INFORMATIVE BOUNDS OF NEURAL NETWORKS PREDICTION FOR COMPOSITE FATIGUE LIFE UNDER VARIABLE AMPLITUDE LOADING

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

Abstract


In this study, the informative bounds of neural networks (NN) prediction with respect to the utilization of less fatigue data for fatigue life assessment of composite material covering a wide range of stress ratios R was examined and investigated. Fiberglass reinforced polyester of [90/0/±45/0]S  lay-up with fatigue data of various stress ratios  (R = 0.1, 0.5, 0.7, 0.8, 0.9, -0.5, -1, -2 and 10)  was examined in the present paper. Multi-layer Perceptrons (MLP) trained with Levenberg-Marquardt algorithm was utilized to result in fast and efficient NN model and Bayesian regularization technique was incorporated to deal with limited training data chosen for the model. The developed NN model was trained with fatigue data from only two stress ratios, where three sets of two stress ratio values were formed and used as the training sets, namely R = 0.1 and 0.5, R = 0.1 and -1, and R = 0.1 and 10, respectively. It was obtained that fatigue data from R = 10 produced the widest bounds of prediction, namely having the highest estimated standard deviation value from the fatigue lives predicted. Furthermore, it is revealed in the current study knowing the fact that fatigue data from R = 10 have the highest estimated standard deviation and subsequently including the fatigue data as one of the training data set, the NN model trained could produce the lowest mean squared error (MSE) value for the results of fatigue life prediction. This is justifying also the selection of training set of R = 0.1 and 10 as best training set in the previous study, which is based on the stress ratios’ better relative positions in the corresponding constant life diagram (CLD).  Finally, taking the highest estimated standard deviation value from fatigue data of R = 10 as the conservative estimated bounds of NN prediction, it was shown that for the NN prediction of fatigue life whose noticeable discrepancies with the experimental data, the discrepancies were well confined within the conservative bounds of prediction.   


Keywords


Neural networks; composite fatigue life; variable amplitude loading; Levenberg-Marquardt; bounds of prediction

Full Text:

PDF

References


Al-Assaf, Y., El-Kadi, H., “Fatigue Life Prediction of Unidirectional Glass Fiber/Epoxy Composite Laminae Using Neural Networks,” Composites Structures, Vol. 53, No. 6, pp. 65-71, 2001.

Bishop, C.M., “Neural Networks for Pattern Recognition”, Clarendon, Oxford 1995, Chap. 10.

El-Kadi, H., Al-Assaf, Y., “Prediction of The Fatigue Life of Unidirectional Glass Fiber/Epoxy Composite Laminae Using Different Neural Network Paradigms,” Composites Structures, Vol. 55, No. 1, pp. 239-246, 2002.

Foresee, F.D. and Hagan, M.T., “Gauss-Newton Approximation to Bayesian Learning”, IEEE International Conference on Neural Networks, Vol. 3, No. 8, pp. 1930-1935, 1997.

Freire Junior, R.C.S., Neto, A.D.D. and de Aquino, E.M.F., “Use of modular networks in the building of constant life diagrams,” International Journal of Fatigue, Vol. 29, No. 1, pp. 389-396, 2007.

Freire Junior, R.C.S., Neto, A.D.D., and de Aquino, E.M.F., “Comparative Study between ANN Models and Conventional Equations in The Analysis of Fatigue Failure of GFRP,” International Journal of Fatigue, Vol. 31, No. 5, pp. 831-839, 2009.

Gupta, M.M., Jin, L., and Homma, N., “Statics and Dynamics Neural Networks-From Fundamentals to Advanced Theory”, John Wiley & Sons, Inc., New Jersey, 2003.

Harris, B. (ed.), “Fatigue in Composites”, Woodhead Publishing Ltd, Cambridge, England, 2003.

Haykin, S., “Neural Networks and Learning Machines”, 3rd ed., Pearson Prentice Hall, USA, 2009.

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.

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

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

Lee, J.A., Almond, D.P., “A Neural-Network Approach to Fatigue Life Prediction,” Fatigue in Composites, edited by B. Harris, Woodhead Publishing Ltd, Cambridge, England, pp. 569-589, 2003.

MacKay, D.J.C, “Information Theory, Inference and Learning Algorithms”, Cambridge University Press, England, 2004.

Mandell J.F., Samborsky D.D., “DOE/MSU Composite Material Fatigue Database: Test, Methods, Material and Analysis”, SAND97-3002, Sandia National Laboratories, 2010.

Nocedal, J. and Wright, S.J., “Numerical Optimization”, 2nd ed., Springer, New York, 2006, Chap. 10.

Vassilopoulos, A.P., Georgopoulos, E.F., and Dionysopoulos, V., “Artificial Neural Networks in Spectrum Fatigue Life Prediction of Composite Materials,” International Journal of Fatigue, Vol. 29, No. 3, pp. 20-29, 2007.




DOI: http://dx.doi.org/10.12962/j2746279X.v2i2.11549

Refbacks

  • There are currently no refbacks.


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

 
View My Stats