Author:
Liewald Mathias,Schenek Adrian,Deliktas Tahsin,Beck Maxim,Görz Marcel
Abstract
The Institute for Metal Forming Technology (IFU) at the University of Stuttgart / Germany since more than six years strongly strives to future oriented research work focusing on far-reaching concepts for digitization of metal forming processes. Main activities of engaged research groups are integrating sensors and actuators into metal forming machines or dies to analyse process data gained that way. Also, development of advanced methods for production data mining are related to those fields of activities. The paper therefore highlights strategies and practical applications of such digitization concepts. Also, important issues in terms of metal forming production processes will be addressed such as avoidance of scrap during ramp up phases and batch processing. Finally, the practical use of machine learning algorithms will be demonstrated in real trimming and metal forming processes.
Reference10 articles.
1. Deliktas T., Böhm J., Alba D., and Liewald M., ‘Digitization of cold extrusion pro- cesses using a combination of free-fall part monitoring with AI-controlled axial punch position’, in 42nd SENAFOR Conference, 2023.
2. Data-Driven Derivation of Sheet Metal Properties Gained from Punching Forces Using an Artificial Neural Network
3. Görz M., Schenek A., Liewald M., and Riedmüller K. R., ‘Evaluation of Feature Engi- neering Methods for the Prediction of Sheet Metal Properties from Punching Force Curves by an Artificial Neural Network’, 2023, pp. 75–85.
4. Tchasse P., Schenek A., Riedmüller K. R., and Liewald M., ‘Detection of Defective Deep Drawn Sheet Metal Parts by Using Machine Learning Methods for Image Classi- fication’, in Lecture Notes in Production Engineering, vol. Part F1764, 2024, pp. 84–93.
5. Application of a neural network for predicting cutting surface quality of punching processes based on tooling parameters