Informatics and Applications
2024, Volume 18, Issue 4, pp 68-76
ON THE PROBLEM OF PREDICTING DEGRADATION IN TECHNICAL SYSTEMS
- S. L. Frenkel
- V. N. Zakharov
Abstract
The problem of predicting the degradation rate of technical system characteristics (life time, LT) is
usually solved within the framework of the accelerating testing (AT) paradigm under stress effects. However,
statistical methods for evaluating the results may be ineffective for AT when the system performance depends on
a very large number of factors. Accelerating testing also has its own specifics at the early stages of experimental
design work when, having only a small number of device copies, it is necessary to estimate their potential service
life to assess the feasibility of continuing the development. The article analyzes the extent to which modern
mathematical and statistical models that formthe ATmethodology, namely, survival analysis, extreme value theory,
allow obtaining forecasts of the service life of the designed devices under real operating conditions at the early
stages of development/design. The authors indicate the problems of solving the LT forecasting problem using
known machine learning tools, consider and propose a heuristic method for solving the LT forecasting problem
in real conditions. As an example, the authors consider the prediction of performance degradation for new solar
cell designs whose performance tends to degrade. This heuristic refers to the extraction of the Hondrick–Prescott
trend from a nonstationary time series that represents the degradation of a quality characteristic. The applicability
of the proposed heuristic to predict degradation in other technical applications, particularly, in computer networks,
is discussed and justified.
[+] References (20)
- Escobar, L.A., and W.Q. Meeker. 2006. A review of
accelerated test models. Stat. Sci. 21(4):552–577. doi:
10.1214/088342306000000321.
- Klein, J. P., and M. L. Moeschberger. 2003. Survival analysis:
Techniques for censored and truncated data. 2nd ed.New
York, NY: Springer-Verlag. 538 p. doi: 10.1007/b97377.
- Kalbfleisch, J.D., and R. L. Prentice. 2002. The statistical
analysis of failure time data. 2nd ed. Hoboken, NJ: Wiley. 462 p.
- Andrzejczak,K., and L. Bukowski. 2021. A method for estimating
the probability distribution of the lifetime for new
technical equipment based on expert judgement. Eksploat.
Niezawodn. 23(4):757–769. doi: 10.17531/ein.2021.4.18.
- Panidi, J., D. Georgiadou, T. Schoetz, and T. Prodromakis.
2022. Advances in organic and perovskite photovoltaics
enabling a greener internet of things. Adv.
Funct. Mater. 32(23):2200694. 26 p. doi: 10.1002/adfm.202200694.
- Burlingame,Q., Yueh-Lin Loo, and E.A. Katz. 2023. Accelerated
ageing of organic and perovskite photovoltaics.
Nature Energy 8(12):1300–1302. doi: 10.1038/s41560-023-01330-8.
- Ding, D., M. Zhang, X. Pan, M. Yang, and X. He. 2019.
Modeling extreme events in time series prediction. 25th
ACM SIGKDD Conference (International) on Knowledge
Discovery and Data Mining Proceedings. New York, NY:
ACM. 1114–1122. doi: 10.1145/3292500.3330896.
- Chuprov, L., A. Reznik, and O. Shetty. 2022.
How degrading network conditions influence machine
learning end systems performance? Conference
on Computer Communications Workshops Proceedings.
Piscataway, NJ: IEEE. Art. 9798388. 6 p. doi: 10.1109/INFOCOMWKSHPS54753.2022.9798388.
- Wen, Yi, and B. Zeng. 1999. A simple nonlinear filter for
economic time series analysis. Econ. Lett. 64(2):151–160.
doi: 10.1016/S0165-1765(99)00089-0.
- Einmahl, J., J.H. Einmahl, and L. Haan. 2019. Limits
to human life span through extreme value theory.
American Statistical Association 114(527):1075–1080. doi:
10.1080/01621459.2018.1537912.
- Xiao-Sheng, S., W. Wang, C.-H. Hu, and D.-H. Zhou.
2011. Remaining useful life estimation — a review on
the statistical data driven approaches. Eur. J. Oper. Res.
213(1):1–14. doi: 10.1016/j.ejor.2010.11.018.
- Montfort, M., and B. Putten. 2002. A comment on modelling
extremes: Links between multi-component extreme
value and general extreme value distributions. J. Hydrol.
41(2):197–202.
- Kudryavtsev, A. A., and O. V. Shestakov. 2023. Metod
otsenivaniya parametrov gamma-eksponentsial’nogo raspredeleniya
po vyborke so slabo zavisimymi komponentami
[A method for estimating parameters of the gammaexponential
distribution from a sample with weakly
dependent components]. Informatika i ee Primeneniya
— Inform. Appl. 17(3):58–63. doi: 10.14357/19922264230308. EDN: PEXTVK.
- Gao, J., F. Wu, Y. Yasen, W. Song, and L. Ren. 2022.
Generalized Cauchy process based on heavy-tailed distribution
and grey relational analysis for reliability predicting
of distribution systems. MBE 19(7):6620–6637. doi:
10.3934/mbe.202231.
- Willinger, W., M. Taqqu, R. Sherman, and D. Wilson.
1997. Self-similarity through high-variability: Statistical
analysis of ethernet LAN traffic at the source level. IEEE
ACMT. Network. 5(1):71–86. doi: 10.1109/90.554723.
- Sohrabpoor, H., G. Puccettib, and N. Gorji. 2016. Modeling
the decay and recovery of perovskite solar cells. RSC
Adv. 6:49328–49334. doi: 10.1039/C6RA06635F.
- Kouroudis, I., K. Tanko, M. Karimipour, A. Ben
Ali, D. Kumar, V. Sudhakar, R. Gupta, I. Visoly-
Fisher, M. Lira-Cantu, and A. Gagliardi. 2024. Artificial
intelligence-based, wavelet-aided prediction of longterm
outdoor. ACS Energy Letters 9(4):1581–1586. doi:
10.1021/acsenergylett.4c00328.
- Vyshinsky, L. L., and Yu.A. Flerov. 2024. Modeli sinteza
komponovochnoy skhemy v zadache formirovaniya
obraza samoleta [Synthesis models of layout scheme in
the task of forming an aircraft image]. Informatika i ee
Primeneniya — Inform. Appl. 18(1):61–70. doi: 10.14357/
19922264240109. EDN: DSPGKV.
- Grusho, A.A., M. I. Zabezhailo, D. V. Smirnov, and
E. E. Timonina. 2020. O veroyatnostnykh otsenkakh dostovernosti
empiricheskikh vyvodov [On probabilistic estimates
of the validity of empirical conclusions]. Informatika
i ee Primeneniya — Inform. Appl. 14(4):3–8. doi:
10.14357/19922264200401. EDN: DOQKNU.
- Kovalyov, S. P. 2021. Metody teorii kategoriy v tsifrovom
proektirovanii geterogennykh kiber-fizicheskikh sistem
[Methods of the category theory in digital design of
heterogeneous cyber-physical systems]. Informatika i ee
Primeneniya — Inform. Appl. 15(1):23–29. doi: 10.14357/19922264210104. EDN: YZVCME.
[+] About this article
Title
ON THE PROBLEM OF PREDICTING DEGRADATION IN TECHNICAL SYSTEMS
Journal
Informatics and Applications
2024, Volume 18, Issue 4, pp 68-76
Cover Date
2024-12-26
DOI
10.14357/19922264240409
Print ISSN
1992-2264
Publisher
Institute of Informatics Problems, Russian Academy of Sciences
Additional Links
Key words
accelerating testing; machine learning
Authors
S. L. Frenkel and V. N. Zakharov
Author Affiliations
Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences, 44-2 Vavilov Str., Moscow 119333, Russian Federation
|