A neural network approach to fatigue life prediction
Source abstract
Abstract
Abstract In this work, a novel approach to fatigue life prediction under step-stress conditions is introduced, where the cumulative distribution function for the failure of components was implemented by means of a neural network. The model was fit to experimental data on the fatigue life of steel under step-stress conditions. For comparison, a standard approach based on the lognormal distribution function was also implemented and fit to the same experimental data. Both models were optimized by evolutionary computation, using a maximum likelihood estimator. The Kolmogorov–Smirnov test was applied to compare the results of the new approach to those obtained with the lognormal distribution function.
Source: openaire · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Fatigue and fracture mechanics · Non-Destructive Testing Techniques · Metallurgy and Material Forming
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (48)
Show source-provided references
1. Collins · 1993
2. Accelerated life testing – step-stress models and data analysis10.1109/TR.1980.5220742 ↗
3. Nelson · 1990
4. Analysis of step-stress accelerated-life-test data: a new approach10.1109/24.488919 ↗
5. Sobczyk · 1992
6. 2004
7. Haykin · 1999
8. Multilayer feedforward networks are universal approximators10.1016/0893-6080(89)90020-8 ↗
9. 1997
10. Mathur S, Gope P, Sharma J. Prediction of fatigue lives of composites material by artificial neural network. In Proceedings of the SEM 2007 annual conference and exposition, Springfield, Massachusetts, USA; June 2007 [Paper 260].
11. Troudt T, Merrill W. A real time neural net estimator of fatigue life. In Proceedings international joint conference on neural networks (SPIE), vol. 2, pages 59–64, San Diego, CA, USA, June 1990.10.1109/IJCNN.1990.137695 ↗
12. Determination of S–N curves with the application of neural networks
13. Artificial neural networks in spectrum fatigue life prediction of composite materials10.1016/j.ijfatigue.2006.03.004 ↗
14. Neural network application in fatigue damage analysis under multiaxial random loadings10.1016/j.ijfatigue.2005.04.012 ↗
15. Prediction of residual fatigue life under interspersed mixed-mode (I and II) overloads by artificial neural network10.1111/j.1460-2695.2009.01407.x ↗
16. A study on fatigue damage modeling using neural networks10.1007/BF03023898 ↗
17. Prediction of fatigue crack growth rate in welded tubular joints using neural network10.1016/j.ijfatigue.2006.03.002 ↗
18. A neural-network approach to describe the scatter of cyclic stressstrain curves
19. A neural network approach to describing the scatter of sn curves10.1016/j.ijfatigue.2005.08.002 ↗
20. Neural networks in materials science
21. Software products for modelling and simulation in materials science10.1016/S0927-0256(03)00106-X ↗
22. The use of artificial neural networks in materials science based research10.1016/j.matdes.2007.02.009 ↗
23. SAE International, SAE handbook. Number J404 in chemical compositions of SAE alloy steels, 1994, p. 1.12–3.
24. Cazaud · 1957
25. American Society for Testing and Materials – ASTM. Standard terminology relating to fatigue and fracture testing, vol. 03.01. Annual Book of ASTM Standards; 2001 [ASTM E 1823–96].
26. Yang · 2007
27. Residuals and their analyses for accelerated life tests with step and varying stress10.1109/TR.2008.920789 ↗
28. Optimum simple step-stress plans for accelerated life testing10.1109/TR.1983.5221475 ↗
29. Step-stress life-testing with random stress-change times for exponential data10.1109/24.784272 ↗
30. Some aspects of accelerated life testing by progressive stress10.1109/TR.1987.5222320 ↗
31. Optimum simple step-stress accelerated life tests with censoring10.1109/24.46476 ↗
32. Performance of parameter-estimates in step-stress accelerated life-tests with various sample-sizes10.1109/TR.2002.802888 ↗
33. Mettas A, Vassiliou P. Modeling and analysis of time-dependent stress accelerated life data. In: Proceedings of the annual reliability and maintainability symposium, Seattle WA, USA; January 2002. p. 343–8.10.1109/RAMS.2002.981665 ↗
34. Inferences on a simple step stress model with type-II censored exponential data10.1109/24.722278 ↗
35. A least-squares approach to analyzing life-stress relationship in step-stress accelerated life tests10.1109/TR.2002.1011523 ↗
36. A model for step-stress accelerated life testing10.1002/nav.10088 ↗
37. Estimation in step-stress accelerated life tests for the exponentiated exponential distribution with type-I censoring10.1016/j.csda.2008.11.006 ↗
38. Cordeiro G. Introdução à teoria de verossimilhança. In: Course during the 10o Simpósio Nacional de Probabilidade e Estatı´stica, Associaçao Brasileira de Estatı´stica, Rio de Janeiro; 1992.
39. Jong · 2006
40. Baeck · 1997
41. Price · 2005
42. On the inverse power laws for accelerated random fatigue testing10.1016/j.ijfatigue.2007.08.023 ↗
43. Kreyszig · 1970
44. Meeker · 1998
45. Pinto J. Modelagem de testes acelerados com esforço aplicado em nı´veis em um estudo de fadiga mecânica. PhD thesis, Instituto de Pesquisas Energéticas e Nucleares, São Paulo, Brazil; 2004.
46. Neural network constructive algorithms: trading generalization for learning efficiency?10.1007/BF01189880 ↗
47. Pruning algorithms: a survey10.1109/72.248452 ↗
48. Alvarenga Jr A. Acúmulo de danos por fadiga no aço SAE 8620. MSc dissertation, Departamento de Engenharia Mecânica da Universidade Católica de Minas Gerais, Belo Horizonte, Brazil; 2001.