Open Access Open Access  Restricted Access Subscription Access

Failure Prediction of Composite Materials Using Deep Neural Networks

ALLYSON FONTES, FARJAD SHADMEHRI

Abstract


Fiber-reinforced polymer (FRP) composite materials are increasingly used in engineering applications. However, an investigation into the precision of conventional failure criteria, known as the World-Wide Failure Exercise (WWFEI), revealed that current theories remain unable to predict failure within an acceptable degree of accuracy. Deep Neural Networks (DNN) are emerging as an alternate and time-efficient technique for predicting the failure strength of FRP composite materials. The present study examined the applicability of DNNs as a tool for creating a data-driven failure model for composite materials. The experimental failure data presented in the WWFE-I were used to develop the datadriven model. A fully connected DNN with 23 input units and 1 output unit trained with a constant learning rate (α=0.0001). The network’s inputs described the laminates and the loading conditions applied to the test specimen, whereas the output was the length of the failure vector (L=(σx+σy+τxy)0.5). The DNN’s performance was evaluated using the mean squared error on a subset of the experimental data unseen during training. Network configurations with a varying number of hidden layers and units per layer were evaluated. The DNN with 3 hidden layers and 20 units per hidden layer performed the best. In fact, the network’s predictions show good agreement with the experimental results. The failure boundaries generated by the DNN were compared to three conventional theories: the Tsai-Wu, Cuntze, and Puck theory. The DNN’s failure envelopes were found to fit the experimental data more closely than the above-mentioned theories. In sum, the DNN’s ability to fit higher-order polynomials to data separates it from conventional failure criteria. This characteristic makes DNNs an effective method for predicting the failure strength of composite laminates.


DOI
10.12783/asc36/35822

Full Text:

PDF

References


C. S. Lee, W. Hwang, H. C. Park, and K. S. Han. 1999. “Failure of carbon/epoxy composite

tubes under combined axial and torsional loading 1. Experimental results and prediction of

biaxial strength by the use of neural networks,” Composites Science and Technology,

(12):1779–1788.

A. T. Seyhan, G. Tayfur, M. Karakurt, and M. Tanoglu. 2005. “Artificial neural network (ANN)

prediction of compressive strength of VARTM processed polymer composites,” Computational

Materials Science, 34(1):99–105.

F. Sen, M. Aydin Komur, and O. Sayman. 2010. “Prediction of Bearing Strength of Two Serial

Pinned/Bolted Composite Joints using Artificial Neural Networks,” Journal of Composite

Materials, 44(11):1365–1377.

Gurney, K. 1997. An introduction to neural networks. UCL Press.

Ketkar, N. 2017. Deep learning with Python: a hands-on introduction. Apress.

Goodfellow, I., Bengio, Y., and Courville, A. 2016. Deep Learning. MIT Press.

Soden, P. D., Hinton, M. J., and Kaddour, A. S. 2004. “Chapter 2.1 - Lamina properties, lay-up

configurations and loading conditions for a range of fibre reinforced composite laminates,” in

Failure Criteria in Fibre-Reinforced-Polymer Composites, Oxford: Elsevier, pp. 30–51.

Soden, P. D., Hinton, M. J., and Kaddour, A. S., 2004. “Chapter 2.2 - Biaxial test results for

strength and deformation of a range of E-glass and carbon fibre reinforced composite laminates:

Failure exercise benchmark data,” in Failure Criteria in Fibre-Reinforced-Polymer Composites,

Oxford: Elsevier, pp. 52–96.

Google Colaboratoy. (2019). Online. Available: https://colab.research.google.com/

Python Version 3.8. (2019). Python Software Foundation. Online. Available:

http://www.python.org

PyTorch: An Imperative Style, High-Performance Deep Learning Library. (2019). Facebook,

Inc. Online. Available: https://pytorch.org/

Kuraishi, A., Tsai, S. W., and Liu, K. K. S. 2004. “Chapter 5.9 - A progressive quadratic failure

criterion, part B,” in Failure Criteria in Fibre-Reinforced-Polymer Composites, M. J. Hinton,

A. S. Kaddour, and P. D. Soden, Eds. Oxford: Elsevier, pp. 903–921.

Cuntze, R. G. 2004. “Chapter 5.13 - The predictive capability of failure mode concept-based

strength criteria for multi-directional laminates—Part B,” in Failure Criteria in Fibre-

Reinforced-Polymer Composites, M. J. Hinton, A. S. Kaddour, and P. D. Soden, Eds. Oxford:

Elsevier, pp. 976–1025.

Puck, A., and Schürmann, H. 2004. “Chapter 5.6 - Failure analysis of FRP laminates by means

of physically based phenomenological models,” in Failure Criteria in Fibre-Reinforced-

Polymer Composites, M. J. Hinton, A. S. Kaddour, and P. D. Soden, Eds. Oxford: Elsevier, pp.

–876.


Refbacks

  • There are currently no refbacks.