0
Research Papers

Modeling the S-N Curves of Polyamide PA66 Using a Serial Hybrid Neural Network

[+] Author and Article Information
Jernej Klemenc1

Andrej Wagner, Matija Fajdiga

 Faculty of Mechanical Engineering, University of Ljubljana, Askerceva 6, SI-1000 Ljubljana, Slovenia

A demo version of the software DATAFIT 9.0 was downloaded from the Oakdale Engineering web-site: http://www.oakdaleengr.com/.

These are the 6 S-N curves from the three groups that are in the area of the sample space that is well covered with the experimental results.

1

Corresponding author.

J. Eng. Mater. Technol 133(3), 031005 (Jul 05, 2011) (14 pages) doi:10.1115/1.4004054 History: Received September 06, 2010; Revised April 06, 2011; Published July 05, 2011; Online July 05, 2011

The fatigue damage to polymers generally depends on the material properties as well as on the mechanical, thermal, chemical, and other environmental influences. In this article, a methodology for modeling the dependence of the PA66 S-N curves on the material parameters, the material state, and the operating conditions is presented. The core of the presented methodology is a multilayer perceptron neural network combined with an analytical model of the PA66 S-N curve. Such a hybrid approach simultaneously utilizes the good approximation capabilities of the multilayer perceptron and knowledge of the phenomenon under consideration, because the analytical model for the S-N curves was estimated on the basis of the existing experimental data from the literature. The article presents the theoretical background of the applied methodology. The applicability and uncertainty of the presented methodology were assessed for the available data from the literature. The results show that it was possible to approximate the PA66 S-N curves for different input parameters if the space of the input parameters was adequately covered by the corresponding S-N curves.

FIGURES IN THIS ARTICLE
<>
Copyright © 2011 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Figure 2

Serial hybrid multilayer perceptron (see also Agarwal [24])

Grahic Jump Location
Figure 3

Topology of the applied hybrid multilayer perceptron

Grahic Jump Location
Figure 4

Simplified histories of the cost-function changes during the training process

Grahic Jump Location
Figure 5

Comparison of the original and approximated S-N curves for the SHMP topologies SHMP_1 (left) and SHMP_2 (right)

Grahic Jump Location
Figure 6

Original and approximated S-N curves for the SHMP topologies SHMP_1 (left) and SHMP_1a (right)

Grahic Jump Location
Figure 7

Influence of the percentage of glass fibers on the variation of the PA66 S-N curve

Grahic Jump Location
Figure 8

Influence of the operating temperature on the variation of the PA66 S-N curve

Grahic Jump Location
Figure 9

Influence of the loading frequency on the variation of the PA66 S-N curve

Grahic Jump Location
Figure 10

Estimation of the parameter uncertainty by the bootstrap method: parameter a

Grahic Jump Location
Figure 11

Estimation of the parameter uncertainty by the bootstrap method: parameter b

Grahic Jump Location
Figure 12

Estimation of the parameter uncertainty by the bootstrap method: parameter c

Grahic Jump Location
Figure 13

Estimation of the parameter uncertainty by the bootstrap method: parameter d

Grahic Jump Location
Figure 1

Typical representatives of the three groups of PA66 S-N curves [30]

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In