Redirecting to http://dergipark.org.tr/_fragment?_hash=uE9W3mxUAbDjrpU70RaUMlUcDMgfM-0TzvqUFD9dPKM&_path=id%3D1550230%26_format%3Dhtml%26_locale%3Den%26_controller%3DApp%255CController%255CSite%255CArticleController%253A%253AesiArticleStats.
Conference Paper
BibTex RIS Cite

Real-Time Detection of Cracks During Dynamic Testing of Sheet Metals Used in Automotive Suspension Systems

Year 2024, Volume: 29, 61 - 68, 30.09.2024

Mehmet Emin Ors Ziya Ozcelik

https://doi.org/10.55549/epstem.1550230

Abstract

Dynamic testing is crucial in the automotive industry for ensuring vehicle safety and performance, particularly in assessing the durability and reliability of front-end and suspension systems. Traditional real-time crack detection methods, which are often manual and time-consuming, face limitations in accuracy and reliability. This study explores the application of deep learning techniques to enhance real-time crack detection during dynamic testing, offering a modern solution to these challenges. The research involves the collection and processing of IP camera data, followed by model training using various deep learning algorithms. The study details how these algorithms are employed to improve the detection and prediction of cracks, providing a systematic approach to overcoming the shortcomings of traditional methods. The deep learning models developed in this research were tested against real-world data, showing significantly higher accuracy in realtime crack detection compared to conventional techniques. The findings indicate that deep learning-based approaches not only improve the precision of real-time crack detection but also contribute to more efficient and effective testing processes in the automotive industry. This research offers a promising direction for future studies and practical applications, suggesting that deep learning can significantly enhance the reliability of dynamic testing. In conclusion, this study highlights the potential of deep learning to transform real time realtime crack detection in the automotive industry, providing a more accurate, reliable, and scalable solution. The results serve as a valuable reference for both academic research and industrial practices, paving the way for further advancements in automotive testing through the integration of artificial intelligence.

Keywords

Deep learning Sheet metal real-time crack detection Automotive industry

References

  • Ors, M. E. & Ozcelik, Z. (2024). Real-time detection of cracks during dynamic testing of sheet metals used in automotive suspension systems. The Eurasia Proceedings of Science, Technology, Engineering & Mathematics (EPSTEM), 29, 61-68.

Year 2024, Volume: 29, 61 - 68, 30.09.2024

Mehmet Emin Ors Ziya Ozcelik

https://doi.org/10.55549/epstem.1550230

Abstract

References

  • Ors, M. E. & Ozcelik, Z. (2024). Real-time detection of cracks during dynamic testing of sheet metals used in automotive suspension systems. The Eurasia Proceedings of Science, Technology, Engineering & Mathematics (EPSTEM), 29, 61-68.
There are 1 citations in total.

Details

Primary Language English
Subjects Electronics, Sensors and Digital Hardware (Other)
Journal Section Articles
Authors

Mehmet Emin Ors

Ziya Ozcelik

Early Pub Date September 15, 2024
Publication Date September 30, 2024
Submission Date February 5, 2024
Acceptance Date March 19, 2024
Published in Issue Year 2024 Volume: 29

Cite

APA Ors, M. E., & Ozcelik, Z. (2024). Real-Time Detection of Cracks During Dynamic Testing of Sheet Metals Used in Automotive Suspension Systems. The Eurasia Proceedings of Science Technology Engineering and Mathematics, 29, 61-68. https://doi.org/10.55549/epstem.1550230
Creative Commons License