Abstract
Neural network (NN) is a representative data-driven method, which is one of prognostics approaches that is to predict future damage/degradation and the remaining useful life of in-service systems based on the damage data measured at previous usage conditions. Even though NN has a wide range of applications, there are a relatively small number of literature on prognostics compared to the usage in other fields such as diagnostics and pattern recognition. Especially, it is difficult to find studies on statistical aspects of NN for the purpose of prognostics. Therefore, this paper presents the aspects of statistical characteristics of NN that are presumable in practical usages, which arise from measurement data, weight parameters related to the neural network model, and loading conditions. The Bayesian framework and Johnson distribution are employed to handle uncertainties, and crack growth problem is addressed as an example.
Similar content being viewed by others
References
M. A. Schwabacher, A survey of data-driven prognostics, AIAA Infotech@Aerospace Conference, Reston, VA (2005).
J. Luo, K. R. Pattipati, L. Qiao and S. Chigusa, Model-based prognostic techniques applied to a suspension system, IEEE Transactions on System, Man and Cybernetics, 38 (5) (2008) 1156–1168.
J. Yan and J. Lee, A hybrid method for on-line performance assessment and life prediction in drilling operations, IEEE International Conference on Automation and Logistics, Jinan, Shandong, China (2007).
K. Chakraborty, K. Mehrotra, C. K. Mohan and S. Ranka, Forecasting the behavior of multivariate time series using neural networks, Neural Networks, 5 (1992) 961–970.
X. Yao, Evolving artificial neural networks, Proceedings of the IEEE, 87 (9) (1999) 1423–1447.
M. Seeger, Gaussian processes for machine learning, International Journal of Neural Systems, 14 (2) (2004) 69–106.
S. Mohanty, R. Teale, A. Chattopadhyay, P. Peralta and C. Willhauck, Mixed Gaussian process and state-space approach for fatigue crack growth prediction, International Workshop on Structural Heath Monitoring, 2 (2007) 1108–1115.
M. E. Tipping, Sparse Bayesian learning and the relevance vector machine, Journal of Machine Learning Research, 1 (2001) 211–244.
V. T. Tran and B. S. Yang, Data-driven approach to machine condition prognosis using least square regression tree, Journal of Mechanical Science and Technology, 23 (2009) 1468–1475.
G. Chryssoloiuris, M. Lee and A. Ramsey, Confidence interval prediction for neural network models, IEEE Transactions on Neural Networks, 7 (1) (1996) 229–232.
R. D. Veaux, J. Schumi, J. Schweinsberg and L. H. Ungar, Prediction intervals for neural networks via nonlinear regression, Technometrics, 40 (4) (1998) 273–282.
L. Yang, T. Kavli, M. Carlin, S. Clausen and P. F. M. Groot, An evaluation of confidence bound estimation methods for neural networks, European Symposium on Intelligent Techniques, Aachen, Germany (2000).
J. A. Leonard, M. A. Kramer and L. H. Ungar, A neural network architecture that computes its own reliability, Computers in Chemical Engineering, 16 (9) (1992) 819–835.
J. F. G. de Freitas, Bayesian methods for neural networks, PhD Thesis, University of Cambridge, UK (2003).
R. M. Neal, Bayesian learning for neural networks, Ph.D. Thesis, University of Toronto, Ontario, Canada (1995).
J. Liu, A. Saxena, K. Goebel, B. Saha and W. Wang, An adaptive recurrent neural network for remaining useful life prediction of lithium-ion batteries, Annual Conference of the Prognostics and Health Management Society, Portland, Oregon, USA (2010).
D. Svozil, V. Kvasnicka and J. Pospíchal, Introduction to multi-layer feed-forward neural networks, Chemometrics and Intelligent Laboratory Systems, 39 (1997) 43–62.
W. Duch and N. Jankowski, Survey of neural transfer functions, Neural Computing Surveys, 2 (1999) 163–212.
A. E. Firth, O. Lahav and R. S. Somerville, Estimating photometric redshifts with artificial neural networks, Monthly Notices of the Royal Astronomical Society, 339 (2003) 1195, DOI: 10.1046/j.1365-8711.2003.06271.
D. E. Rumelhart, G. E. Hinton and R. J. Williams, Learning internal representations by error propagation, In Parallel Distributed Processing: Ex-plorations in the Microstructure of Cognition, Vol. 1: foundations, MIT Press (1986) 318–362.
P. C. Paris and F. Erdogan, A critical analysis of crack propagation laws, Transactions of the ASME, Journal of Basic Engineering, Series D, 85 (3) (1963) 528–534.
T. Bayes, An essay towards solving a problem in the doctrine of chances, Philosophical Transactions of the Royal Society of London, 53 (1763) 370–418.
X. Huang, M. Torgeir and W. Cui, An engineering model of fatigue crack growth under variable amplitude loading, International Journal of Fatigue, 30 (1) (2008) 2–10.
N. L. Johnson, Systems of frequency curves generated by methods of translation, Biometrika, 36 (1949) 149–176.
J. Lee, H. Qiu, G. Yu, J. Lin and Rexnord Technical Services, Bearing data set, IMS, University of Cincinnati, NASA Ames Prognostics Data Repository, http://ti.arc.nasa.gov/project/prognostic-data-repository, NASA Ames, Moffett Field, CA (2007).
Author information
Authors and Affiliations
Corresponding author
Additional information
Recommended by Guest Editor Joo-Ho Choi
Dawn An received the B.S. degree and M.S. degree of mechanical engineering from Korea Aerospace University in 2008 and 2010, respectively. She is now a joint Ph.D. student at Korea Aerospace University and the University of Florida. Her current research is focused on prognostics methods for practical considerations, such as a large noise in data, insufficient number of data, and indirectly measured data.
Nam-Ho Kim received the B.S. degree of mechanical engineering from Seoul National University in 1989, the M.S. and Ph.D. degrees of mechanical engineering from Korea Advanced Institute of Science and Technology (KAIST) in 1991 and the University of Iowa in 1999, respectively. He worked as a Postdoctoral Associate at the University of Iowa from 1999 to 2001. He joined the Dept. of Mechanical & Aerospace Engineering at the University of Florida, in 2002 and is now Professor. His current research is focused on design under uncertainty, design optimization of automotive NVH problem, shape DSA of transient dynamics (Implicit/explicit) and structural health monitoring.
Joo-Ho Choi received the B.S. degree of mechanical engineering from Hanyang University in 1981, the M.S. and Ph.D. degrees of mechanical engineering from Korea Advanced Institute of Science and Technology (KAIST) in 1983 and 1987, respectively. During the year 1988, he worked as a Postdoctoral Fellow at the University of Iowa. He joined the School of Aerospace and Mechanical Engineering at Korea Aerospace University, Korea, in 1997 and is now Professor. His current research is focused on the reliability analysis, design for lifetime reliability, and prognostics and health management.
Rights and permissions
About this article
Cite this article
An, D., Kim, N.H. & Choi, JH. Statistical aspects in neural network for the purpose of prognostics. J Mech Sci Technol 29, 1369–1375 (2015). https://doi.org/10.1007/s12206-015-0306-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12206-015-0306-8