Abstract
This study proposes a method for the temporal and spatial determination of the onset of local necking determined by means of a Nakajima test set-up for a DC04 deep drawing and a DP800 dual-phase steel, as well as an AA6014 aluminum alloy. Furthermore, the focus lies on the observation of the progress of the necking area and its transformation throughout the remainder of the forming process. The strain behavior is learned by a machine learning approach on the basis of the images when the process is close to material failure. These learned failure characteristics are transferred to new forming sequences, so that critical areas indicating material failure can be identified at an early stage, and consequently enable the determination of the beginning of necking and the analysis of the necking area. This improves understanding of the necking behavior and facilitates the determination of the evaluation area for strain paths. The growth behavior and traceability of the necking area is objectified by the proposed weakly supervised machine learning approach, thereby rendering a heuristic-based determination unnecessary. Furthermore, a simultaneous evaluation on image and pixel scale is provided that enables a distinct selection of the failure quantile of the probabilistic forming limit curve.
Highlights
The forming range of sheet metal to produce defect-free components is evaluated by means of the forming limit curve (FLC), whose limits are defined by the major and minor strain pairs and define the onset of local necking immediately
The focus of our approach is the differentiation of the individual forming phases on image scale, with respect to the image characteristics of the entire image without focusing or emphasizing explicitly occurring structures. This is exactly where our suggested method comes into play, so that fine structures that are characteristic for material failure are segmented early within forming sequences such that the development of the critical area can be accurately traced on a pixel scale
In order to assess the quality of the segmentation method, a comparison between the estimates and the automatically generated ground truth annotations is provided by the dice coefficient [36], which enables an evaluation on pixel scale: Dice =
Summary
The forming range of sheet metal to produce defect-free components is evaluated by means of the forming limit curve (FLC), whose limits are defined by the major and minor strain pairs and define the onset of local necking immediately. Even though the features were learned with only two classes, a three-class classification of the forming process into a homogeneous, transition and inhomogeneous forming phase is provided by the cluster method (cf Figure 1a) An advantage of this methodology is the complete independence from time and predefined evaluation area. Another important factor is the possible application of the well-established Grad–Cam method [30] This approach highlights the relevant regions for the decision process, i.e., from the network point of view, by providing a heat map for each strain distribution of the forming sequence, facilitating visual interpretation of the results and the determination of the onset of necking. (b) time step 10 (c) time step 36 (d) time step 46 (e) time step 48 (f) time step 52
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
