Abstract
The relationships between the fatigue crack growth rate and stress intensity factor range are not always linear even in the Paris region. The stress ratio effects on fatigue crack growth rate are diverse in different materials. However, most existing fatigue crack growth models cannot handle these nonlinearities appropriately. The machine learning method provides a flexible approach to the modeling of fatigue crack growth because of its excellent nonlinear approximation and multivariable learning ability. In this paper, a fatigue crack growth calculation method is proposed based on three different machine learning algorithms (MLAs): extreme learning machine (ELM), radial basis function network (RBFN) and genetic algorithms optimized back propagation network (GABP). The MLA based method is validated using testing data of different materials. The three MLAs are compared with each other as well as the classical two-parameter model ( approach). The results show that the predictions of MLAs are superior to those of approach in accuracy and effectiveness, and the ELM based algorithms show overall the best agreement with the experimental data out of the three MLAs, for its global optimization and extrapolation ability.
Highlights
As the damage tolerance concept has been widely accepted and applied in the aerospace engineering, it becomes necessary and important to calculate the fatigue crack growth
The results reveal that though the employed materials are of different fatigue crack growth characteristics, the three machine learning algorithms (MLAs) all can fit the experimental data very well with excellent nonlinearities, which is better than that of the employed materials are of different fatigue crack growth characteristics, the three
A fatigue crack growth calculation method based on MLA is proposed, and three
Summary
As the damage tolerance concept has been widely accepted and applied in the aerospace engineering, it becomes necessary and important to calculate the fatigue crack growth. Da/dN − ∆K curve in the log-log coordinate has three characteristic regions, which are named threshold region (region I), Paris region (region II) and high ∆K region (region III). It can be observed in extensive experimental results that the relationships between fatigue crack growth rate (da/dN ) and stress intensity factor range (∆K ) are not linear even in the Paris region [1,2,3,4]. The stress ratio effects on da/dN − ∆K curves are diverse in different materials. The relationship between da/dN and ∆K is of complex nonlinearity
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call