Learning process adaptation for tool grinding

• Applicant: Professor Dr.-Ing. Berend Denkena
• Subject Area: Metal-Cutting and Abrasive Manufacturing Engineering
• Term: from 2020 to 2023
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 445811009

• Final Report Year: 2024

Final Report Abstract

The grinding of shank tools requires comprehensive process knowledge in order to produce the increasingly complex geometries of the tools within the required tolerances. A well-known problem in the production of twist drills is the displacement of the workpieces by the grinding wheel during flute grinding. In this project, the resulting dimensional deviations were compensated for by an automated process adaptation based on a process-parallel material removal simulation. Empirical and numerical models of the relationship between process input variables and output variables such as dimensional deviation and surface roughness were developed for this purpose. Another result is automated modelling based on segmented data sets in order to incorporate new materials and tools into self-learning models. Finally, a method for optimizing surface roughness and production time was developed and researched, whereby the adapted grinding pathway minimizes the dimensional deviation.

Publications

• Optimierte Prozessplanung durch digitale Zwillinge für das Werkzeugschleifen. Schweizer Schleifsymposium 2022 (06.- 07.09.2022, Zürich, Schweiz).
  Denkena, B.; Wichmann, M. & Wulf, M.
  
• Revolutionäres Werkzeugschleifen dank digitalem Zwilling. Diamond Business, 82(3), 26-28.
  Denkena, B.; Wichmann, M. & Wulf, M.
  
• Clustering methods to model complex relations in tool grinding processes. CIRP General Assembly STC G, Dublin (IRL), 20.- 26.08.2023.
  Denkena, B.; Wichmann, M. & Wulf, M.
  
• Sensorfreie Kraftmessung beim Werkzeugschleifen, VDI-Z, 165 (4), (56-58).
  Denkena, B., Wichmann, M. & Wulf, M.
  
• Wie Maschinen von uns lernen können. In Neues von der Mensch-Maschine-Schnittstelle. WGP-Newsletter 2023(2).
  Denkena, B., Wichmann, M. & Wulf, M.
  
• Clustering of Learning Sub-models for Quality Prediction in a Resource-Efficient Tool Grinding Process. Production at the Leading Edge of Technology, 94–103.
  Denkena, Berend; Wichmann, Marcel & Wulf, Michael
  
• Tool Grinding of Drills with various Diamond Grinding Wheels and Tungsten Carbide Materials. Mendeley Data, V. 3
  Denkena, B.; Wichmann, M. & Wulf, M.