Mechanical performance prediction for friction riveting joints of dissimilar materials via machine learning

Publikation: Beiträge in ZeitschriftenKonferenzaufsätze in FachzeitschriftenForschungbegutachtet

Authors

Solid-state joining techniques have become increasingly attractive for joining similar and dissimilar materials because it enables further optimization of lightweight components. In contrast to fusion-based joining processes, solid-state joining prevents the occurrence of typical defects such as pores or hot cracking. Machine learning algorithms are powerful tools to identify and quantify relationships between essential features along the process-property chain. In particular, different supervised machine learning algorithms can be used to perform regression analyses and establish correlations between process parameters as well as resulting properties. This can help to circumvent the demand for conducting a vast number of additional experiments to determine optimized process parameters for desired material properties. Additionally, this knowledge can be utilized to obtain a deeper understanding of the underlying mechanisms. In this study, a number of regression algorithms, such as support vector machines, decision trees, random forest and 2nd-order polynomial regression have been applied to correlate process parameters and materials properties for the solid-state joining process of force-controlled friction riveting. Experimental data generated via a central-composite Design of Experiments, serves as source of two separate data sets: one for training and one for testing the machine learning algorithms. The performances of the different algorithms are evaluated based on the determination coefficient R2 and the standard deviation of the predictions on the test data set. The trained algorithms with the best performance measures can be used as predictive models to forecast specific influences of process parameters on mechanical properties. Through the application of these models, optimized process parameters can be determined that lead to desired properties.

OriginalspracheEnglisch
ZeitschriftProcedia Manufacturing
Jahrgang47
Seiten (von - bis)615-622
Anzahl der Seiten8
DOIs
PublikationsstatusErschienen - 05.2020
Veranstaltung23rd International Conference on Material Forming - 2020 - online, Cottbus, Deutschland
Dauer: 04.05.202008.05.2020
Konferenznummer: 23
https://esaform2020.org/

Bibliographische Notiz

The authors acknowledge funding from the Helmholtz-Association via an ERC-Recognition-Award (ERC-RA-0022).

Dokumente

DOI

Zuletzt angesehen

Presse / Medien

  1. Durch Kunst fair im Verkehr

Publikationen

  1. Kontext
  2. TACKLING THE GLOBAL WASTE PROBLEM AS A MULTI-LEVEL PROCESS
  3. A Systematic Literature Review Of Machine Learning Approaches For The Prediction Of Delivery Dates
  4. Modelling of a servo piezo mechanical hydraulic actuator and its feed-forward control
  5. Implicit processes in moral decision making: Why milliseconds matter
  6. The principle of unjust enrichment
  7. Institutional Proxy Representatives of Future Generations
  8. Phantasmal Spaces
  9. Essential ecosystem service variables for monitoring progress towards sustainability
  10. Union membership and age: the inverted u-shape hypothesis under test
  11. No-Code Platforms in Startups: Explaining Decisions for Adoption and Abandonment
  12. Quality based prevention of overweight in the school setting: the HEPS quality checklist
  13. Lernprotokollunterstütztes Lernen - ein Vergleich zwischen unstrukturiertem und systemkontrolliertem diskursivem Lernen im Netz
  14. Global networks & local partnerships
  15. Widening the evaluative space for ecosystem services
  16. Constellations of Transdisciplinary Practices: A Map and Research Agenda for the Responsible Management Learning Field
  17. On the measuring accuracy of the “Vehrs-Hebel”, a scaling apparatus for nonverbal real-time assessment of perceived quantity
  18. „Das ewig Dauernde in uns“. Immanenz und Transzendenz in Stifters Nachsommer
  19. Rudi Carrell
  20. Borders, Citizenship, War, Class
  21. Consumer preferences and willingness to pay for apples from agrivoltaics
  22. A journey worth taking
  23. “They Are Stumbling Around Quite Helplessly”: How Supporters of Refugee Families Frame Vulnerability and Agency Relating to Childcare
  24. Microstructural evolution and mechanical properties of Mg-11Gd-4.5Y-1Nd-1.5Zn-0.5Zr alloy prepared via pre-ageing and hot extrusion
  25. Von Joseph Ratzinger zu Papst Benedikt XVI
  26. Best practice for bio-waste collection as a prerequisite for high-quality compost
  27. Self-Control Following Prior Exertion
  28. Making education for sustainable development happen in elementary schools
  29. Ästhetische Bildung der Differenz