degradation prediction taking account of uncertainty becomes more reliable as more data are employed.
References
An D, Choi JH, Kim NH (2012) Identification of correlated damage parameters under noise and bias using Bayesian inference. Struct Health Monit 11(3):293–303
An D, Choi JH, Schmitz TL et al (2011) In-situ monitoring and prediction of progressive joint wear using Bayesian statistics. Wear 270(11–12):828–838
Bretscher O (1995) Linear algebra with applications. Prentice Hall, New Jersey
Coppe A, Haftka RT, Kim NH (2010) Uncertainty reduction of damage growth properties using structural health monitoring. J Aircraft 47(6):2030–2038
Dalal M, Ma J, He D (2011) Lithium-ion battery life prognostic health management system using particle filtering framework. Proc Inst Mech Eng, Part O: J Risk Reliab 225:81–90
Haldar A, Mahadevan S (2000) Probability, reliability, and statistical methods in engineering design. Wiley, New York
Hawkins DM (2004) The problem of overfitting. J Chem Inf Comput Sci 44(1):1–12
Kohavi R (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Paper presented at the international joint conference on artificial intelligence, Montreal, Quebec, Canada, 20–25 August 1995
Montgomery DC, Peck EA, Vining GG (1982) Introduction to linear regression analysis. Wiley, New York
Paris PC, Erdogan F (1963) A critical analysis of crack propagation laws. ASME J Basic Eng 85:528–534
Saed S (2010) Model evaluation—regression. http://www.saedsayad.com/model_evaluation_r.htm. Accessed 25 May 2016
Sankararaman S, Ling Y, Shantz C et al (2009) Uncertainty quantification in fatigue damage prognosis. In: Paper presented at the annual conference of the prognostics and health management society, San Diego, California, USA, 27 September–1 October 2009
Saxena A, Celaya J, Saha B et al (2009) On applying the prognostic performance metrics. In: Paper presented at the annual conference of the prognostics and health management society, San Diego, California, USA, 27 September–1 October 2009
Wu F, Lee J (2011) Information reconstruction method for improved clustering and diagnosis of generic gearbox signals. Int J Progn Health Manage 2:1–9
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2017 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Kim, NH., An, D., Choi, JH. (2017). Tutorials for Prognostics. In: Prognostics and Health Management of Engineering Systems. Springer, Cham. https://doi.org/10.1007/978-3-319-44742-1_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-44742-1_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-44740-7
Online ISBN: 978-3-319-44742-1
eBook Packages: EngineeringEngineering (R0)