The press plants of the future will have networked processes that run automatically and are supported by intelligent algorithms. With sensors and the expansion of interfaces, quality parameters can be recorded for each component and monitored during the process. Controllable parameters can then be individually adjusted and stored in a verifiable manner. In this way, an individual dataset is created for each component, in which all process parameters are automatically saved. This ensures the traceability of production and supports the diagnosis of malfunctions, the preventive maintenance of systems and the quality assurance of the parts produced. This also reduces rejections, increase resource efficiency and ultimately saves costs. Using machine learning, relationships between process parameters can be revealed and parameters can be automatically adjusted. Furthermore, machine-learned algorithms such as predictive maintenance concepts can contribute to a further optimization of the processes.