Computer Graphics
TU Braunschweig

Dreaming Neural Networks for Adaptive Polishing


Dreaming Neural Networks for Adaptive Polishing

Mechanical polishing is an important step within the process chain of manufacturing workpieces with high requirements regarding the surface quality, e.g. for optical components. The resulting surface quality depends on several parameters, e.g. the process parameters, the workpiece material, the initial surface roughness and the tool condition. Thus, finding process parameters that lead to the desired surface roughness can be regarded as a complex optimization problem. For this purpose, an artificial neural network (ANN) has been designed and trained with data from polishing experiments. Using a dreaming network approach, the ANN has been enabled to suggest appropriate process parameters under consideration of the initial roughness of the workpiece and the tool condition. The validation experiments showed that the process parameters suggested by the neural network led in 72% to the target roughness within a standard deviation.


Author(s):Marc-André Dittrich, Bodo Rosenhahn, Marcus Magnor, Berend Denkena, Talash Malek, Marco Munderloh, Marc Kassubeck
Published:June 2020
Type:Article in conference proceedings
Book:Proc. Int. Conf. European Society for Precision Engineering and Nanotechnology (euspen) (euspen)
Presented at:International Conference & Exhibition European Society for Precision Engineering and Nanotechnology (EUSPEN) 2020
Project(s): Physical Parameter Estimation from Images 


@inproceedings{dittrich2020dreaming,
  title = {Dreaming Neural Networks for Adaptive Polishing},
  author = {Dittrich, Marc-Andr{\'e} and Rosenhahn, Bodo and Magnor, Marcus and Denkena, Berend and Malek, Talash and Munderloh, Marco and Kassubeck, Marc},
  booktitle = {Proc. Int. Conf. European Society for Precision Engineering and Nanotechnology (euspen)},
  pages = {263--266},
  month = {Jun},
  year = {2020}
}

Authors