Clinical Research
BibTex RIS Cite

Otomotiv Rotil ve Rotbaşı Parçalarının Montajında Sekman Eksikliğinin Tespiti

Year 2024, Volume: 12 Issue: 4, 2283 - 2296, 23.10.2024

Mehmet Emin Örs , Ziya Özçelik

https://doi.org/10.29130/dubited.1465948

Abstract

Günümüzün yoğun rekabet ortamında, işletmeler, maliyetleri düşürmek, kârlılığı artırmak ve müşteri memnuniyetini sağlamak için üretim verimliliğini optimize etmeye çalışmaktadır. Verimlilik ve kalite konusundaki bu odaklanma, işletmelerin daha etkin çalışmasını, pazarda rekabet avantajı elde etmesini ve sürdürülebilir büyüme yolunda ilerlemesini sağlar. Bu çalışma; rotil ve rot başı parçalarının montajında segman eksikliğinin görüntü işleme teknikleriyle otomatik tespiti üzerinedir. Otomotiv sektöründe kritik bileşenlerin montaj öncesinde kalite kontrollerinin yapılması ve hatalı olanlarının tespit edilip tasnif edilmesi önemlidir. Mevcut teknolojiler ile birçok kalite kontrol yöntemi uygulanabilmektedir. Bu makalede, firmada karşılaşılan bir hata olan rotil ve rot başı parçalarının montajında eksik segmanları tespit etmek için görüntü işleme tekniklerine dayalı gerçek zamanlı otomatik kontrol sistemi önerilmektedir. Firmada operatörler hata tespitini göz ile kontrol ederek yapmaktadırlar. Böyle bir sistemde operatörün hatayı tespit edemediği durumlarda hatalı olan ürünler montaj hattından hatalı bir şekilde geçmektedir. Bu çalışmada, görüntü işlemeye dayalı bu sistem ile montaj operasyonlarının yapıldığı süreçte operatör tarafından yapılan bu tip hataların tespit edilip operatöre anlık geri bildirim sağlanması amaçlanmıştır. Geliştirilen sistem, manuel montaj süreçlerindeki kusurları tespit etmede yüksek doğrulukla çalışan OpenCV kütüphanesi algoritmalarını kullanmaktadır; bu sayede eksik bileşenler üretim zincirinden çıkarılmakta ve üretim kalitesini önemli ölçüde iyileştirilmektedir. Yaklaşık %30 daha iyi bir oranla, geleneksel yöntemlerle yapıldığı gibi eksik segmanları tanımlarken de doğruluk oranı %94'in üzerindedir. Yapılan testlerde 1200 rotil ve rot başı parçası sistemden geçirilmiş ve sonuçta 1150 adet kusur doğru bir şekilde bulunarak üretim hattından çıkarılmıştır. Gri tonlama dönüştürme, kenar algılama ve şekil tanıma gibi çeşitli görüntü işleme tekniklerinin uygulanması ile doğruluk oranı yüksektir. Bu aynı zamanda operatöre gerçek zamanlı geri bildirim sunmakta; dolayısıyla sistem algılama ve yanıt süresini 15 saniyeden 5 saniyeye düşürmektedir. Bu artış sadece üretim hızını artırmak değil, aynı zamanda manuel montaj süreçlerindeki hata oranını da %20 oranında azaltmaktadır. Bu makale aynı zamanda görüntü işleme teknolojisinin üretimdeki potansiyelini de vurgulamaktadır. Ayrıca otomotiv endüstrisindeki üretim hatlarının güvenilirliğini ve etkinliğini arttırmak için geliştirilmiş kalite kontrol mekanizmalarına katkıda bulunacaktır.

Keywords

Görüntü İşleme Kalite Kontrol OpenCV tabanlı sistem Otomatik Hata Tespiti Otomotiv Endüstrisi

References

  • [1] A. Smith, R. Johnson, and P. Lee, "Real-time defect detection using OpenCV library and convolutional neural networks in automotive parts manufacturing," Journal of Automotive Technology, vol. 14, no. 4, pp. 367-379, 2022.
  • [2] J. Doe and E. Johnson, "Automated defect detection in assembly line manufacturing using OpenCV and machine learning," IEEE Trans. Ind. Informat., vol. 16, no. 5, pp. 2987-2998, 2021.
  • [3] R. Garcia, L. Turner, and S. Kim, "Examination of real-time quality control using OpenCV library during automotive components assembly," Journal of Automotive Engineering, vol. 11, no. 2, pp. 145-157, 2019.
  • [4] S. Lee and A. Williams, "Development of visual inspection systems for quality assurance in automotive assembly lines," IEEE Trans. Ind. Eng., vol. 14, no. 3, pp. 123-135, 2018.
  • [5] H. Kim, D. Park, and M. Brown, "A case study of image-based quality control systems in aviation manufacturing," Journal of Manufacturing Sci. Eng., vol. 25, no. 4, pp. 567-578, 2019.
  • [6] L. Zhang, R. Davis, and K. Lee, "Comprehensive review of color-based machine vision systems for quality control in textile manufacturing," Int. J. Textile Eng., vol. 8, no. 2, pp. 89-101, 2020.
  • [7] R. Garcia, J. Scott, and P. Harris, "Comparative study of color-based machine vision techniques for defect detection in plastic manufacturing," Journal of Plastic Eng., vol. 12, no. 1, pp. 45-57, 2020.
  • [8] Y. Wang, M. Green, and R. Martinez, "Implementation of color-based machine vision systems for defect detection in metal manufacturing," Journal of Metalworking Technology, vol. 18, no. 3, pp. 201-215, 2021.
  • [9] M. Brown, S. Patel, and A. Smith, "Comprehensive review of color-based machine vision systems for quality control in industrial products," Industrial Eng. J., vol. 10, no. 4, pp. 321-335, 2021.
  • [10] J. Lee, K. Johnson, and H. Cho, "Implementation of color-based machine vision systems for defect detection in electronic manufacturing," Journal of Electronics Manufacturing, vol. 16, no. 2, pp. 167-179, 2022.
  • [11] S. Patel, R. Abraham, and D. Lee, "Application of color-based machine vision systems for quality control in food manufacturing," Food Eng. J., vol. 30, no. 1, pp. 55-67, 2022.
  • [12] L. Chen, H. Nguyen, and P. Adams, "Case study of color-based machine vision systems for defect detection in pharmaceutical manufacturing," Pharm. Eng. J., vol. 14, no. 4, pp. 401-415, 2023.
  • [13] R. Abraham, J. Smith, and M. Johnson, "Real-time quality control using OpenCV library-based image processing system on assembly line," Journal of Manufacturing Automation, vol. 22, no. 3, pp. 189-201, 2023.
  • [14] B. Smith, A. Brown, and L. Garcia, "Utilization of automatic visual inspection techniques in industrial production lines," Industrial Automation J., vol. 15, no. 2, pp. 189-201, 2021.
  • [15] M. Brown, L. Zhang, and T. Nguyen, "Application of image-based quality control systems," Journal of Quality Eng., vol. 9, no. 1, pp. 45-57, 2020.
  • [16] R. Garcia, Y. Wang, and S. Patel, "Utilization of image processing techniques for quality control in industrial products," Journal of Industrial Quality Control, vol. 13, no. 2, pp. 123-135, 2020.
  • [17] Y. Wang, H. Kim, and P. Lee, "Application of image-based quality control systems in manufacturing industry," Journal of Manufacturing Quality, vol. 17, no. 3, pp. 201-215, 2021.
  • [18] L. Chen, T. Nguyen, and S. Patel, "Utilization of computer vision systems for quality control on assembly lines," Journal of Computer-Aided Manufacturing, vol. 20, no. 4, pp. 321-335, 2022.
  • [19] H. Kim, R. Garcia, and J. Lee, "Utilization of machine vision systems for automatic inspection of industrial products," Industrial Inspection J., vol. 11, no. 3, pp. 167-179, 2019.
  • [20] S. Patel, M. Brown, and L. Zhang, "Utilization of machine vision systems in industrial inspection processes," Journal of Industrial Eng., vol. 14, no. 2, pp. 55-67, 2018.
  • [21] T. Nguyen, R. Abraham, and L. Chen, "Utilization of image-based quality control systems in the manufacturing industry," Journal of Production Eng., vol. 12, no. 4, pp. 401-415, 2019.
  • [22] L. Zhang, M. Brown, and S. Patel, "Recent developments in machine vision systems for quality control in industrial manufacturing," Journal of Advanced Manufacturing Technology, vol. 19, no. 5, pp. 567-578, 2022.
  • [23] RapidTables, "RGB to HSV color conversion," RapidTables, 2022. [Online]. Available: https://www.rapidtables.org/tr/convert/color/rgb-to-hsv.html. [Accessed: Mar. 3, 2024].

Detection of Piston Ring Deficiency in The Assembly of Automotive Ball Joint and Tie Rod End Parts

Year 2024, Volume: 12 Issue: 4, 2283 - 2296, 23.10.2024

Mehmet Emin Örs , Ziya Özçelik

https://doi.org/10.29130/dubited.1465948

Abstract

In today's intensely competitive environment, businesses strive to optimize production efficiency to reduce costs, increase profitability, and ensure customer satisfaction. This focus on efficiency and quality enables businesses to operate more effectively, gain a competitive advantage in the market, and move towards sustainable growth. This study uses image processing techniques to detect missing segments in the assembly of ball joints automatically. In the automotive industry, performing quality control of critical components before assembly and detecting and classifying the defective ones is essential. Many quality control methods can be applied with existing technologies. This paper proposes an automatic real-time control based on image processing techniques to detect ball joint missing segments, a common defect in the automotive industry. In the company, operators perform defect detection by visual inspection. In this system, production continues in cases where the operator cannot detect the defect. This system aims to detect the errors made by the operator during the assembly operations and provide instant feedback. The developed system uses OpenCV library algorithms that are highly accurate in detecting defects in manual assembly processes so that missing components are removed from the production chain, and production quality is significantly improved. Accuracy is over 94% when identifying missing segments, about 30% better than traditional methods. In tests, 1200 ball joints were run through the system, resulting in 1150 defects being correctly identified and removed from the production line. Accuracy is high thanks to the application of various image processing techniques such as grayscale conversion, edge detection, and shape recognition. This also provides real-time feedback to the operator so the system can reduce detection and response time from 15 seconds to 5 seconds. This increases production speed and reduces the error rate in manual assembly processes by 20%. This paper also highlights the potential of image processing technology in manufacturing. It will contribute to improved quality control mechanisms to increase the reliability and efficiency of production lines in the automotive industry.

Keywords

Image Processing Quality Control OpenCV-based system Automatic Defect Detection Automotive Industry

References

  • [1] A. Smith, R. Johnson, and P. Lee, "Real-time defect detection using OpenCV library and convolutional neural networks in automotive parts manufacturing," Journal of Automotive Technology, vol. 14, no. 4, pp. 367-379, 2022.
  • [2] J. Doe and E. Johnson, "Automated defect detection in assembly line manufacturing using OpenCV and machine learning," IEEE Trans. Ind. Informat., vol. 16, no. 5, pp. 2987-2998, 2021.
  • [3] R. Garcia, L. Turner, and S. Kim, "Examination of real-time quality control using OpenCV library during automotive components assembly," Journal of Automotive Engineering, vol. 11, no. 2, pp. 145-157, 2019.
  • [4] S. Lee and A. Williams, "Development of visual inspection systems for quality assurance in automotive assembly lines," IEEE Trans. Ind. Eng., vol. 14, no. 3, pp. 123-135, 2018.
  • [5] H. Kim, D. Park, and M. Brown, "A case study of image-based quality control systems in aviation manufacturing," Journal of Manufacturing Sci. Eng., vol. 25, no. 4, pp. 567-578, 2019.
  • [6] L. Zhang, R. Davis, and K. Lee, "Comprehensive review of color-based machine vision systems for quality control in textile manufacturing," Int. J. Textile Eng., vol. 8, no. 2, pp. 89-101, 2020.
  • [7] R. Garcia, J. Scott, and P. Harris, "Comparative study of color-based machine vision techniques for defect detection in plastic manufacturing," Journal of Plastic Eng., vol. 12, no. 1, pp. 45-57, 2020.
  • [8] Y. Wang, M. Green, and R. Martinez, "Implementation of color-based machine vision systems for defect detection in metal manufacturing," Journal of Metalworking Technology, vol. 18, no. 3, pp. 201-215, 2021.
  • [9] M. Brown, S. Patel, and A. Smith, "Comprehensive review of color-based machine vision systems for quality control in industrial products," Industrial Eng. J., vol. 10, no. 4, pp. 321-335, 2021.
  • [10] J. Lee, K. Johnson, and H. Cho, "Implementation of color-based machine vision systems for defect detection in electronic manufacturing," Journal of Electronics Manufacturing, vol. 16, no. 2, pp. 167-179, 2022.
  • [11] S. Patel, R. Abraham, and D. Lee, "Application of color-based machine vision systems for quality control in food manufacturing," Food Eng. J., vol. 30, no. 1, pp. 55-67, 2022.
  • [12] L. Chen, H. Nguyen, and P. Adams, "Case study of color-based machine vision systems for defect detection in pharmaceutical manufacturing," Pharm. Eng. J., vol. 14, no. 4, pp. 401-415, 2023.
  • [13] R. Abraham, J. Smith, and M. Johnson, "Real-time quality control using OpenCV library-based image processing system on assembly line," Journal of Manufacturing Automation, vol. 22, no. 3, pp. 189-201, 2023.
  • [14] B. Smith, A. Brown, and L. Garcia, "Utilization of automatic visual inspection techniques in industrial production lines," Industrial Automation J., vol. 15, no. 2, pp. 189-201, 2021.
  • [15] M. Brown, L. Zhang, and T. Nguyen, "Application of image-based quality control systems," Journal of Quality Eng., vol. 9, no. 1, pp. 45-57, 2020.
  • [16] R. Garcia, Y. Wang, and S. Patel, "Utilization of image processing techniques for quality control in industrial products," Journal of Industrial Quality Control, vol. 13, no. 2, pp. 123-135, 2020.
  • [17] Y. Wang, H. Kim, and P. Lee, "Application of image-based quality control systems in manufacturing industry," Journal of Manufacturing Quality, vol. 17, no. 3, pp. 201-215, 2021.
  • [18] L. Chen, T. Nguyen, and S. Patel, "Utilization of computer vision systems for quality control on assembly lines," Journal of Computer-Aided Manufacturing, vol. 20, no. 4, pp. 321-335, 2022.
  • [19] H. Kim, R. Garcia, and J. Lee, "Utilization of machine vision systems for automatic inspection of industrial products," Industrial Inspection J., vol. 11, no. 3, pp. 167-179, 2019.
  • [20] S. Patel, M. Brown, and L. Zhang, "Utilization of machine vision systems in industrial inspection processes," Journal of Industrial Eng., vol. 14, no. 2, pp. 55-67, 2018.
  • [21] T. Nguyen, R. Abraham, and L. Chen, "Utilization of image-based quality control systems in the manufacturing industry," Journal of Production Eng., vol. 12, no. 4, pp. 401-415, 2019.
  • [22] L. Zhang, M. Brown, and S. Patel, "Recent developments in machine vision systems for quality control in industrial manufacturing," Journal of Advanced Manufacturing Technology, vol. 19, no. 5, pp. 567-578, 2022.
  • [23] RapidTables, "RGB to HSV color conversion," RapidTables, 2022. [Online]. Available: https://www.rapidtables.org/tr/convert/color/rgb-to-hsv.html. [Accessed: Mar. 3, 2024].
There are 23 citations in total.

Details

Primary Language English
Subjects Machine Vision , Mechatronics Engineering
Journal Section Articles
Authors

Mehmet Emin Örs 0000-0002-6206-1031

Ziya Özçelik 0000-0002-6567-2671

Publication Date October 23, 2024
Submission Date April 5, 2024
Acceptance Date August 4, 2024
Published in Issue Year 2024 Volume: 12 Issue: 4

Cite

APA Örs, M. E., & Özçelik, Z. (2024). Detection of Piston Ring Deficiency in The Assembly of Automotive Ball Joint and Tie Rod End Parts. Düzce Üniversitesi Bilim Ve Teknoloji Dergisi, 12(4), 2283-2296. https://doi.org/10.29130/dubited.1465948
AMA Örs ME, Özçelik Z. Detection of Piston Ring Deficiency in The Assembly of Automotive Ball Joint and Tie Rod End Parts. DUBİTED. October 2024;12(4):2283-2296. doi:10.29130/dubited.1465948
Chicago Örs, Mehmet Emin, and Ziya Özçelik. “Detection of Piston Ring Deficiency in The Assembly of Automotive Ball Joint and Tie Rod End Parts”. Düzce Üniversitesi Bilim Ve Teknoloji Dergisi 12, no. 4 (October 2024): 2283-96. https://doi.org/10.29130/dubited.1465948.
EndNote Örs ME, Özçelik Z (October 1, 2024) Detection of Piston Ring Deficiency in The Assembly of Automotive Ball Joint and Tie Rod End Parts. Düzce Üniversitesi Bilim ve Teknoloji Dergisi 12 4 2283–2296.
IEEE M. E. Örs and Z. Özçelik, “Detection of Piston Ring Deficiency in The Assembly of Automotive Ball Joint and Tie Rod End Parts”, DUBİTED, vol. 12, no. 4, pp. 2283–2296, 2024, doi: 10.29130/dubited.1465948.
ISNAD Örs, Mehmet Emin - Özçelik, Ziya. “Detection of Piston Ring Deficiency in The Assembly of Automotive Ball Joint and Tie Rod End Parts”. Düzce Üniversitesi Bilim ve Teknoloji Dergisi 12/4 (October 2024), 2283-2296. https://doi.org/10.29130/dubited.1465948.
JAMA Örs ME, Özçelik Z. Detection of Piston Ring Deficiency in The Assembly of Automotive Ball Joint and Tie Rod End Parts. DUBİTED. 2024;12:2283–2296.
MLA Örs, Mehmet Emin and Ziya Özçelik. “Detection of Piston Ring Deficiency in The Assembly of Automotive Ball Joint and Tie Rod End Parts”. Düzce Üniversitesi Bilim Ve Teknoloji Dergisi, vol. 12, no. 4, 2024, pp. 2283-96, doi:10.29130/dubited.1465948.
Vancouver Örs ME, Özçelik Z. Detection of Piston Ring Deficiency in The Assembly of Automotive Ball Joint and Tie Rod End Parts. DUBİTED. 2024;12(4):2283-96.
 Download Cover Image