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

Research output: Journal contributionsConference article in journalResearchpeer-review

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.
Original languageEnglish
JournalProcedia CIRP
Volume130
Pages (from-to)270-275
Number of pages6
ISSN2212-8271
DOIs
Publication statusPublished - 01.01.2024
Event57th CIRP Conference on Manufacturing Systems - CIRP CMS 2024: Speeding up manufacturing - Universität Minho, Póvoa de Varzim , Portugal
Duration: 29.05.202431.05.2024
Conference number: 57
https://www.cirpcms2024.org/

Bibliographical note

Publisher Copyright:
© 2024 The Authors.

    Research areas

  • Artificial Intelligence, Machine Learning, Artificial neural network, Transfer Learning, Industrial applications, Deep-drawing
  • Engineering

Recently viewed

Publications

  1. Mechanical behavior, microstructural evolution and texture analysis of AA2024-T351 processed by multi-layer friction surfacing with high build rates
  2. Effect of silicon content on hot working, processing maps, and microstructural evolution of cast TX32-0.4Al magnesium alloy
  3. Mechanistic Realization of the Turtle Shell
  4. Hybrid modelling by machine learning corrections of analytical model predictions towards high-fidelity simulation solutions
  5. How difficult is the adaptation of POS taggers?
  6. Intellectual Property Issues in Space Contracts
  7. Learning how to request using textbooks
  8. Spaces with a temper
  9. Do connectives improve the level of understandability in mathematical reality-based tasks?
  10. Temperature control in Peltier cells comparing sliding mode control and PID controllers
  11. Interplays between relational and instrumental values
  12. Comparison of modeling approaches based on the microstructure of thermally sprayed coatings
  13. rSOESGOPE Method Applied to Four-Tank System Modeling
  14. Non-invariance? An Overstated Problem With Misconceived Causes
  15. Analytics and Intuition in the Process of Selecting Talent
  16. Using rating scales for the assessment of physical self-concept
  17. Principled Interpolation in Normalizing Flows
  18. Learning with summaries
  19. Facing Up to Third Party Liability for Space Activities
  20. Extraterritorial Asylum Processing. The Libya-Niger Emergency Transit Mechanism
  21. Comparison of Backpropagation and Kalman Filter-based Training for Neural Networks
  22. How much can we learn about voluntary climate action from behavior in public goods games?
  23. A dynamic perspective on affect and creativity
  24. Investigating Factors on R estorative Sleep Quality and its Relationship with Personal Work Performance - An Analysis of Diary Data
  25. An introduction to sliding mode control for interdisciplinary education
  26. Leaf trait variation within individuals mediates the relationship between tree species richness and productivity
  27. Sustainability-oriented technology exploration: managerial values, ambidextrous design, and separation drift
  28. Norms and variation in L2 pragmatics
  29. Determinants in the online distribution of digital content
  30. Modeling of 3D fluid-structure-interaction during in-situ hybridization of double-curved fiber-metal-laminates
  31. Co-production of nature's contributions to people
  32. Out of the box
  33. Logistische Lageranalyse und Methodenvalidierung