Fatigue life prediction of composite materials using polynomial classifiers and recurrent neural networks

2007 ◽  
Vol 77 (4) ◽  
pp. 561-569 ◽  
Author(s):  
Yousef Al-Assaf ◽  
Hany El Kadi
Keyword(s):  
Neural Networks ◽  
Fatigue Life ◽  
Composite Materials ◽  
Recurrent Neural Networks ◽  
Life Prediction ◽  
Fatigue Life Prediction ◽  
Polynomial Classifiers

Fatigue Life Prediction of Composite Materials: Artificial Neural Networks vs. Polynomial Classifiers

2011 ◽  
Vol 471-472 ◽  
pp. 221-226 ◽  
Author(s):  
Hany A. El Kadi
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Fatigue Life ◽  
Composite Materials ◽  
Life Prediction ◽  
Fatigue Behavior ◽  
Fatigue Life Prediction ◽  
Advantages And Disadvantages ◽  
Artificial Neural ◽  
Polynomial Classifiers

Artificial neural networks (ANN) and polynomial classifiers (PC) have been successfully used to predict the fatigue failure of fiber reinforced composite materials. This includes predicting the behavior of the same material subjected to different loading conditions as well as predicting the fatigue behavior of different materials. In this work, the fatigue life prediction obtained using both methods will be compared. The effect of the various parameters influencing the prediction will be presented and the advantages and disadvantages of each of the methods will be discussed.

Fatigue Life Prediction of Different Fiber-Reinforced Composites Using Polynomial Classifiers

2011 ◽  
Vol 133 (2) ◽  
Author(s):  
H. El Kadi ◽  
I. M. Deiab ◽  
M. Al-Assadi
Keyword(s):  
Fatigue Life ◽  
Composite Materials ◽  
Fiber Orientation ◽  
Life Prediction ◽  
Fatigue Loading ◽  
Experimental Results ◽  
Fatigue Life Prediction ◽  
Fiber Reinforced Composites ◽  
Reinforced Composites ◽  
Polynomial Classifiers

Polynomial classifiers (PC) have already been shown to produce good fatigue life prediction for a specific composite under a variety of fatigue loading conditions. In this study, polynomial classifiers are used to predict the fatigue life in other composite materials not used in training. Different composite materials with a variety of fiber orientation angles are considered. The predictions obtained using PC are compared with the experimental results and are shown to be promising.

Sign in / Sign up

Export Citation Format

Share Document