Perspectives on data-driven models and its potentials in metal forming and blanking technologies

Abstract

Today, design and operation of manufacturing processes heavily rely on the use of models, some analytical, empirical or numerical i.e. finite element simulations. Models do reflect reality as best as their design and structure may appear, but in many cases, they are based on simplifying assumptions and abstractions. Reality in production, i.e. reflected by measures such as forces, deflections, travels, vibrations etc. during the process execution, is tremendously characterised by noise and fluctuations revealing a stochastic nature. In metal forming such kind of impact on produced product today in detail is neither explainable nor supported by the aforementioned models. In industrial manufacturing the game to deal with process data changed completely and engineers learned to value the high significance of information included in such digital signals. It should be acknowledged that process data gained from real process environments in many cases contain plenty of technological information, which may lead to increase efficiency of production, to reduce downtime or to avoid scrap. For this reason, authors started to focus on process data gained from numerous metal forming technologies and sheet metal blanking in order to use them for process design objectives. The supporting idea was found in a potential combination of conventional process design strategies with new models purely based on digital signals captured by sensors, actuators and production equipment in general. To utilise established models combined with process data, the following obstacles have to be addressed: (1) acquired process data is biased by sensor artifacts and often lacks data quality requirements; (2) mathematical models such as neural networks heavily rely on high quantities of training data with good quality and sufficient context, but such quantities often are not available or impossible to gain; (3) data-driven black-box models often lack interpretability of containing results, further opposing difficulties to assess their plausibility and extract new knowledge. In this paper, an insight on usage of available data science methods like feature-engineering and clustering on metal forming and blanking process data is presented. Therefore, the paper is complemented with recent approaches of data-driven models and methods for capturing, revealing and explaining previously invisible process interactions. In addition, authors follow with descriptions about recent findings and current challenges of four practical use cases taken from different domains in metal forming and blanking. Finally, authors present and discuss a structure for data-driven process modelling as an approach to extent existing data-driven models and derive process knowledge from process data objecting a robust metal forming system design. The paper also aims to figure out future demands in research in this challenging field of increasing robustness for such kind of manufacturing processes.

Evolving the Digital Industrial Infrastructure for Production: Steps Taken and the Road Ahead

“…The incorporation of domain knowledge at the edge is crucial, since the sooner the data is preprocessed and labeled in a domainspecific way, the less redundant or irrelevant information needs to be passed on. Note, however, that a purely human-based method of preprocessing for knowledge may neglect important unknown effects (Liewald et al 2022). Thus, edge-based preprocessing pipelines need to incorporate domain knowledge-based approaches into data-driven approaches to fully leverage the power of edge systems.…”

Towards a real-time tool state detection in sheet metal forming processes validated by wear classification during blanking

“…Klingenberg and de Boer extracted a feature describing the length of the punch penetration into the sheet until the maximum force is reached, as well as the work done in the punch phase, and correlated them with the rounding of the cutting edge [27]. A similar approach was chosen by Kubik et al, who extracted four features from the force signal and correlated them with the cutting edge radii of the punch [3,28].…”

Hardness Assessment Considering Nitrided Layers Based on Tempering Tests for Numerical Wear Prediction for Forging Processes

“…Following the stroke influence investigation, it is obvious that similar process variations, such as the billet temperature of the component, which in turn significantly influence the yield stress, lead to a direct influence on the wear. Based on this finding, the authors, together with other scientists of the German Academic Association for Production Technology (WGP), participated in a memorandum for further research on (process) data-based models for the prediction of issues that could not previously be described analytically [ 33 ]. In the context of further work, the aim is to generate a broad database of process-relevant data (e.g., various temperatures, press force and timings) for a variety of forging conditions, to be able to map the processes not only on the basis of FE simulations but also on the basis of process-data-based models.…”