During the manufacture of metal parts, geometrical deviations can appear. The reasons for this can be a variation in the properties of the semi-finished product, or wear phenomena on the punch-bending machine itself or on the punch-bending tool. When geometrical deviations appear, the process parameters normally have to be adjusted manually. The choice of the most appropriate process parameters is currently based on the operator's experience. Unfortunately, this is a time-consuming and expensive procedure right at the early stages of a production scenario. In addition, the trend towards reduced part sizes with tight tolerances, made of high strength materials, is drastically increasing the requirements regarding the production process. In order to reduce the scrap rate and the setup time for production scenarios, it is necessary to implement corrective action during the process by means of a special control strategy. A self-correcting control strategy based on a closed-loop control approach is thus under development at the University of Paderborn. The first step in this strategy involved conducting simulations is to identify those process variables, e.g. the strength or the geometrical properties of the material, which have a significant influence on the process. Once correlations between input and output variables had been established, different self-correcting control strategies were set up. To validate the simulation and to test the quality of the self-correcting control strategies, a special experimental tool, mapping the most important bending operations, was constructed at the University of Paderborn. The experimental tool is equipped with an additional measurement device and can be operated on a universal testing machine. Finally, the self-correcting control strategies were tested under production conditions on the original tool in order to take any additional influences of the punch-bending machine into consideration. In this paper, recent investigations are presented that were conducted in a collaborative project at the University of Paderborn together with two industrial partners. The results of the correlation between the variables governing the process, the development of a suitable measurement method, and a first approach to a self-correcting control strategy are set out.
