In this paper, we propose a new approach for the simulation-based support of tryout operations in deep drawing which can be schematically classified as automatic knowledge acquisition. The central idea is to identify information maximising sensor positions for draw-in as well as local blank holder force sensors by solving the column subset selection problem with respect to the sensor sensitivities. Inverse surrogate models are then trained using the selected sensor signals as predictors and the material and process parameters as targets. The final models are able to observe the drawing process by estimating current material and process parameters, which can then be compared to the target values to identify process corrections. The methodology is examined on an Audi A8L side panel frame using a set of 635 simulations, where 20 out of 21 material and process parameters can be estimated with an R2 value greater than 0.9. The result shows that the observational models are not only capable of estimating all but one process parameters with high accuracy, but also allow the determination of material parameters at the same time. Since no assumptions are made about the type of process, sensors, material or process parameters, the methodology proposed can also be applied to other manufacturing processes and use cases.

No abstract

No abstract

Recent work aims at the inverse parameter estimation in deep drawing using pretrained surrogate models for the detection of the current process, material or tool parameters. The use of the methodology requires the definition of state variables to describe the current process state. Whereas our recent work makes use of draw-ins and local blankholder forces, other approaches from the literature also use skid-lines measured after the deep drawing process. For the future, the solution with even higher information content would be to detect the global strain distribution on the final part and use it as a state variable for process detection, which has not been documented in the literature to the best knowledge of the authors. In this work, we present a first step into this direction by comparing the surrogate model based parameter estimation by using draw-ins and by using the movement of material fixed points on the blank over the deep drawing process. The result shows that the mathematical methods used for parameter prediction based on draw-ins can directly be used for the prediction with fixed point translations as reference. For the investigations, a cup drawing process is used.