Networking and digitization in manufacturing enable novel methods of data-driven analysis and optimization of processes through cross-process data availability. The creation of digital twins plays an important role in this. However, not all data relevant for a digital twin can be measured directly in the process. Therefore, methods are needed that enable the modelling of quantities that are difficult or impossible to measure directly in the process, such as the finite element method. In many companies, however, neither the know-how nor the necessary IT infrastructure for finite element simulations is available. External commissioning processes are also not suitable for achieving the goals of higher productivity and agility pursued with the digitization and networking of manufacturing processes. In this contribution, an architecture is presented that enables the fully automated use of finite element simulation as a service. The architecture is developed using the case study of fine blanking. First, the requirements of the architecture to be created are determined. Important characteristics of the architecture should be scalability as well as interfaces and means of payment suitable for machine communication. In addition, ensuring data integrity is an important requirement when creating the digital twin. Based on the identified requirements, an architecture is then presented that meets these requirements by using cloud computing and distributed ledger technologies and interfaces that can directly process measurement signals from the process and communicate with the architecture. Finally, the capability of the architecture is tested, possible applications and limitations are discussed, and future extensions are considered.

制造业中的网络和数字化通过跨过程数据可用性实现了数据驱动的分析和过程优化的新方法。数字双胞胎的创建在其中起着重要作用。但是，并非所有与数字双胞胎有关的数据都可以在此过程中直接测量。因此，需要能够对难以或不可能在过程中直接测量的数量进行建模的方法，例如有限元方法。但是，在许多公司中，既没有专有技术，也没有用于有限元模拟的必要IT基础结构。外部调试过程也不适合实现制造过程的数字化和网络化所追求的更高生产率和敏捷性的目标。在这项贡献中，提出了一种体系结构，该体系结构允许将有限元模拟作为服务完全自动化地使用。该架构是使用精细消隐的案例研究开发的。首先，确定要创建的体系结构的要求。该体系结构的重要特征应该是可伸缩性以及适用于机器通信的接口和付款方式。此外，在创建数字孪生模型时，确保数据完整性是一项重要要求。根据确定的要求，然后提出一种架构，该架构通过使用云计算和分布式分类帐技术以及可以直接处理来自过程的测量信号并与该架构通信的接口来满足这些要求。最后，测试架构的功能，