EFFICIENT FATIGUE LIFE ASSESSMENT OF COMPOSITE MATERIALS BY USING A HYBRID SURROGATE MODELING

Prima P Airlangga, Azzah Dyah Pramata, Mas Irfan P Hidayat

Abstract


In this study, hybrid surrogate and nonlinear autoregressive with exogenous inputs (NARX) model is developed and presented as data-driven based predictive model for efficient fatigue life assessment of composite materials. Surrogate modeling based upon wavelet neural networks (WNN) is employed to efficiently unveil mathematical pattern in S-N data, but costly to get from experiments. Moreover, the NARX architecture is chosen in order to enable multi-step ahead prediction in fatigue life assessment of multivariable amplitude loadings. By observing fatigue data as dynamic data of stress ratio series, it is shown that the hybrid model produces reasonably accurate fatigue life prediction by using fatigue data from two stress ratio values only. The use of two stress ratio values also allows usage of more limited fatigue data in the lifetime prediction. The WNN-NARX surrogate model is tested with well-known fatigue data in literature. Several composite materials examined in this study show the efficacy and robustness of the proposed model.

Keywords


surrogate model; fatigue life prediction; limited fatigue data; multivariable amplitude loading; composite materials

Full Text:

PDF

References


A. Bezazi, S. G. Pierce, K. Worden, and E. H. Harkati, “Fatigue life prediction of sandwich composite materials under flexural tests using a Bayesian trained artificial neural network,” Int. J. Fatigue, 29(4), 738–747 (2007).

A. P. Vassilopoulos and T. P. Philippidis, "Complex stress state effect on fatigue life of GRP laminates. Part I, experimental. Int. J. Fatigue, 24(8), 813-823, (2002).

A. P. Vassilopoulos, E. F. Georgopoulos, and T. Keller, “Comparison of genetic programming with conventional methods for fatigue life modeling of FRP composite materials,” Int. J. Fatigue, 30(9), 1634–1645 (2008).

A. Yaich, A. El Hami, L. Walha, and M. Haddar, “Local multiaxial fatigue damage estimation for structures under random vibrations,” Finite Elem. Anal. Des., 132, 1–7 (2017).

C. R. Kennedy, C. M. T. Brádaigh, and S. B. Leen, “A multiaxial fatigue damage model for fibre reinforced polymer composites,” Compos. Struct., 106, 201–210 (2013).

C.B. Kalayci, S. Karagoz and Ö. Karakas, “Soft computing methods for fatigue life estimation: A review of the current state and future trends”, Fatigue & Fracture of Engineering Materials & Structures, 143(12), 2763-2785 (2020).

D. Flore and K. Wegener, “Modelling the mean stress effect on fatigue life of fibre reinforced plastics,” Int. J. Fatigue, 82, 689–699 (2016).

G.P. Sendeckyj, "Constant life diagrams-a historical review," Int. J. Fatigue, 23(4), 347-353 (2001).

H. Chen and D. G. Shang, “An on-line algorithm of fatigue damage evaluation under multiaxial random loading,” Int. J. Fatigue, 33(2), 250–254 (2011).

Harris, B. ed., 2003. Fatigue in Composites. Cambridge: Woodhead Publishing Ltd.

Hidayat, M.I.P. (2015). System Identification Technique and Neural Networks for Material Lifetime Assessment Application. In Q. Zhu & A.T. Azar (Eds.), Complex System Modelling and Control Through Intelligent Soft Computations, Studies in Fuzziness and Soft Computing 319 (pp. 773-806). Switzerland: Springer International Publishing.

Hidayat, M.I.P., and Yusoff, P.S.M.M. (2009). Optimizing Neural Network Prediction of Composite Fatigue Life Under Variable Amplitude Loading Using Bayesian Regularization. In S. M. Sapuan & I.M. Mujtaba (Eds.), Composite Materials Technology: Neural Network Applications (pp. 221-249). New York, USA: CRC Press.

I. Daubechies, Ten Lectures on Wavelets, Vol. 61, Society for Industrial and Applied Mathematics, Philadelphia, 1992, pp. 198–202.

J. C. F. Pujol and J. M. A. Pinto, “A neural network approach to fatigue life prediction,” Int. J. Fatigue, 33(3), 313–322 (2011).

J. Chen and Y. Liu, “Fatigue modeling using neural networks: a comprehensive review”, Authorea (2021). DOI: 10.22541/au.163254701.14733101/v1

J. D. Martin and T. W. Simpson, “Use of kriging models to approximate deterministic computer models,” AIAA J., 43(4), 853–863 (2005).

J. F. Durodola, S. Ramachandra, S. Gerguri, and N. A. Fellows, “Artificial neural network for random fatigue loading analysis including the effect of mean stress,” Int. J. Fatigue, 111, 321–332 (2018).

J. F. Mandell and D. D. Samborsky, 2010. DOE/MSU composite material fatigue data-base: test, methods, material and analysis. SAND97-3002. Albuquerque, NM: Sandia National Laboratories.

J. Klemenc and M. Fajdiga, "Estimating S–N curves and their scatter using a differential ant-stigmergy algorithm. Int. J. Fatigue, 43(1), 90–97 (2012).

J. P. C. Kleijnen, “Kriging metamodeling in simulation: A review,” Eur. J. Oper. Res., 192(3), 707–716 (2009).

J. T. Hwang and J. R. R. A. Martins, “A fast-prediction surrogate model for large datasets,” Aerosp. Sci. Technol., 75(2), 74–87 (2018).

J. Weng, W. Wen, and H. Zhang, “Multiaxial fatigue life prediction of composite materials,” Chinese J. Aeronaut., 30(3), 1012–1020 (2017).

J. Y. Kang, B. I. Choi, H. J. Lee, J. S. Kim, and K. J. Kim, “Neural network application in fatigue damage analysis under multiaxial random loadings,” Int. J. Fatigue, 28(2), 132–140 (2006).

J. Yang, G. Kang, Y. Liu, K. Chen, and Q. Kan, "Life prediction for rate-dependent low-cycle fatigue of PA6 polymer considering ratchetting: Semi-empirical model and neural network based approach," Int. J. Fatigue, 136 105619 (2020).

J. Zhu, W. Zhang, and X. Li, “Fatigue damage assessment of orthotropic steel deck using dynamic Bayesian networks,” Int. J. Fatigue, 118, 44–53 (2019).

J.F. Durodola, N. Li, S. Ramachandra, A.N. Thite, "A pattern recognition artificial neural network method for random fatigue loading life prediction," Int. J. Fatigue, 99, 55–67 (2017).

K. Narendra and K. Parthasarathy, "Identification and control of dynamic systems using neural networks," IEEE Trans. Neural Networks, 1(1), 4–27, (1990).

L. K. Song, G. C. Bai, and C. W. Fei, “Probabilistic LCF life assessment for turbine discs with DC strategy-based wavelet neural network regression,” Int. J. Fatigue, 119, 204–219 (2019).

M. Al-Assadi, H. A. E. Kadi, and I. M. Deiab, “Using artificial neural networks to predict the fatigue life of different composite materials including the stress ratio effect,” Appl. Compos. Mater., 18(4), 297–309 (2011).

M. J. Pais, F. A. C. Viana, and N. H. Kim, “Enabling high-order integration of fatigue crack growth with surrogate modeling,” Int. J. Fatigue, 43, 150–159 (2012).

M. Scheuerer, R. Schaback, and M. Schlather, “Interpolation of spatial data-A stochastic or a deterministic problem?” Eur. J. Appl. Math., 24(4), 601–629 (2013).

M.I.P. Hidayat, B.A. Wahjoedi and S. Parman, "B-spline collocation method for boundary value problems in complex domains", Int. J. Computing Science and Mathematics, 7(2), 110-125 (2016).

M.I.P. Hidayat, B.A. Wahjoedi, S. Parman and T.V.V.L.N. Rao, “Meshless Local B-Spline Collocation Method for Two-Dimensional Heat Conduction Problems With Nonhomogenous and TimeDependent Heat Sources”, Journal of Heat Transfer, 139, 071302-1 - 071302-11 (2017).

M.I.P. Hidayat, D.M. Felicia, F.I. Rafandi, A. Machmudah, "Effects of Sample Shapes and Thickness on Distribution of Temperature inside the Mineral Ilmenite Due to Microwave Heating", Minerals, 10(4):382, 1-19 (2020).

N. Stojković, R. Folić, and H. Pasternak, “Mathematical model for the prediction of strength degradation of composites subjected to constant amplitude fatigue,” Int. J. Fatigue, 103, 478–487 (2017).

Neural Network Toolbox™ User’s Guide © COPYRIGHT 1992–2017, The MathWorks, Inc., USA.

P. Prebeg, V. Zanic, and B. Vazic, “Application of a surrogate modeling to the ship structural design,” Ocean Eng., 84, 259–272 (2014).

Q. Zhang and A. Benveniste, “Wavelet Networks,” IEEE Trans. Neural Networks, 3(6), 889–898 (1992).

R. K. Tripathy and I. Bilionis, “Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantification,” J. Comput. Phys., 375, 565–588 (2018).

R.B. Kalombo, M.S. Pestana, R.C.S. Freire Júnior, J.L.A. Ferreira, C.R.M. Silva, L.A.C.M. Veloso, E.C.B. Câmara, J.A. Araújo, "Fatigue life estimation of an all aluminium alloy 1055 MCM conductor for different mean stresses using an artificial neural network," Int. J. Fatigue, 140 105814 (2020).

R.C.S. Freire Junior, A.D.D. Neto and E.M.F. de Aquino, "Building of constant life diagrams of fatigue using artificial neural networks," Int. J. Fatigue, 27(7), 746-751 (2005).

Reifsnider, K.L. ed., 1991. Fatigue of Composite Materials. Amsterdam: Elsevier.

S. Chen, S. A. Billings and P. M. Grant, "Non-linear system identification using neural networks." Int. J. Control, 51(6), 1191-1214 (1990).

S. Shiri, M. Yazdani, and M. Pourgol-Mohammad, “A fatigue damage accumulation model based on stiffness degradation of composite materials,” Mater. Des., 88, 1290–1295 (2015).

S.G. Mallat, "A theory for multiresolution signal decomposition: the wavelet representation," IEEE Trans. Pattern Anal. Mach. Intell," 11(7), 674–693 (1989).

Schijve, J. ed., 2009. Fatigue of Structures and Materials. Netherlands: Springer.

T. Bučar, M. Nagode, and M. Fajdiga, “A neural network approach to describing the scatter of S-N curves,” Int. J. Fatigue, 28(4), 311–323 (2006).

V. Shanmugam, O. Das, K. Babu, U. Marimuthu, A. Veerasimman, D. J. Johnson, R. E. Neisiany, M. S. Hedenqvist, S. Ramakrishna and F. Berto, "Fatigue behaviour of FDM-3D printed polymers, polymeric composites and architected cellular materials," Int. J. Fatigue, 143 106007 (2021).

W. Lian and W. Yao, “Fatigue life prediction of composite laminates by FEA simulation method,” Int. J. Fatigue, 32(1), 123–133 (2010).

Z.-H. Han, K.-S. Zhang, W.-P. Song and Z.-D. Qiao, “Optimization of active flow control over an airfoil using a surrogate-management framework,” J. Aircr., 47(2), 603–612 (2010).




DOI: http://dx.doi.org/10.12962/j2746279X.v2i2.11550

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.

 
View My Stats