Fraunhofer-Institut für Produktionsanlagen und Konstruktionstechnik IPK

Filters

2
2
Reset filters

Settings
Now showing 1 - 2 of 2
  • Publication
    Transferability of ANN-generated parameter sets from welding tracks to 3D-geometries in Directed Energy Deposition
    ( 2022-11-04)
    Marko, Angelina
    ;
    Bähring, Stefan
    ;
    Raute, Maximilian Julius
    ;
    Biegler, Max
    ;
    Rethmeier, Michael
    Directed energy deposition (DED) has been in industrial use as a coating process for many years. Modern applications include the repair of existing components and additive manufacturing. The main advantages of DED are high deposition rates and low energy input. However, the process is influenced by a variety of parameters affecting the component quality. Artificial neural networks (ANNs) offer the possibility of mapping complex processes such as DED. They can serve as a tool for predicting optimal process parameters and quality characteristics. Previous research only refers to weld beads: a transferability to additively manufactured three-dimensional components has not been investigated. In the context of this work, an ANN is generated based on 86 weld beads. Quality categories (poor, medium, and good) are chosen as target variables to combine several quality features. The applicability of this categorization compared to conventional characteristics is discussed in detail. The ANN predicts the quality category of weld beads with an average accuracy of 81.5%. Two randomly generated parameter sets predicted as “good” by the network are then used to build tracks, coatings, walls, and cubes. It is shown that ANN trained with weld beads are suitable for complex parameter predictions in a limited way.
  • Publication
    Hyperparameter Optimization of Artificial Neural Networks to Improve the Positional Accuracy of Industrial Robots
    ( 2021)
    Uhlmann, Eckart
    ;
    Polte, Mitchel
    ;
    Blumberg, Julian
    ;
    Li, Zhoulong
    ;
    Kraft, Adrian
    Due to the rising demand for individualized product specifications and short innovation cycles, industrial robots gain increasing attention for machining operations as milling and forming. Limitations in their absolute positional accuracy are addressed by enhanced modelling and calibration techniques. However, the resulting absolute positional accuracy stays in a range still not feasible for general purpose milling and forming tolerances. Improvements of the model accuracy demand complex, often not accessible system knowledge on the expense of realtime capability. This article presents a new approach using artificial neural networks to enhance positional accuracy of industrial robots. A hyperparameter optimization is applied, to overcome the downside of choosing an appropriate artificial neural network structure and training strategy in a trial and error procedure. The effectiveness of the method is validated with a heavy-duty industrial robot. It is demonstrated that artificial neural networks with suitable hyperparameters outperform a kinematic model with calibrated geometric parameters.