α-S-N curve: A novel S-N curve modeling method under small-sample test data using uncertainty theory
Source abstract
Abstract
Abstract Considering the unconvincing results produced by probability theory when dealing with small sample data, this paper introduces uncertainty theory (a branch of axiomatic mathematics parallel to probability theory) to model and estimate the uncertainty of fatigue life with the small sample of fatigue test data. A new method called α -S-N curves is firstly proposed to describe the relationship between fatigue life and stress levels. Subsequently, general procedures are established for the determination of α -S-N curves based on the four basic assumptions to improve the information utilized in the estimation process and overcome the large-scatter of the small sample fatigue failure data. Finally, the developed procedures are verified by the data of aluminum alloy data and laminate panel data. The precision and stability of the developed procedures are validated by the index relative slope in comparison with the method stated in ISO 12107.
Source: openaire · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Probabilistic and Robust Engineering Design · Fatigue and fracture mechanics · Structural Health Monitoring Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (30)
Show source-provided references
1. Collins · 1981
2. Chen J, Liu S, Zhang W, Liu Y. Uncertainty quantification of fatigue s-n curves with sparse data using hierarchical bayesian augmentation. Int J Fatigue 134(105511). doi: 10.1016/j.ijfatigue.2020.105511.10.1016/j.ijfatigue.2020.105511 ↗
3. International Standard, Metallic materials - Fatigue testing - Statistical planning and analysis of data, ISO12107:2003(E); 2003.
4. On stochastic evaluation of s-n models based on lifetime distribution
5. Backwards statistical inference method for p–s–n curve fitting with small-sample experiment data10.1016/j.ijfatigue.2014.01.006 ↗
6. p–s–n curve fitting method based on sample aggregation principle10.1007/s11668-019-00586-1 ↗
7. New method for determining p-s-n curves in terms of equivalent fatigue lives10.1111/ffe.13075 ↗
8. A maximum likelihood method for estimating p-s-n curves10.1016/S0142-1123(97)00037-6 ↗
9. A new method for obtaining p-s-n curves under the condition of small sample
10. A bayesian analysis of fatigue data10.1016/j.strusafe.2009.08.001 ↗
11. Hierarchical bayesian fatigue data analysis10.1016/j.ijfatigue.2017.03.043 ↗
12. Survival analysis of fatigue data: Application of generalized linear models and hierarchical bayesian model10.1016/j.ijfatigue.2018.07.027 ↗
13. Aleatory or epistemic? Does it matter?10.1016/j.strusafe.2008.06.020 ↗
14. Pawitan · 2001
15. Fitting fatigue test data with a novel s-n curve using frequentist and bayesian inference10.1016/j.ijfatigue.2017.08.024 ↗
16. Liu · 2007
17. Liu · 2010
18. Measuring reliability under epistemic uncertainty: Review on non-probabilistic reliability metrics10.1016/j.cja.2016.04.004 ↗
19. Uncertain shapley value of coalitional game with application to supply chain alliance10.1016/j.asoc.2016.06.018 ↗
20. Asian option pricing problems of uncertain mean-reverting stock model10.1007/s00500-017-2524-8 ↗
21. Belief reliability for uncertain random systems10.1109/TFUZZ.2018.2838560 ↗
22. B-spline method of uncertain statistics with applications to estimate travel distance
23. Method of moments for estimating uncertainty distributions10.1186/2195-5468-2-5 ↗
24. Uncertain regression analysis: an approach for imprecise observations10.1007/s00500-017-2521-y ↗
25. Uncertain time series analysis with imprecise observations10.1007/s10700-018-9298-z ↗
26. Modeling accelerated degradation data based on the uncertain process10.1109/TFUZZ.2018.2883016 ↗
27. The exponential law of endurance tests
28. Maximum entropy principle for uncertain variables
29. Graduation formula: a new method to construct belief reliability distribution under epistemic uncertainty10.23919/JSEE.2020.000038 ↗
30. Estimating fatigue curves with the random fatigue-limit model10.1080/00401706.1999.10485925 ↗