文档介绍：Available online at ernational
Journalof
International Journal of Fatigue 30 (2008) 1634–1645 Fatigue
ate/ijfatigue
Comparison of ic programming with conventional methods
for fatigue life modeling of posite materials
Anastasios P. Vassilopoulos a,*, Efstratios F. opoulos b, Thomas Keller a
posite Construction Laboratory (CCLab), Ecole Polytechnique Fe´de´rale de Lausanne (EPFL), Station 16, CH-1015 Lausanne, Switzerland
b Pattern Recognition Laboratory, Department puter Engineering and Informatics, University of Patras, 265 04 Patras, Greece
Received 17 May 2007; received in revised form 4 October 2007; accepted 13 November 2007
Available online 23 November 2007
Abstract
ic programming is used in this paper for modeling the fatigue life of several fiber–posite material systems. It is
shown that if the ic programming tool is adequately trained, it can produce theoretical predictions pare favorably with
corresponding predictions by other, conventional methods for the interpretation of fatigue data. For parison of results, curves
produced by the ic programming tool are plotted together with curves produced by three monly used methods for the
analysis posite material fatigue data: linear regression, Whitney’s Weibull statistics and Sendeckyj’s wear-out model. The mod-
eling accuracy of putational technique, whose application for this purpose is novel, is very high. The proposed modeling tech-
nique presents certain pared to conventional methods. The new technique is a stochastic process that leads straight to a
multi-slope S–N curve that follows the trend of the experimental data, without the need for any assumptions.
Ó 2007 Elsevier Ltd. All rights reserved.
Keywords: Fatigue; ic programming; Life prediction; S–N curve
1. Introduction ters of the fatigue model are then estimated by fitting the
experimental data.
The realization prehensive experimental pro- One of the most explicit and straightforward ways to
grams is very important w