Techno Press
Techno Press

Steel and Composite Structures   Volume 9, Number 6, December 2009, pages 557-568
DOI: http://dx.doi.org/10.12989/scs.2009.9.6.557
 
Prediction on the fatigue life of butt-welded specimens using artificial neural network
Kim, Kyoung Nam, Lee, Seong Haeng and Jung, Kyoung Sup

 
Abstract     [Full Text]
    Fatigue tests for extremely thick plates require a great deal of manufacturing time and are expensive to perform. Therefore, if predictions could be made through simulation models such as an artificial neural network (ANN), manufacturing time and costs could be greatly reduced. In order to verify the effects of fatigue strength depending on the various factors in SM520C-TMC steels, this study constructed an ANN and conducted the learning process using the parameters of calculated stress concentration factor, thickness and input heat energy, etc. The results showed that the ANN could be applied to the prediction of fatigue life.
 
Key Words
    prediction; fatigue life; fatigue strength; artificial neural network.
 
Address
Kim, Kyoung Nam; School of Civil Engineering, Chungbuk National University, Cheongju, Korea
Lee, Seong Haeng; Department of Civil Engineering, Pusan National University, Busan, Korea
Jung, Kyoung Sup; School of Civil Engineering, Chungbuk National University, Cheongju, Korea
 

Techno-Press: Publishers of international journals and conference proceedings.       Copyright © 2019 Techno Press
P.O. Box 33, Yuseong, Daejeon 305-600 Korea, Tel: +82-42-828-7996, Fax : +82-42-828-7997, Email: technop@chol.com