Increased Reliability of Draw-In Prediction in a Single Stage Deep-Drawing Operation via Transfer Learning

Publikation: Beiträge in ZeitschriftenKonferenzaufsätze in FachzeitschriftenForschungbegutachtet

Authors

In sheet metal forming operations, finite element simulations and experimental works are used to evaluate predictions on different parameter settings. During the manufacturing process, there often exists a discrepancy of expected outcomes due to varying material properties. With the aim to save simulation and experimental resources, this paper provides a reliable transfer learning model suiting the deep-drawing case, where a model is pre-trained on simulation data, neurons are frozen in different layers and is then fine-tuned on real data. This model is evaluated in its behavior by gradually learning on different number of real data points as well as simulation data points.
OriginalspracheEnglisch
ZeitschriftProcedia CIRP
Jahrgang130
Seiten (von - bis)270-275
Anzahl der Seiten6
ISSN2212-8271
DOIs
PublikationsstatusErschienen - 01.01.2024
Veranstaltung57th CIRP Conference on Manufacturing Systems - CIRP CMS 2024: Speeding up manufacturing - Universität Minho, Póvoa de Varzim , Portugal
Dauer: 29.05.202431.05.2024
Konferenznummer: 57
https://www.cirpcms2024.org/

Bibliographische Notiz

Publisher Copyright:
© 2024 The Authors.

DOI

Zuletzt angesehen

Publikationen

  1. Steering of land use in the context of sustainable development
  2. Diversity Management and Corporate Change: Implications for Co-Determination
  3. Obtaining Object Information from Stereo Vision System for Autonomous Vehicles
  4. Rethinking Economic Practices and Values As Assemblages of More-Than-Human Relations
  5. The development of an eco-label for software products
  6. Dynamic Inversion-Enhanced U-Control of Quadrotor Trajectory Tracking
  7. Towards Computer Simulations of Virtue Ethics
  8. Exploring the Unknown
  9. A Multilab Replication of the Ego Depletion Effect
  10. DigiSchreib
  11. High-precision frequency measurements: indispensable tools at the core of the molecular-level analysis of complex systems.
  12. Using the Domestication Approach for the Analysis of Diffusion and Participation Processes of New Media
  13. Does modality play a role? Visual-verbal cognitive style and multimedia learning
  14. Development and characterisation of a new interface for coupling capillary LC with collision-cell ICPMS and its application for phosphorylation profiling of tryptic protein digests
  15. Assessing User Behavior by Mouse Movements
  16. Interactive sequential generative models for team sports
  17. Negotiation complexity
  18. Non-identity – So what? A political scientist’s perspective on a curious but somehow arbitrary problem
  19. Comparing two hybrid neural network models to predict real-world bus travel time
  20. Landscape models for use in studies of landscape change and habitat fragmentation
  21. A four-component classification of uncertainties in biological invasions: implications for management
  22. Mapping industrial patterns in spatial agglomeration
  23. Accuracy Improvement by Artificial Neural Networks in Technical Vision System
  24. Model-based Analysis of Reassembly Processes within the Regeneration of Complex Capital Goods
  25. Personalization strategies in digital mental health interventions: a systematic review and conceptual framework for depressive symptoms
  26. Prothesen, Aufschreibesysteme, Cyborgs
  27. Cobalt in end-of-life products in the EU, where does it end up? - The MaTrace approach
  28. Learning Online: A Comparison of Different Media Types
  29. On the Equivalence of Transmission Problems in Nonoverlapping Domain Decomposition Methods for Quasilinear PDEs
  30. What is a Digital Object?
  31. TANGO: A reliable, open-source, browser-based task to assess individual differences in gaze understanding in 3 to 5-year-old children and adults
  32. The Transition to Renewable Energy Systems - On the Way to a Comprehensive Transition Concept