Advertisement

System Identification Technique and Neural Networks for Material Lifetime Assessment Application

  • Mas Irfan P. HidayatEmail author
Chapter
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 319)

Abstract

Modeling of a material lifetime to assess the material useful lifetime during its service in design has been always challenging task. In the present study, a framework of system identification technique based upon nonlinear autoregressive exogenous inputs (NARX) was introduced and presented for material lifetime assessment using neural networks (NN). Using the framework, the task of material lifetime assessment was accomplished in a fashion of one-step ahead prediction with respect to stress level. In addition, by sliding over one-step to one-step of the stress level, the task of prediction dynamically covered all loading spectrum. As a result, material lifetime assessment can be fashioned for a wide spectrum of loading in an efficient manner based upon limited material lifetime data as the basis of the NARX regressor. The multilayer perceptron (MLP)-NARX and radial basis functions NN (RBFNN)-NARX models were developed to predict fatigue lives of composite materials under multiaxial and multivariable loadings. Several multidirectional laminates of polymeric based composites were examined in this study.

Keywords

Fatigue Life Stress Ratio Radial Basis Function Neural Network Fatigue Data Fatigue Life Prediction 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Notes

Acknowledgment

The present author would like to thank the Montana State University and A.P. Vassilopoulos and T.P. Philippidis (doi: 10.1016/S0142-1123(02)00003-8) for the fatigue database published through the internet. The author also would like to thank to editors and reviewers for their useful suggestions and comments that further improve the presentation of this research work.

References

  1. Al-Assaf, Y., & El-Kadi, H. (2001). Fatigue life prediction of unidirectional glass fiber/epoxy composite laminae using neural networks. Composites Structures, 53(6), 65–71.CrossRefGoogle Scholar
  2. Aymerich, F., & Serra, M. (1998). Prediction of fatigue strength of composite laminates by means of neural networks. In The third seminar on experimental techniques and design in composite materials (pp. 231–240), October 30–31, 1996, Cagliari, Italy. doi: 10.4028/www.scientific.net/KEM.144.231.Google Scholar
  3. Azar, A. T. (2013). Fast neural network learning algorithms for medical applications. Neural Computing and Applications, 23(3–4), 1019–1034.CrossRefGoogle Scholar
  4. Basso, M., Giarre, L., Groppi, S., & Zappa, G. (2005). NARX models of an industrial power plant gas turbine. IEEE Transactions on Control System Technology, 13(4), 599–604.CrossRefGoogle Scholar
  5. Bezazi, A., Pierce, S. G., Worden, K., & Harkati, E. H. (2007). Fatigue life prediction of sandwich composite materials under flexural tests using a Bayesian trained artificial neural network. International Journal of Fatigue, 29(4), 738–747.CrossRefGoogle Scholar
  6. Bucar, T., Nagode, M., & Fajdiga, M. (2007). An improved neural computing method for describing the scatter of S-N curves. International Journal of Fatigue, 29(12), 2125–2137.CrossRefzbMATHGoogle Scholar
  7. Bukkapatnam, S. T. S., & Sadananda, K. (2005). A genetic algorithm for unified approach-based predictive modeling of fatigue crack growth. International Journal of Fatigue, 27(10–12), 1354–1359.CrossRefGoogle Scholar
  8. Catelani, M., & Fort, A. (2000). Fault diagnosis of electronic analog circuits using a radial basis function network classifier. Measurement, 28(3), 147–158.CrossRefGoogle Scholar
  9. Chen, S., Billings, S. A., & Grant, P. M. (1990). Non-linear system identification using neural networks. International Journal of Control, 51(6), 1191–1214.CrossRefzbMATHMathSciNetGoogle Scholar
  10. El-Kadi, H., & Al-Assaf, Y. (2002). Prediction of the fatigue life of unidirectional glass fiber/epoxy composite laminae using different neural network paradigms. Composites Structures, 55(1), 239–246.CrossRefGoogle Scholar
  11. Fathi, A., & Aghakouchak, A. A. (2007). Prediction of fatigue crack growth rate in welded tubular joints using neural network. International Journal of Fatigue, 29(2), 261–275.CrossRefGoogle Scholar
  12. Foresee, F. D., & Hagan, M. T. (1997). Gauss-Newton approximation to Bayesian learning. In The 1997 IEEE international conference on neural networks (ICNN) (pp. 1930–1935), June 9–12, 1997, Houston, TX, USA. doi: 10.1109/ICNN.1997.614194.
  13. Freire Junior, R. C. S., Neto, A. D. D., & de Aquino, E. M. F. (2005). Building of constant life diagrams of fatigue using artificial neural networks. International Journal of Fatigue, 27(7), 746–751.CrossRefGoogle Scholar
  14. Freire Junior, R. C. S., Neto, A. D. D., & de Aquino, E. M. F. (2007). Use of modular networks in the building of constant life diagrams. International Journal of Fatigue, 29(3), 389–396.CrossRefGoogle Scholar
  15. Freire Junior, R. C. S., Neto, A. D. D., & de Aquino, E. M. F. (2009). Comparative study between ANN models and conventional equations in the analysis of fatigue failure of GFRP. International Journal of Fatigue, 31(5), 831–839.CrossRefGoogle Scholar
  16. Haque, M. E., & Sudhakar, K. V. (2002). ANN back-propagation prediction model for fracture toughness in microalloy steel. International Journal of Fatigue, 24(9), 1003–1010.CrossRefGoogle Scholar
  17. Harris, B. (Ed.). (2003). Fatigue in composites. Cambridge: Woodhead Publishing Ltd.Google Scholar
  18. Haykin, S. (2009). Neural networks and learning machines (3rd ed.). USA: Pearson Prentice Hall.Google Scholar
  19. Hidayat, M. I. P., & Melor, P. S. (2009). Optimizing neural network prediction of composite fatigue life under variable amplitude loading using Bayesian regularization chap. 9. In S. M. Sapuan & I. M. Mujtaba (Eds.), Composite materials technology: Neural network applications. USA: CRC Press, Taylor and Francis LLC.Google Scholar
  20. Hidayat, M. I. P., Yusoff, P. S. M. M., & Berata, W. (2011). Neural networks with NARX structure for material lifetime assessment application. In The 2011 IEEE symposium on computers and informatics (ISCI) (pp. 273–278), March 20–23, 2011, Kuala Lumpur, Malaysia. doi: 10.1109/ISCI.2011.5958926.
  21. Hidayat, M. I. P., & Berata, W. (2011). Neural networks with radial basis function and NARX structure for material lifetime assessment application. In The 12th international conference on quality in research (QiR 12) (pp. 143–150), July 4–7, 2011, Bali, Indonesia. doi: 10.4028/www.scientific.net/AMR.277.143.Google Scholar
  22. Hung, S. L., & Kao, C. Y. (2002). Structural damage detection using the optimal weights of the approximating artificial neural networks. Earthquake Engineering and Structural Dynamics, 31(2), 217–234.CrossRefGoogle Scholar
  23. Klemenc, J., & Fajdiga, M. (2012). Estimating S-N curves and their scatter using a differential ant-stigmergy algorithm. International Journal of Fatigue, 43(1), 90–97.CrossRefGoogle Scholar
  24. Klemenc, J., & Fajdiga, M. (2013). Joint estimation of E-N curves and their scatter using evolutionary algorithms. International Journal of Fatigue, 56(1), 42–53.CrossRefGoogle Scholar
  25. Lee, J. A., & Almond, D. P. (2003). A neural-network approach to fatigue life prediction chap. 21. In B. Harris (Ed.), Fatigue in composites. Cambridge: Woodhead Publishing Ltd.Google Scholar
  26. MacKay, D. J. C. (2004). Information theory, inference and learning algorithms. England: Cambridge University Press.Google Scholar
  27. Majidian, A., & Saidi, M. H. (2007). Comparison of fuzzy logic and neural network in life prediction of boiler tubes. International Journal of Fatigue, 29(3), 489–498.CrossRefGoogle Scholar
  28. Mandell, J. F., & Samborsky, D. D. (2010). DOE/MSU composite material fatigue database: Test, methods, material and analysis. SAND97-3002. Albuquerque, NM: Sandia National Laboratories.Google Scholar
  29. Mollah, A. A., & Pratihar, D. K. (2008). Modeling of TIG welding and abrasive flow machining processes using radial basis function networks. International Journal of Advanced Manufacturing Technology, 37(9–10), 937–952.CrossRefGoogle Scholar
  30. Nabney, I. T. (2002). NETLAB algorithms for pattern recognition. London: Springer.zbMATHGoogle Scholar
  31. Narendra, K., & Parthasarathy, K. (1990). Identification and control of dynamic systems using neural networks. IEEE Transactions on Neural Networks, 1(1), 4–27.CrossRefGoogle Scholar
  32. Neural Network Toolbox™ User’s Guide © COPYRIGHT 1992–2010. USA: The MathWorks, Inc.Google Scholar
  33. Nocedal, J., & Wright, S. J. (2006). Numerical optimization (2nd ed.). New York: Springer.zbMATHGoogle Scholar
  34. Philippidis, T. P., & Passipoularidis, V. A. (2007). Residual strength after fatigue in composites: Theory vs. experiment. International Journal of Fatigue, 29(12), 2104–2116.CrossRefGoogle Scholar
  35. Passipoularidis, V. A., & Philippidis, T. P. (2009). A study of factors affecting life prediction of composites under spectrum loading. International Journal of Fatigue, 31(3), 408–417.CrossRefGoogle Scholar
  36. Passipoularidis, V. A., Philippidis, T. P., & Brondsted, P. (2011). Fatigue life prediction in composites using progressive damage modelling under block and spectrum loading. International Journal of Fatigue, 33(2), 132–144.CrossRefGoogle Scholar
  37. Post, N. L., Case, S. W., & Lesko, J. J. (2008). Modeling the variable amplitude fatigue of composite materials: A review and evaluation of the state of the art for spectrum loading. International Journal of Fatigue, 30(12), 2064–2086.CrossRefzbMATHGoogle Scholar
  38. Pujol, J. C. F., & Pinto, J. M. A. (2011). A neural network approach to fatigue life prediction. International Journal of Fatigue, 33(3), 313–322.CrossRefGoogle Scholar
  39. Reifsnider, K. L. (Ed.). (1991). Fatigue of composite materials. Amsterdam: Elsevier.Google Scholar
  40. Schijve, J. (Ed.). (2009). Fatigue of structures and materials (pp. 373–394). Netherlands: Springer.Google Scholar
  41. Sendeckyj, G. P. (2001). Constant life diagrams—A historical review. International Journal of Fatigue, 23(4), 347–353.CrossRefGoogle Scholar
  42. Vassilopoulos, A. P., & Philippidis, T. P. (2002). Complex stress state effect on fatigue life of GRP laminates. Part I, experimental. International Journal of Fatigue, 24(8), 813–823.CrossRefGoogle Scholar
  43. Vassilopoulos, A. P., Georgopoulos, E. F., & Dionysopoulos, V. (2007). Artificial neural networks in spectrum fatigue life prediction of composite materials. International Journal of Fatigue, 29(3), 20–29.CrossRefGoogle Scholar
  44. Vassilopoulos, A. P., Georgopoulos, E. F., & Keller, T. (2008). Comparison of genetic programming with conventional methods for fatigue life modeling of FRP composite materials. International Journal of Fatigue, 30(9), 1634–1645.CrossRefGoogle Scholar
  45. Vassilopoulos, A. P., Manshadi, B. D., & Keller, T. (2010). Influence of the constant life diagram formulation on the fatigue life prediction of composite materials. International Journal of Fatigue, 32(4), 659–669.CrossRefGoogle Scholar
  46. Venkatesh, V., & Rack, H. J. (1999). A neural network approach to elevated temperature creep–fatigue life prediction. International Journal of Fatigue, 21(3), 225–234.CrossRefGoogle Scholar
  47. Zhang, Z., & Friedrich, K. (2003). Artificial neural networks applied to polymer composites: A review. Composites Science and Technology, 63(14), 2029–2044.CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Department of Materials and Metallurgical Engineering-FTIInstitut Teknologi Sepuluh Nopember SurabayaSurabayaIndonesia

Personalised recommendations