RWTH Aachen University (RWTH)

Consultancy : Research : Academic

Website | Video

Aachen, North Rhine-Westphalia, Germany

The mission of the Chair of Production Engineering is to drive business development in industry from the perspective of continuous productivity increases. Digital solutions and business models are developed to ensure sustainable production. A particular strength lies in the close connection between engineering and business research. At the Chair of Manufacturing Technology, we research numerous manufacturing technologies and jointly design the digitally networked, sustainable production of the future. The digital twin - a virtual image of the component based on manufacturing data and a wide variety of models and simulations - plays a decisive role in this. The Chair of Machine Tools deals with the design, investigation and optimization of machine elements that are combined into mechatronic systems. The chair also focuses on intelligent control and automation concepts based on the Internet of Production. By linking process data with models, a detailed digital image of the component, machine and process can be generated.

Assembly Line

Transfer learning with artificial neural networks between injection molding processes and different polymer materials


Authors: Yannik Lockner, Christian Hopmann, Weibo Zhao

Topics: artificial intelligence, machine learning

Vertical: Plastics and Rubber

Organizations: RWTH Aachen University

Finding appropriate machine setting parameters in injection molding remains a difficult task due to the highly nonlinear process behavior. Artificial neural networks are a well-suited machine learning method for modelling injection molding processes, however, it is costly and therefore industrially unattractive to generate a sufficient amount of process samples for model training. Therefore, transfer learning is proposed as an approach to reuse already collected data from different processes to supplement a small training data set. Process simulations for the same part and 60 different materials of 6 different polymer classes are generated by design of experiments. After feature selection and hyperparameter optimization, finetuning as transfer learning technique is proposed to adapt from one or more polymer classes to an unknown one. The results illustrate a higher model quality for small datasets and selective higher asymptotes for the transfer learning approach in comparison with the base approach.

Read more at ScienceDirect

Fields of action towards automated facility layout design and optimization in factory planning – A systematic literature review


Authors: Peter Burggräf, Tobias Adlon, Viviane Hahn, Timm Schulz-Isenbeck

Topics: facility design

Organizations: RWTH Aachen University, University of Siegen

The success of a factory planning project is significantly influenced by the layout design. It contributes to make the production process more economical and reliable. Studies show that an effective layout can reduce the operating costs of a factory by up to 30%.

Layout design is a very complex planning problem characterized by the conflict between competing goals and restrictions. Both quantitative goals, such as material flow, and qualitative goals, like communication and adaptability of a layout, must be taken into account. In addition, regulatory requirements and norms, which are the restrictions the design is based on, must also be met.

Despite the high complexity, the arrangement of the operational functional units is usually done manually, either on paper or with a digital layout design software. The layout variants are then evaluated by experts to identify the optimal layout.

Read more at ScienceDirect