Fraunhofer-Institut für Produktionsanlagen und Konstruktionstechnik IPK

Filters

2 1
Reset filters

Settings
Now showing 1 - 3 of 3
  • Publication
    Schweißen unter Zug - LME-Eingangsprüfung für die Autoindustrie
    ( 2021)
    El-Sari, Bassel
    ;
    Biegler, Max
    ;
    Rethmeier, Michael
    Der Trend zum Leichtbau und die Transformation zur E-Mobilität in der Automobilindustrie befeuern die Entwicklung neuer hochfester Stähle für den Karosseriebau. Derartige Werkstoffe sind beim Widerstandspunktschweißen besonders rissanfällig (LME). Das Schweißen unter Zug stellt eine effektive Methode um die LME-Anfälligkeit unterschiedlicher Werkstoffe qualitativ zu bestimmen.
  • Publication
    Investigation of the Extrapolation Capability of an Artificial Neural Network Algorithm in Combination with Process Signals in Resistance Spot Welding of Advanced High-Strength Steels
    ( 2021)
    El-Sari, Bassel
    ;
    Biegler, Max
    ;
    Rethmeier, Michael
    Resistance spot welding is an established joining process for the production of safety-relevant components in the automotive industry. Therefore, consecutive process monitoring is essential to meet the high quality requirements. Artificial neural networks can be used to evaluate the process parameters and signals, to ensure individual spot weld quality. The predictive accuracy of such algorithms depends on the provided training data set, and the prediction of untrained data is challenging. The aim of this paper was to investigate the extrapolation capability of a multi-layer perceptron model. That means, the predictive performance of the model was tested with data that clearly differed from the training data in terms of material and coating composition. Therefore, three multi-layer perceptron regression models were implemented to predict the nugget diameter from process data. The three models were able to predict the training datasets very well. The models, which were provided with features from the dynamic resistance curve predicted the new dataset better than the model with only process parameters. This study shows the beneficial influence of process signals on the predictive accuracy and robustness of artificial neural network algorithms. Especially, when predicting a data set from outside of the training space.
  • Publication
    Auf hohem Niveau: Anforderungen der Automobilindustrie an die Reinigungstechnik
    ( 2004)
    Rochowicz, M.
    ;
    Krieg, M.C.
    An moderne Automobilkomponenten werden extrem hohe Sauberkeitsanforderungen gestellt. Damit verbunden ist ein prinzipielles Umdenken: Reinigung ist nicht mehr ein notwendiges Übel, sondern entwickelt sich zu einem wertschöpfenden Prozess.