Prediction of fatigue crack propagation rate on the interface of wood-FRP using the artificial neural network (ANN)

Liang Zhang; Junhui Jia; Yongjun Liu

doi:10.1117/12.839046

27 August 2009 Prediction of fatigue crack propagation rate on the interface of wood-FRP using the artificial neural network (ANN)

Liang Zhang, Junhui Jia, Yongjun Liu

Author Affiliations +

Proceedings Volume 7375, ICEM 2008: International Conference on Experimental Mechanics 2008; 737513 (2009) https://doi.org/10.1117/12.839046
Event: International Conference on Experimental Mechanics 2008 and Seventh Asian Conference on Experimental Mechanics, 2008, Nanjing, China

Abstract

Crack propagation rate of the interface of fiber reinforced polymer (FRP) bonded to red maple wood, is analyzed and predicted using an artificial neural network (ANN) method. The performance of Multilayer Perceptron (MLP) and Modular Neural Network (MNN) is compared to obtain an optimal ANN model to predict the crack propagation rate. The effect of various parameters of the MNN and MLP models are investigated. The number of input vectors of MLP and MNN models is studied to see if this will affect the training and predicting performance by the scatter of input vectors. At last, a new method called sensitivity analysis is adopted to explore the influenced proportion of the input vectors and the effect of load ratio, frequency, et al., on the crack propagation rate.

Citation Download Citation

Liang Zhang, Junhui Jia, and Yongjun Liu "Prediction of fatigue crack propagation rate on the interface of wood-FRP using the artificial neural network (ANN)", Proc. SPIE 7375, ICEM 2008: International Conference on Experimental Mechanics 2008, 737513 (27 August 2009); https://doi.org/10.1117/12.839046

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available