This study consists in the evaluation of the use of an artificial neural network of modular architecture in building probabilistic constant life diagrams. Therefore, an algorithm developed in previous studies which was applied to achieve deterministic values has proved itself viable when at least three S-N curves were used. For this case, the probability S-N curves were used for training and validation of the modular network based on the generalized power law and a probability of 5% for failure has been considered. In addition, three composite materials were evaluated with a considerable number of tests to better assess the model.
PhilippidisTPVassilopoulosAP. Fatigue of composite laminates under off-axis loading. Int J Fatigue1999; 21: 253–262.
2.
SubramanianSReifsniderKLStinchcombWW. A cumulative damage model to predict the fatigue life of composite laminates including the effect of a fibrematrix interphase. Int J Fatigue1995; 17: 343–351.
3.
WahlNSamborskyDMandellJ. Effects of modeling assumptions on the accuracy of spectrum fatigue lifetime predictions for a fiberglass laminate. Wind Energy2002; 1: 19–26.
4.
HarrisB. A parametric constant life model for prediction of the fatigue lives of fibre reinforced plastics. Fatigue In Composites, Woodhead Publishing and CRC Press, 2003, pp. 546–568.
5.
AdamTFernandoGDicksonRF. Fatigue life prediction for hybrid composites. Int J Fatigue1989; 11: 233–237.
6.
VassilopoulosAPManshadiBDKellerT. Piecewise non-linear constant life diagram formulation for FRP composite materials. Int J Fatigue2010; 32: 1731–1738.
7.
FreireRCSJrDoria NetoADAquinoEMF. Use of modular networks in the building of constant life diagrams. Int J Fatigue2007; 29: 389–396.
8.
El KadiHAl-AssafY. Prediction of the fatigue life prediction of unidirectional glass fiber/epoxy composite laminate using different neural network paradigms. Compos Struct2002; 55: 239–246.
9.
El KadiHAl-AssafY. Energy based fatigue life prediction of fiberglass/epoxy composites using modular neural network. Compos Struct2002; 57: 85–89.
10.
MohantyJRVermaBBRayPK. Prediction of fatigue crack growth and residual life using an exponential model: Part I (constant amplitude loading). Int J Fatigue2009; 31: 418–424.
11.
KwofieS. An exponential stress function for prediction fatigue strength and life due to mean stresses. Int J Fatigue2001; 23: 829–836.
12.
ChoiSRNemethNNGyekenyesiJP. Slow crack growth of brittle materials with exponential crack velocity under cyclic fatigue loading. Int J Fatigue2006; 28: 164–172.
13.
BergnerFZouharG. A new approach to the correlation between the coefficient and the exponent in the power law equation of fatigue crack growth. Int J Fatigue2000; 22: 229–239.
14.
AllegriGZhangX. On the inverse power laws for accelerated random fatigue. Int J Fatigue2008; 30: 967–977.
15.
CarpinteriAPaggiM. A unified interpretation of the power laws in fatigue and the analytical correlations between cyclic properties of engineering materials. Int J Fatigue2009; 31: 1524–1531.
16.
Dunand-ChâtelletCMoumniZ. Experimental analysis of the fatigue of shape memory alloys through power-law statistics. Int J Fatigue2012; 36: 163–170.
17.
FreireRCSJrAquinoEMFNeto DóriaAD. Building of constant life diagrams of fatigue using artificial neural networks. Int J Fatigue2005; 27: 746–751.
18.
SubramanianSReifsniderKLStinchcombWW. A cumulative damage model to predict the fatigue life of composite laminates including the effect of a fibre–matrix interphase. Int J Fatigue1995; 17: 343–351.
19.
ASTM E739-10. Standard Practice for Statistical Analysis of Linear or Linearized Stress-Life (S-N) and Strain-Life (ɛ-N) Fatigue Data, ASTM International, West Conshohocken, PA, 2010.
20.
CastilhoEAenlleMLRamosA. Specimen length effect on parameter estimation in modelling fatigue strength by Weibull distribution. Int J Fatigue2006; 28: 1047–1058.
21.
SakaiTSakaiTOkadaK. Statistical fatigue properties of SCM435 steel in ultra-long-life regime based on JSMS database on fatigue strength of metallic materials. Int J Fatigue2006; 28: 1486–1492.
22.
SakaiTLianBTakedaM. Statistical duplex S–N characteristics of high carbon chromium bearing steel in rotating bending in very high cycle regime. Int J Fatigue2010; 32: 497–504.
23.
VassilopoulosAPGeorgopoulosEFKellerT. Comparison of generic programming with conventional methods for fatigue life modeling of FRP composite materials. Int J Fatigue2008; 30: 1634–1645.
24.
FreireRCSJrBelísioA. Probabilistic S–N curves using exponential and power laws equations. Compos Part B Eng2014; 56: 582–590.
25.
Freire Jr RCS. Fadiga de Alto Ciclo em Compósitos de PRFV. Modelagem por RNAs e Prevenção de Falha. 2005. 171 f. Tese (Doutorado) - Universidade Federal do Rio Grande do Norte, Natal, 2005.
26.
FreireRCSJrAquinoEMF. Fatigue damage mechanism and failure prevention in fiberglass reinforced plastic. Mater Res2005; 8: 45–49.
27.
CahnRWHaasenPKramerEJ. Mater Sci Technol1993; 6: 625–625.
Mandell JF and Samborsky DD. DOE/MSU composite material fatigue database. Sandia National Laboratories, v. 19.0; 2010. http://www.coe.montana.edu/composites/ (accessed 15 December 2014).
30.
HarrisBGathercoleNLeeJA. Life-prediction for constant stress fatigue in carbon-fibre composites. Philos Trans Roy Soc Lond A1997, pp. 1259–1294.
31.
GathercoleNReiterHAdamT. Life prediction for fatigue of T800/5245 carbon-fibre composites I: Constant-amplitude loading. Fatigue1994; 6: 523–532.
32.
SenaBBVFreireRCSJr. Criteria for the use of modular networks: fatigue in composite materials. J Compos Mater2012; 46: 2973–2985.
33.
VassilopoulosAPKellerT. Fatigue of fiber-reinforced composites, London: Springer, 2011.
