Project Details
Projekt
DatProForge - Data-driven process modelling of closed-die forging processes to increase productivity using adaptive tool design methodology
Subject Area
Primary Shaping and Reshaping Technology, Additive Manufacturing
Term
since 2023
Project identifier
Deutsche Forschungsgemeinschaft (DFG) - Project number 520194997
Current trends in forming technology show an increasing degree of automation and an increasing demand for the geometric accuracy of the forgings. Numerical calculations enable the optimisation of the forming process and a significant improvement of the technology even before technological testing. The current state of research shows that analytical and numerical models can be used to model not only the forging process but also the static and dynamic behaviour of the press, which in turn also has an influence on the component quality. For example, even a deterministic or stochastic deviation from the ideal insertion position of the blank has a significant influence on the quality of the forging, the speed profile of the bear, and the local contact pressure. Also, it is known that the process resilience is affected by small changes in the surface of the die. The aim of the research project is to develop a basic understanding of the interaction between changes in measurement data (pattern recognition, as a result of deliberately altered process conditions) and the die face design in drop forging (e.g., inclined angle or die pitch) on product quality in continuous operation. AI methods are to be used to design the effective surfaces in the forging process in such a way that the component scrap rate is significantly reduced with regard to deterministic and stochastic effects. In the digitisation of the forging process, velocity measurement is crucial in addition to temperature measurement. For this purpose, direct velocity measurement by means of radar technology is used. In contrast to previous investigations, patterns and features are generated with the help of simulations and expert knowledge, which can then be identified in the measurement data. This enables the development of artificial intelligence that will later help in the development of new tools. The AI will use data from an endurance test sensor network in which speed measurement via 120 GHz radars is integrated into a forming system for the first time. A cloud fog edge data processing approach will be used for the measurement and simulation data. The identified patterns and features will be applied in conjunction with AI in such a way that it improves the service life of the forming surfaces. In the first funding period (1st FOP), the experimental conditions for single- and multi-stage forming processes with cyclic loading and unloading of the die knitting surfaces will be created, which will enable the digitisation of the forming process in a continuous run. In comprehensible reference data sets and data from endurance tests, the process measurement data is finally broken down into short- and long-term process uncertainties. With the completion of the first FOP, both initial characteristics and patterns have been identified, and data spaces for measurements and simulations have been defined.
DFG Programme
Priority Programmes
Co-Investigator
Professor Dr.-Ing. Johannes Buhl
