An artificial neural network-based model for analysing the R-ratio effect on fatigue crack propagation

In this paper, we present an overall strategy for analyzing the crack growth rate of some metals with respect to the influence of different stress ratio (R-ratio) using artificial neural networks (ANNs) models. Two ANN models are used to approximate the inherent nonlinear relationship between the material parameters and the R-ratio. Through training with the back-propagation algorithm, the ANN models are capable of predicting the unknown material parameters based on a given R-ratio. The good performance of the proposed ANN models is validated on two sets of published fatigue crack growth data under different R-ratios, i.e. the 2024-T351 aluminum alloy data and steel 4340 data. The simulation results indicate that the ANNs-based overall strategy is feasible and effective for the analysis of fatigue crack growth rates under the influence of different R-ratio.

[1]  R. Palmer,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[2]  P. C. Paris,et al.  A Critical Analysis of Crack Propagation Laws , 1963 .

[3]  Zhihong Man,et al.  Robust Single-Hidden Layer Feedforward Network-Based Pattern Classifier , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[4]  Royce Forman,et al.  Fatigue Crack Growth Database for Damage Tolerance Analysis , 2005 .

[5]  Omesh K. Chopra,et al.  Using artificial neural networks to predict the fatigue life of carbon and low-alloy steels , 2000 .

[6]  Daniela Iacoviello,et al.  Analysis of stress ratio effects on fatigue propagation in a sintered duplex steel by experimentation and artificial neural network approaches , 2004 .

[7]  Pang Chong-Myong,et al.  Crack growth and closure behavior of short fatigue cracks , 1994 .

[8]  Digby D. Macdonald,et al.  Prediction of crack growth rate in Type 304 stainless steel using artificial neural networks and the coupled environment fracture model , 2014 .

[9]  Zhigang Zeng,et al.  Deformation Prediction of Landslide Based on Improved Back-propagation Neural Network , 2012, Cognitive Computation.

[10]  Kaj Madsen,et al.  Methods for Non-Linear Least Squares Problems , 1999 .

[11]  W. Elber.  The Significance of Fatigue Crack Closure , 1971 .

[12]  Chuanzeng Zhang,et al.  A new approximate model for the R-ratio effect on fatigue crack growth rate , 2014 .

[13]  Shucheng Yu,et al.  Privacy Preserving Back-Propagation Neural Network Learning Made Practical with Cloud Computing , 2014, IEEE Transactions on Parallel and Distributed Systems.

[14]  G. Glinka,et al.  A two parameter driving force for fatigue crack growth analysis , 2005 .

[15]  P. Paris.  A rational analytic theory of fatigue , 1961 .

[16]  Torgeir Moan,et al.  Improved modeling of the effect of R-ratio on crack growth rate , 2007 .

[17]  U. Krupp.  Fatigue Crack Propagation in Metals and Alloys: Microstructural Aspects and Modelling Concepts , 2007 .

[18]  Zhihong Man,et al.  Dynamic neural modeling of fatigue crack growth process in ductile alloys , 2016, Inf. Sci..

[19]  Krishna Dutta,et al.  Low Cycle Fatigue Life Prediction of Al–Si–Mg Alloy Using Artificial Neural Network Approach , 2016, Transactions of the Indian Institute of Metals.