Abstract
This paper mainly proposes an artificial neural network (ANN) model for predicting edge stretchability of GPa-grade steels, which is substantially difficult to predict due to the complex nonlinear relation among the numerous sheared edge qualities. We newly suggest the physically characterized parameters, such as material properties, deformed shape, and work hardening of sheared edge, to predict the various materials and punching methods, simultaneously. The proposed parameters are trained with the pre-damage strain which is calculated by inherent fracture strain and experimental results in terms of hole expansion ratio. To prevent the overfitting issues, cross validation method with additional datasets from a different kind of edge stretchability test such as sheared edge tensioning test are utilized. Experimental validations have been conducted with various GPa-grade steels and sheared edge conditions, which are compared with the proposed ANN model and numerical simulation. The proposed ANN model exhibits remarkable performance in the prediction of hole expansion ratio having a mean absolute error of 1.5% when compared to the previous studies such as numerical simulation and ANN model with utilizing the maximum hardness measured at the sheared edge.
Highlights
GPa-grade steels which exhibit an ultimate tensile strength of at least 1,000 MPa have been widely applied to body-inwhite (BIW) structures to improve their crash worthiness and reduce their weight [1,2,3]
The rest of the paper is organized as follow: In Section II, we present the new experimental datasets to predict various sheared edge qualities by categorizing the input parameters based on the physically meanings related to the edge cracking
It is not proper to apply for the advanced punching method such as humped bottom punch and twostage punching which show remarkable improvements in hole expansion ratio (HER) compared to the flat punch, since advanced punching methods can improve the HER by dramatically reducing the hardness at the bottom of fracture zone, the maximum hardness is similar to the conventional punch as shown in Fig. 5 [8,9]
Summary
GPa-grade steels which exhibit an ultimate tensile strength of at least 1,000 MPa have been widely applied to body-inwhite (BIW) structures to improve their crash worthiness and reduce their weight [1,2,3]. Pathak [17] suggested predamage value using 3-dimentional X-ray computed tomography for capturing the number of voids per unit volume after punching process, which could precisely represent the edge cracking by considering the void growth and their coalescence Despite their good prediction accuracy, this method is limited to utilize due to the high costs and time to obtain dataset, which makes it possible to apply to various applications. He et al [18] recently proposed an experimental method for defining the pre-damage using the hardness (HV) to characterize the work hardening with respect to the punching clearances. To evaluate the initial strain hardening characteristics in detail, the mean gradient for each section was calculated by partitioning 5 sections from yield strength to ultimate tensile strength as shown in Fig. 3, which are adopted for the input features of material hardening including conventional input features such as yield strength and strain hardening exponent
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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
