A study on using image-based machine learning methods to develop surrogate models of stamp forming simulations

In design for forming, it is becoming increasingly significant to develop surrogate models of high-fidelity finite element analysis (FEA) simulations of forming processes, to achieve effective component feasibility assessment as well as process and component optimizations. However, surrogate models using traditional scalar-based machine learning methods (SBMLMs) fall short on accuracy and generalizability. This is because SBMLMs fail to harness the location information available from the simulations. To overcome this shortcoming, the theoretical feasibility and practical advantages of innovatively applying image-based machine learning methods (IBMLMs) in developing surrogate models of sheet stamp forming simulations are explored in this study. To demonstrate the advantages of IBMLMs, the effect of the location information on both design variables and simulated physical fields is firstly proposed and analyzed. Based on a sheet steel stamping case study, a Res-SE-U-Net IBMLM surrogate model of stamping simulations is then developed and compared with a baseline multi-layer perceptron (MLP) SBMLM surrogate model. The results show that the IBMLM model is advantageous over the MLP SBMLM model in accuracy, generalizability, robustness, and informativeness. This paper presents a promising methodology in leveraging IBMLMs as surrogate models to make maximum use of information from stamp forming FEA results. Future prospective studies that are inspired by this paper are also discussed.

Influence of Automated Fiber Placement Parameters on Thermoplastic Composite Blanks Used on Stamp Forming Process

In recent years, advanced manufacturing processes have been developed to increase the speed of production in order to reduce production costs. At the scale of thermoplastic composites, the translation is the combination of advanced manufacturing processes. The focus in this study is more specifically on the coupling of automated lay-up (AFP) and stamp forming processes. To date, a consolidation process, such as press-consolidation of thermoplastic composites, obtained blanks. Several trials have begun using an automated fiber placement consolidation to reduce manufacturing time and use unidirectional material. However, the combination of AFP and stamp forming is useful if it optimizes this process without the blank’s full consolidation, which by resulting reduces the manufacturing time. This study estimates blank characteristics through thermal history imposed by a more rapid manufacturing process. A set of blanks with varying process parameters is produced to investigate the influence at the microscopic scale. The interface behaviour is observed with optical microscope and image processing. A statistical study applied to the process is carried out in order to relate the material observations to the input parameters. The results of this study are used for the study of the next process of the combination: the stamp forming.

Stamp Forming: A Comparison in the Use of Draw Beads and Blank Holder Force for Producing Aluminum Panels

An investigation was performed examining the effects of draw beads and blank holder forces on local forces in various regions of a stamp forming process that produced oval aluminum panels. The results showed that provided there was sufficient blank holder forces to prevent wrinkling, the regions with draw beads were affected more by draw bead height than by blank holder force. However, at the die ends, away from the draw beads, blank holder force had more of an effect than the draw beads did with respect to local forces. Additionally, the draw bead height effects at the die end were not directly related but had to be interpreted based upon the effect on strains within the flange region at the die ends. This study may be especially useful for researchers in the automotive sector who are particularly interested in aluminum panel forming.