Research Article
BibTex RIS Cite

Development of a Machine Fasteners Classification System

Year 2020, Ejosat Special Issue 2020 (HORA), 289 - 299, 15.08.2020
https://doi.org/10.31590/ejosat.779981

Abstract

Machine fasteners (bolts, nuts, washers, etc.) are an integral part of the production, maintenance, repair, and assembly processes. Machine fasteners that have been previously used but are scatheless can be reused in new processes. For this reason, used machine fasteners that are generally mixed in an area are subjected to a sorting process, and those that cannot be used are scrapped. In this process, the fasteners are sorted with respect to their types, sizes, and metrics. This sorting process is usually done with manpower and this leads to errors and loss of labor which diminish productivity. In this study, the development of an automation system that classifies mixed machine fasteners as type, size, and metric using the image processing method is presented. The system consists of four main units: a vibrating feeder, a conveyor belt, an image processing unit, and a packaging mechanism. The fasteners are put in the vibration feeder in order to be sent to the conveyor. The elements lined up are transferred with the conveyor to the image processing unit and are classified as type, size, and metric in this unit. Classified elements are placed in the relevant boxes in the packaging mechanism. During these processes, all system data are recorded and transferred to the computer environment, and the user can access these data thanks to the developed user interface. Firstly, the electrical and mechanical designs of the system are done depending on the specified design criteria. Then, graphical user interface, control, and image processing algorithms are developed. After the production of mechanical parts, the integration of the system is completed and functional tests are carried out successfully. Test results show that the success rate of the developed image processing algorithm is over 90%. 

References

  • Ekici, Süleyman & Erbil, Emre & Bıyık, Aysel. (2016). Bağlantı Elemanı Ayıklama Uygulamalarında Makine Vizyonu Teknikleri. 9. 82-92.
  • Daniyan, I. A., Adeodu, A. O. and Dada, O. M. (2014). Design of a Material Handling Equipment: Belt Conveyor System for Crushed Limestone Using 3 Roll Idler. Journal of Advancement in Engineering and Technology. pp. 1-7.
  • Standard for Conveyor Belt Covers, H. Simonsen Consultant, Sept. 1990 Manager R & D, Germany, Sept. 1990.
  • Besser Service Bulletin. (2006). Conveyor Belt Basic Rules and Procedure for Tracking. pp. 1-7
  • García-Martín, Javier & Gomez-Gil, Jaime & Vázquez-Sánchez, Ernesto. (2011). Non-Destructive Techniques Based on Eddy Current Testing. Sensors (Basel, Switzerland). 11. 2525-65. 10.3390/s110302525.
  • Feng, Hao & Jiang, Zhiguo & Xie, Fengying & Yang, Ping & Shi, Jun & Chen, Long. (2014). Automatic Fastener Classification and Defect Detection in Vision-Based Railway Inspection Systems. Instrumentation and Measurement, IEEE Transactions on. 63. 877-888. 10.1109/TIM.2013.2283741.
  • D'Angelo, Gianni & Rampone, Salvatore. (2015). Shape-based defect classification for Non Destructive Testing. 2nd IEEE International Workshop on Metrology for Aerospace, MetroAeroSpace 2015 - Proceedings. 406-410. 10.1109/MetroAeroSpace.2015.7180691.
  • Xiukun Wei, Ziming Yang, Yuxin Liu, Dehua Wei, Limin Jia, Yujie Li, Railway track fastener defect detection based on image processing and deep learning techniques: A comparative study, Engineering Applications of Artificial Intelligence, Volume 80, 2019, Pages 66-81, ISSN 0952-1976.
  • P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on, vol: 1, pp.:I-511-I518, 2001.
  • R. Hussin, M.R. Juhari, N.W. Kang, R.C. Ismail and A. Kamarudin, “Digital image processing techniques for object detection from complex background image”. Procedia Engineering, vol:41, pp:340-344, 2012
  • M. Sonka, V. Hlavac and R. Boyle, “Image processing, analysis, and machine vision. Cengage Learning”, 2014
  • Attica Automation Inc., AVB100, Erişim adresi: http://www.atticaautomation.com/wp-content/uploads/2019/06/Attica_Booklet.pdf
  • Delta Vision, DV-RDSM – Rotary Disc Sorting Machine, Erişim adresi: http://www.deltavisione.com/files/33826_Delta_Visione_Brochure_Selezionatrici_ENG_02_2018.pdf
  • S, Shilpashree & Hlmg, Lokesha & Shivkumar, Hadimani. (2015). Implementation of Image Processing on Raspberry Pi. IJARCCE. 4. 199-202. 10.17148/IJARCCE.2015.4545.
  • Bordignon, Lucas & Von Wangenheim, Aldo. (2019). Benchmarking Deep Learning Models on Jetson TX2. 10.13140/RG.2.2.28466.15040.
  • P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on, vol: 1, pp.:I-511-I518, 2001.
  • Y. Zhang, et al., "Gilbreth: A Conveyor-Belt Based Pick-and-Sort Industrial Robotics Application," in 2018 Second IEEE International Conference on Robotic Computing (IRC), Laguna Hills, CA, USA, 2018 pp. 17-24.
  • Silversides, Richard & Dai, Jian & Seneviratne, Lakmal. (2005). Force Analysis of a Vibratory Bowl Feeder for Automatic Assembly. Journal of Mechanical Design - J MECH DESIGN. 127. 10.1115/1.1897407.
  • Ramalingam, M., & Samuel, G. L. (2008). Investigation on the conveying velocity of a linear vibratory feeder while handling bulk-sized small parts. The International Journal of Advanced Manufacturing Technology, 44(3–4), 372–382.
  • Abdulla, Shaeez & K., Kunhimohammed & K., Muhammed & S., Sahna & S., Gokul. (2016). Automatic Color Sorting Machine Using TCS230 Color Sensor And PIC Microcontroller. International Journal of Research and Innovations in Science and Technology, ISSN 2395-3858, Jan, 2016. 2.
  • Gladwell G. M. L., and Masour W. M., 1971, “Simulation of Vibratory Feeders, Proc. Of the Symp. on Computer-Aided Engineering,” Univ. Waterloo, pp. 215–249.
  • Mansour W. M., 1972, “Analog and Digital Analysis and Synthesis of Oscillatory Tracks,” ASME J. Eng. Ind., 94(2), pp. 488–494.
  • M.A, A., Latest Developments in Belt Conveyor Technology. MINExpo 2004, Las Vegas, NV, USA. September 27, (2004). 2004.
  • S. Bellal, H. Mouss and R. Bensaadi, "Recognition of objetcts in an image for triage," 2013 International Conference on Control, Decision and Information Technologies (CoDIT), Hammamet, 2013, pp. 359-365.
  • Xu, Dong & Li, Hua. (2006). Euclidean Distance Transform of Digital Images in Arbitrary Dimensions. 4261. 72-79. 10.1007/11922162_9.
  • Srisha, Ravi & Khan, Am. (2013). Morphological Operations for Image Processing : Understanding and its Applications.
  • Gedraite, Estevao & Hadad, M.. (2011). Investigation on the effect of a Gaussian Blur in image filtering and segmentation. 393-396.
  • Ismail, Abdul Halim & Marhaban, Mohammad Hamiruce. (2009). A simple approach to determine the best threshold value for automatic image thresholding. 10.1109/ICSIPA.2009.5478623.

Makine Bağlantı Elemanlarını Ayıklama Sistemi Geliştirilmesi

Year 2020, Ejosat Special Issue 2020 (HORA), 289 - 299, 15.08.2020
https://doi.org/10.31590/ejosat.779981

Abstract

Makine bağlantı elemanları (cıvata, somun, pul, vb.) üretim, bakım, onarım ve montaj işlemlerinin ayrılmaz bir parçasıdır. Daha önce kullanılmış ancak sağlam olan makine bağlantı elemanları yeni işlemlerde tekrar kullanılabilmektedir. Bu nedenle, genellikle bir alanda karışık şekilde toplanmış makine bağlantı elemanları bir ayıklama işleminden geçirilir. Böylece sağlam olan bağlantı elemanları sınıflandırılarak ayıklanır ve kullanılamayacak durumda olanlar hurdaya gönderilir. Bu ayıklama işlemi genellikle insan gücü ile yapılmaktadır. Burada ortaya çıkan insan kaynaklı hatalar ve iş gücü kaybı verimliliği düşürmektedir. Bu çalışmada, karışık halde bulunan makine bağlantı elemanlarını görüntü işleme metodu kullanılarak tür, boyut ve metrik olarak sınıflandıran bir otomasyon sisteminin geliştirilmesi anlatılmıştır. Sistem titreşimli besleyici, konveyör bant, görüntü işleme birimi ve paketleme mekanizması olmak üzere 4 ana birimden oluşmaktadır. Bağlantı elemanları, konveyöre gönderilmek üzere titreşim besleyiciye yerleştirilmektedir. Sıralanmış elemanlar konveyör ile görüntü işleme ünitesine aktarılmakta ve bu ünitede tür, boyut ve metrik olarak sınıflandırılmaktadır. Sınıflandırılmış elemanlar paketleme mekanizmasındaki ilgili kutulara yerleştirilmektedir. Bu işlemler sırasında tüm sistem verileri kayıt altına alınarak bilgisayar ortamına aktırılmakta ve geliştirilen arayüz sayesinde kullanıcının bu verilere ulaşması sağlanmaktadır. İlk olarak, sistemin elektrik ve mekanik tasarımları belirlenen tasarım kriterlerine bağlı olarak gerçekleştirilmiştir. Ardından, grafik kullanıcı arayüzü, kontrol ve görüntü işleme algoritmaları geliştirilmiştir. Mekanik parçaların üretiminden sonra sistemin entegrasyonu tamamlanmış ve fonksiyonel testler başarıyla gerçekleştirilmiştir. Test sonuçları, geliştirilen sistemin görüntü işleme tabanlı sınıflandırma başarı oranının % 90' ın üzerinde olduğunu göstermektedir.

References

  • Ekici, Süleyman & Erbil, Emre & Bıyık, Aysel. (2016). Bağlantı Elemanı Ayıklama Uygulamalarında Makine Vizyonu Teknikleri. 9. 82-92.
  • Daniyan, I. A., Adeodu, A. O. and Dada, O. M. (2014). Design of a Material Handling Equipment: Belt Conveyor System for Crushed Limestone Using 3 Roll Idler. Journal of Advancement in Engineering and Technology. pp. 1-7.
  • Standard for Conveyor Belt Covers, H. Simonsen Consultant, Sept. 1990 Manager R & D, Germany, Sept. 1990.
  • Besser Service Bulletin. (2006). Conveyor Belt Basic Rules and Procedure for Tracking. pp. 1-7
  • García-Martín, Javier & Gomez-Gil, Jaime & Vázquez-Sánchez, Ernesto. (2011). Non-Destructive Techniques Based on Eddy Current Testing. Sensors (Basel, Switzerland). 11. 2525-65. 10.3390/s110302525.
  • Feng, Hao & Jiang, Zhiguo & Xie, Fengying & Yang, Ping & Shi, Jun & Chen, Long. (2014). Automatic Fastener Classification and Defect Detection in Vision-Based Railway Inspection Systems. Instrumentation and Measurement, IEEE Transactions on. 63. 877-888. 10.1109/TIM.2013.2283741.
  • D'Angelo, Gianni & Rampone, Salvatore. (2015). Shape-based defect classification for Non Destructive Testing. 2nd IEEE International Workshop on Metrology for Aerospace, MetroAeroSpace 2015 - Proceedings. 406-410. 10.1109/MetroAeroSpace.2015.7180691.
  • Xiukun Wei, Ziming Yang, Yuxin Liu, Dehua Wei, Limin Jia, Yujie Li, Railway track fastener defect detection based on image processing and deep learning techniques: A comparative study, Engineering Applications of Artificial Intelligence, Volume 80, 2019, Pages 66-81, ISSN 0952-1976.
  • P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on, vol: 1, pp.:I-511-I518, 2001.
  • R. Hussin, M.R. Juhari, N.W. Kang, R.C. Ismail and A. Kamarudin, “Digital image processing techniques for object detection from complex background image”. Procedia Engineering, vol:41, pp:340-344, 2012
  • M. Sonka, V. Hlavac and R. Boyle, “Image processing, analysis, and machine vision. Cengage Learning”, 2014
  • Attica Automation Inc., AVB100, Erişim adresi: http://www.atticaautomation.com/wp-content/uploads/2019/06/Attica_Booklet.pdf
  • Delta Vision, DV-RDSM – Rotary Disc Sorting Machine, Erişim adresi: http://www.deltavisione.com/files/33826_Delta_Visione_Brochure_Selezionatrici_ENG_02_2018.pdf
  • S, Shilpashree & Hlmg, Lokesha & Shivkumar, Hadimani. (2015). Implementation of Image Processing on Raspberry Pi. IJARCCE. 4. 199-202. 10.17148/IJARCCE.2015.4545.
  • Bordignon, Lucas & Von Wangenheim, Aldo. (2019). Benchmarking Deep Learning Models on Jetson TX2. 10.13140/RG.2.2.28466.15040.
  • P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on, vol: 1, pp.:I-511-I518, 2001.
  • Y. Zhang, et al., "Gilbreth: A Conveyor-Belt Based Pick-and-Sort Industrial Robotics Application," in 2018 Second IEEE International Conference on Robotic Computing (IRC), Laguna Hills, CA, USA, 2018 pp. 17-24.
  • Silversides, Richard & Dai, Jian & Seneviratne, Lakmal. (2005). Force Analysis of a Vibratory Bowl Feeder for Automatic Assembly. Journal of Mechanical Design - J MECH DESIGN. 127. 10.1115/1.1897407.
  • Ramalingam, M., & Samuel, G. L. (2008). Investigation on the conveying velocity of a linear vibratory feeder while handling bulk-sized small parts. The International Journal of Advanced Manufacturing Technology, 44(3–4), 372–382.
  • Abdulla, Shaeez & K., Kunhimohammed & K., Muhammed & S., Sahna & S., Gokul. (2016). Automatic Color Sorting Machine Using TCS230 Color Sensor And PIC Microcontroller. International Journal of Research and Innovations in Science and Technology, ISSN 2395-3858, Jan, 2016. 2.
  • Gladwell G. M. L., and Masour W. M., 1971, “Simulation of Vibratory Feeders, Proc. Of the Symp. on Computer-Aided Engineering,” Univ. Waterloo, pp. 215–249.
  • Mansour W. M., 1972, “Analog and Digital Analysis and Synthesis of Oscillatory Tracks,” ASME J. Eng. Ind., 94(2), pp. 488–494.
  • M.A, A., Latest Developments in Belt Conveyor Technology. MINExpo 2004, Las Vegas, NV, USA. September 27, (2004). 2004.
  • S. Bellal, H. Mouss and R. Bensaadi, "Recognition of objetcts in an image for triage," 2013 International Conference on Control, Decision and Information Technologies (CoDIT), Hammamet, 2013, pp. 359-365.
  • Xu, Dong & Li, Hua. (2006). Euclidean Distance Transform of Digital Images in Arbitrary Dimensions. 4261. 72-79. 10.1007/11922162_9.
  • Srisha, Ravi & Khan, Am. (2013). Morphological Operations for Image Processing : Understanding and its Applications.
  • Gedraite, Estevao & Hadad, M.. (2011). Investigation on the effect of a Gaussian Blur in image filtering and segmentation. 393-396.
  • Ismail, Abdul Halim & Marhaban, Mohammad Hamiruce. (2009). A simple approach to determine the best threshold value for automatic image thresholding. 10.1109/ICSIPA.2009.5478623.
There are 28 citations in total.

Details

Primary Language Turkish
Subjects Engineering
Journal Section Articles
Authors

Bedirhan Tuncer

Fatih Sultan Fırıl This is me

Seyit Gündoğan This is me

Ali Kalkanlı This is me

Cenk Ulu

Publication Date August 15, 2020
Published in Issue Year 2020 Ejosat Special Issue 2020 (HORA)

Cite

APA Tuncer, B., Fırıl, F. S., Gündoğan, S., Kalkanlı, A., et al. (2020). Makine Bağlantı Elemanlarını Ayıklama Sistemi Geliştirilmesi. Avrupa Bilim Ve Teknoloji Dergisi289-299. https://doi.org/10.31590/ejosat.779981