The paper examines how artificial intelligence can be used to predict forming effects in sheet metal forming processes more accurately and quickly. The focus is on the use of data-driven models that can complement or partially replace classical numerical simulations, in particular finite element methods. The goal is to predict process quantities such as forces, geometric deviations, or potential defects early and efficiently.

It is shown that modern machine learning approaches offer great potential, especially for complex or time-critical manufacturing processes. By combining experimental data, process monitoring, and AI models, development times can be shortened, simulation effort reduced, and process reliability improved. Thus, the work contributes to a central trend in modern manufacturing engineering: the intelligent, data-driven optimization of forming processes.