Corrosion Prediction Approach Combining FEM‐Simulations and AI‐Modules for Complex Automotive Geometries
Source abstract
Abstract
ABSTRACT The necessity of corrosion protection significantly influences the development of automotive body‐in‐white assemblies. This paper presents a digital hybrid framework that enables early‐stage prediction of corrosion behavior in complex automotive geometries by combining physics‐based simulations with data‐driven artificial intelligence (AI) models. Validation on real vehicle components demonstrates high predictive accuracy, with correlation coefficients up to and the majority of results within a 30% deviation from experimental measurements. The approach thus provides a scalable and physically interpretable method for virtual corrosion evaluation, enabling data‐driven optimization of corrosion protection concepts in automotive design.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Structural Integrity and Reliability Analysis · Corrosion Behavior and Inhibition · Machine Learning in Materials Science
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Surface & Corrosion Protection Complete Vehicle Mercedes‐Benz AG Sindelfingen Germany
Chair of Methods for Model‐based Development in Computational Engineering RWTH Aachen Aachen Germany
Institute of Materials Engineering Technische Universität Bergakademie Freiberg Freiberg Germany
References (32)
Show source-provided references
1. M.Wünsche Numerische Korrosionssimulation von konstruktiven Schwachstellen für die industrielle Anwendung Dissertation. Technische Universität Dresden Dresden (2020).
2. 10.1016/j.corcom.2021.07.00110.1016/j.corcom.2021.07.001 ↗
3. 10.1016/j.porgcoat.2016.08.00310.1016/j.porgcoat.2016.08.003 ↗
4. 10.1016/j.porgcoat.2017.03.01610.1016/j.porgcoat.2017.03.016 ↗
5. 10.1016/j.porgcoat.2016.10.01010.1016/j.porgcoat.2016.10.010 ↗
6. 10.1002/maco.20181039210.1002/maco.201810392 ↗
7. 10.1016/j.porgcoat.2015.01.02310.1016/j.porgcoat.2015.01.023 ↗
8. K.Kapfer Untersuchung und Modellierung der Korrosion an Kanten und Flanschen unter unterschiedlichen Klimabedingungen und räumlichen Anordnungen. PhD thesis. Technische Universität Bergakademie Freiberg https://nbn‐resolving.org/urn:nbn:de:bsz:105‐qucosa2‐826936.
9. 10.1002/maco.20181020910.1002/maco.201810209 ↗
10. 10.1002/maco.20181021010.1002/maco.201810210 ↗
11. 10.1149/1.278924010.1149/1.2789240 ↗
12. 10.1016/j.corsci.2008.07.00510.1016/j.corsci.2008.07.005 ↗
13. 10.1002/maco.20211263610.1002/maco.202112636 ↗
14. 10.1016/j.corsci.2010.06.03110.1016/j.corsci.2010.06.031 ↗
15. 10.1002/maco.20090542510.1002/maco.200905425 ↗
16. 10.5006/129810.5006/1298 ↗
17. 10.5006/1.328051410.5006/1.3280514 ↗
18. 10.1016/j.corsci.2025.11289810.1016/j.corsci.2025.112898 ↗
19. 10.5006/1.328079010.5006/1.3280790 ↗
20. 10.1038/s41529‐022‐00218‐410.1038/s41529‐022‐00218‐4 ↗
21. 10.1007/s11837‐021‐04701‐210.1007/s11837‐021‐04701‐2 ↗
22. L.Waibel Segmentierung und Bewertung korrosionskritischer Konstruktionen einer Gesamtfahrzeugstruktur mittels Methoden der künstlichen Intelligenz. PhD Thesis. Universität Ulm (2022).
23. vda. 239‐100. Sheet Steel for Cold Forming (2016).
24. 10.1038/s41529‐022‐00316‐310.1038/s41529‐022‐00316‐3 ↗
25. 10.1016/j.electacta.2016.04.07210.1016/j.electacta.2016.04.072 ↗
26. 10.2320/matertrans.m201501610.2320/matertrans.m2015016 ↗
27. 10.1016/j.corsci.2017.10.01710.1016/j.corsci.2017.10.017 ↗
28. 10.1002/maco.20201213410.1002/maco.202012134 ↗
29. M.Gollé‐Leidreiter K.Kapfer A.Mittelbach andJ.Kowalski “AI‐Based Segmentation for Corrosion Risk Prediction in Carline Designs ”Materials and Corrosion76 no.3(2025):386–397.https://doi.org/10.1002/maco.202414622.10.1002/maco.202414622 ↗
30. 10.4271/05‐13‐02‐001310.4271/05‐13‐02‐0013 ↗
31. 10.1002/maco.20211263710.1002/maco.202112637 ↗
32. MathWorks. “Design Time Series NARX Feedback Neural Networks ” Accessed: 2025‐06‐13 https://de.mathworks.com/help/deeplearning/ug/design‐time‐series‐narx‐feedback‐neural‐networks.html.