Hatalı Uçlu İnşaat Demirlerinin Yüksek Doğruluklu Sayımı

Abstract

Demir çelik sektöründe ürün kalitesi son derece önemlidir. Döküm sürecinden paketlemeye kadar, üretimin her aşamasında büyük miktarda enerji harcanılır. Bu çalışmada, depolama alanında bulunan çelik inşaat demiri sayımı dikkate alınmıştır. Bir paketteki demetin yeniden sayılması gerektiğinde, paketteki demet sayısına bağlı olarak ya saymak için bir personel atanır ya da tekrar tartılmak üzere götürülür. Her ikisi de zaman ve enerji tüketen çözümlerdir. Bu çalışmada, inşaat demiri uçlarının depolama alanlarında fotoğrafı çekilerek bir paket içerisindeki demet sayımı için bir algoritma geliştirilmiştir. Deforme kesme, çelik nervür özellikleri, boyama eksikliği ve ayrıca depolama alanının yetersiz aydınlatılması gibi kusurların varlığına rağmen, geliştirilmiş algortitma son derece doğru sonuçlar verebilmektedir.

Keywords

• Görüntü işleme
• demir çelik endüstrisi
• demir demet sayımı
• yüksek doğruluk

High Accurate Counting of Steel Rebar with Defected Tips

Abstract

The product quality in the iron and steel industry is highly important. From the casting process to bundling, a large amount of energy is used at each step of the production. In the present study, the counting of steel rebar bundles located in the storage area has been taken into account. When it is necessary to recount the rebar in a bundle, depending on the number of rebar in the bundle, either a staff is assigned to count or the bundle is moved for weighting again. Both of them are time and energy-consuming solutions. In the present study, an algorithm is developed to count the rebar in a bundle by taking a photograph of rebar tips. Although the existence of defects such as deforming cutting, steel rib features, lack of painting, and also insufficient lighting of the storage area, the proposed algorithm is able to give highly accurate results.

Keywords

• Image processing
• iron and steel industry
• steel rebar counting
• high accuracy

References

1. Tunuz, A. & Furat, M. A Sensorless Crude Steel Cutting Method for Continuous Casting Machine. CILICIA International Symposıum On Engineering and Technology CISET, Mersin, Turkey, 19-22 June 2018.
2. Yılmaz, F., Dağılgan, N. S. & Furat, M. Image Processing Applications For Sustainable Production In Iron And Steel Industry. 7th International Iron & Steel Symposium, İzmir, Turkey, 26-27 September 2019, pp. 51-54.
3. Wu, Y., Zhou, X. & Zhang, Y. Steel bars counting and splitting method based on machine vision. IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER) 2015, Shenyang, China, pp. 420-425, doi: 10.1109/CYBER.2015.7287974.
4. Nie, Z., Hung, M. & Huang, J. Rebar Counting on Production Line Based on Machine Vision. 3rd International Conference on Robot, Vision and Signal Processing (RVSP), Kaohsiung, 2015, pp. 39-42, doi: 10.1109/RVSP.2015.18.
5. Fernández, A., Souto, M. Á. & Guerra, L. Automatic steel bar counting in production line based on laser triangulation. IECON 2019 - 45th Annual Conference of the IEEE Industrial Electronics Society, Lisbon, Portugal, 2019, pp. 80-85, doi: 10.1109/IECON.2019.8927798.
6. Zhang, Y., Jiang, M., Wu, Y. & Zhou, X. An automatic rebar splitting system based on two-level of the chain transmission. 2015 IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER), Shenyang, 2015, pp. 587-590, doi: 10.1109/CYBER.2015.7288006.
7. Su, Z., Fang, K., Peng, Z. & Feng, Z. Rebar automatically counting on the product line. IEEE International Conference on Progress in Informatics and Computing, Shanghai, China, 2010, Vol. 2, pp. 756-760, doi: 10.1109/PIC.2010.5688012.
8. Xiaohu L. & Jineng, O. Research on steel bar detection and counting method based on contours. 2018 International Conference on Electronics Technology (ICET), Chengdu, 2018, pp. 294-297, doi: 10.1109/ELTECH.2018.8401470.

9. Ablidas, M. R., Monsura, A., Ablidas, L. A. & Cruz, J. D. (2019) An Application of Image Processing Technology in Counting Rebars as an Alternative to Manual Counting Process. International Journal of Simulation -- Systems, Science & Technology, 20(5), pp. 1–9. doi: 10.5013/IJSSST.a.20.05.02
10. Fang, H. P., Fang, K. L. & Liu, X. H. (2013) Online Rebar Recognition Based on Multi-View Images. Applied Mechanics and Materials, vols. 416–417, pp. 1192–1195, doi: 10.4028/www.scientific.net/amm.416-417.1192.
11. Park, J.-H., Kim T.-H. & Choo, S.-Y. (2020) Deep learning-based rebar reinforcement detection technology to improve supervision work efficiency. Journal of the Architectural Institute of Korea: Planning Section, Vol. 36 (5), pp. 93–103, doi: 10.5659/JAIK_PD.2020.36.5.93
12. Internet source: Smoothing Images, https://docs.opencv.org/master/d4/d13/tutorial_py_filtering.html (last access: 12 Dec 2020)
13. Internet source: Canny Edge Detection, https://docs.opencv.org/master/da/d22/tutorial_py_canny.html (last access: 12 Dec 2020)
14. Rong, W., Li, Z., Zhang, W. & Sun, L. An improved Canny edge detection algorithm. IEEE International Conference on Mechatronics and Automation, Tianjin, 2014, pp. 577-582, doi: 10.1109/ICMA.2014.6885761.
15. Jie, G. & Ning, L. An improved adaptive threshold canny edge detection algorithm. International Conference on Computer Science and Electronics Engineering, Hangzhou, China, 2012, Vol. 1, pp. 164-168, doi: 10.1109/ICCSEE.2012.154
16. Xinman, Z., Mei, M., Tingting, H. & Xuebin, X. Steel bars counting method based on image and video processing. International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), Xiamen, 2017, pp. 304-309, doi: 10.1109/ISPACS.2017.8266493.
17. Internet Source: Hough Teansform, , https://en.wikipedia.org/wiki/Circle_Hough_Transform, (last access: 12 Dec 2020)
18. Internet source: http://www.aveaplast.com/images/stories/virtuemart/product/demircubuk.jpg