Using data mining techniques to investigate the correlation between surface cracks and flange lengths in deep drawn sheet metals

Research output: Journal contributionsConference article in journalResearchpeer-review

Authors

A problem during manufacturing of body parts in the automobile industry is the frequent occurrence of surface cracks in sheet metal cold forming processes. In this paper, we compare different supervised data mining techniques to predict cracks in deep-drawn sheet metals using their flange lengths as correlating features. Inline images of sheet metals are taken during the deep drawing process through cameras that are installed in every stage of a six-stage press line. A commercial software is used to label the images as defective and non-defective. Additionally, flange lengths, which generally correlate with forces set at the machines, are measured along the periphery of the sheets. The results are promising, as the models achieved satisfactory accuracy rates, albeit with some margin for improvement. This paper aims to choose a binary classification algorithm that is best suitable for the given dataset. Furthermore, the results provide an insight on the correlation of flange lengths with the occurrence of cracks, which can be used for online parameter adjustments of the machines in the future.

Original languageEnglish
JournalIFAC-PapersOnLine
Volume52
Issue number13
Pages (from-to)851-856
Number of pages6
ISSN2405-8971
DOIs
Publication statusPublished - 01.09.2019
Event9th International Federation of Automatic Control Conference on Manufacturing Modelling, Management and Control - 2019: Digital, Resilient and Sustainable Manufacturing 4.0 - Berlin, Germany
Duration: 28.08.201930.08.2019
Conference number: 9
https://blog.hwr-berlin.de/mim2019/

    Research areas

  • Classifier evaluation, Cold forming, Computer vision, Data mining, Deep drawing, Quality control, Surface inspection
  • Engineering

Recently viewed

Publications

  1. Duration of Organizational Decision Processes in Organizations in View of Simulation Calculations
  2. Backstepping-based Input-Output Linearization of a Peltier Element for Ice Clamping using an Unscented Kalman Filter
  3. Hybrid modelling by machine learning corrections of analytical model predictions towards high-fidelity simulation solutions
  4. The Dialectics of Open Access
  5. Experimentally established correlation of friction surfacing process temperature and deposit geometry
  6. Participatory energy scenario development as dramatic scripting
  7. Is implicit Theory of Mind real but hard to detect?
  8. Efficacy of an internet and app-based gratitude intervention in reducing repetitive negative thinking and mechanisms of change in the intervention's effect on anxiety and depression
  9. Material flow analysis between dynamic modelling and life cycle assessment
  10. Markups and Concentration in the Context of Digitization
  11. Internal forces in robotic manipulation and in general mechanisms using a geometric approach
  12. Getting down to specifics on RCA [Resource Consumption Accounting]
  13. A toolkit for robust risk assessment using F-divergences
  14. From Enterprise Architecture to Business Ecosystem Architecture
  15. Legitimizing Digital Transformation: From System Integration to Platformization
  16. Creating Value from in-Vehicle Data
  17. Modeling High Aswan Dam Reservoir Morphology Using Remote Sensing to Reduce Evaporation
  18. Effects of plyometric training on postural control in static and dynamic testing situations
  19. As cast microstructures on the mechanical and corrosion behaviour of ZK40 modified with Gd and Nd additions
  20. I share because of who I am: values, identities, norms, and attitudes explain sharing intentions
  21. Towards more effective and transferable transition experiments
  22. Foreword to applied data science, demo, and nectar tracks