No abstract

The amount of information contained in process signals such as acoustic emission and force signals has proven vital for the detection of changes in physical conditions or quality feature prediction in sheet metal forming applications. Both signal types have also been researched in the context of wear detection, yet systems that reliably identify the wear state at a given time in sheet metal forming processes based on these signals do not exist. This paper proposes an architecture to assess the wear increase within a given time frame in an experiment based on an autoencoder. The ability of autoencoders to encode and decode signals has been widely studied and this approach leverages the fact that autoencoders are more likely to learn representative encodings on stable and homogeneous signals than on heterogeneous signals with high fluctuations. This approach utilizes the circumstance that high tool wear leads to changes in the signal and signal fluctuation. In consequence, autoencoders can be utilized to track tool wear progression without the need for labelled data. The findings show a strong similarity to physical models for the wear progression of tool components, indicating the validity of this approach. Additionally, an analysis of the signals yields characteristic effects of the considered force signals that could specifically represent wear resistance.

No abstract

The process setup of manufacturing processes is generally knowledge-based and carried out once for a material batch. Industry experts observe fluctuations in product quality and tool life, albeit the process setup remains unchanged. These fluctuations are mainly attributed to fluctuations in material parameters. An in-situ detection of changes in material parameters would enable manufacturers to adapt process parameters like forces or lubrication before turbulences like unexpectedly high tool wear or degradation in product quality occurs. This contribution shows the applicability of a deep learning time series classification architecture that does not rely on handcrafted feature engineering for the classification of hardness fluctuations in a sheet-metal coil using magnetic Barkhausen noise emission. This methodology is not limited to the detection of hardness fluctuations in sheet-metal coils and can potentially be applied for the in-situ material property classification in different manufacturing processes and for different material parameters.

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.