Classification of Zinc-Coated Parts in Accordance with their Brightness Degree using Deep Learning Techniques

Abstract

A novel technique was suggested to measure the brightness of the coated parts. The algorithm of Mask RCNN was used to detect the relevant region on the whole image. The pixels of black lines, which are associated with the brightness of the coating and reflected from the foreground, were counted using image processing technique. These pixels were used as the output in the machine learning training to classify the coated parts. The output was binarized to classify the coated plates as “Pass” and “Fail”. It was found that the RF model was the best model. The scores of its accuracy, F1, precision, and recall were established to be 0.97, 0.97, 1, and 0.94, respectively. The overlap scores of Mask RCNN were found to be in the range of 0.92-0.97, which proved that Mask RCNN algorithm detected the concerned region with high precision and accuracy.

Keywords

• Mask RCNN
• Deep learning
• Machine learning
• Zinc electroplating
• Brightness measurement
• Image processing
• Surface detection

References

1. 1. Safavi MS, Walsh FC. Electrodeposited Co-P alloy and composite coatings: A review of progress towards replacement of conventional hard chromium deposits. Surface and Coatings Technology. 2021 Sep;422:127564. Available from: ,
2. 2. Fotovvati B, Namdari N, Dehghanghadikolaei A. On Coating Techniques for Surface Protection: A Review. JMMP. 2019 Mar;3(1):28.
3. 3. Gu Y, Liu J, Qu S, Deng Y, Han X, Hu W, et al. Electrodeposition of alloys and compounds from high-temperature molten salts. Journal of Alloys and Compounds. 2017 Jan;690:228–38.
4. 4. Gérard B. Application of thermal spraying in the automobile industry. Surface and Coatings Technology. 2006 Oct;201(5):2028–31.
5. 5. Bobzin K, Brögelmann T, Kalscheuer C, Liang T. High-rate deposition of thick (Cr,Al)ON coatings by high speed physical vapor deposition. Surface and Coatings Technology. 2017 Aug;322:152–62.
6. 6. Xia F, Xu H, Liu C, Wang J, Ding J, Ma C. Microstructures of Ni–AlN composite coatings prepared by pulse electrodeposition technology. Applied Surface Science. 2013 Apr;271:7–11.
7. 7. Safavi MS, Etminanfar M. A review on the prevalent fabrication methods, microstructural, mechanical properties, and corrosion resistance of nanostructured hydroxyapatite containing bilayer and multilayer coatings used in biomedical applications. J Ultrafine Grained Nanostruct Mater [Internet]. 2019 Jun [cited 2022 Oct 17];52(1).
8. 8. Katırcı R, Yılmaz EK, Kaynar O, Zontul M. Automated evaluation of Cr-III coated parts using Mask RCNN and ML methods. Surface and Coatings Technology. 2021 Sep;422:127571.

9. 9. Bayati MR, Shariat MH, Janghorban K. Design of chemical composition and optimum working conditions for trivalent black chromium electroplating bath used for solar thermal collectors. Renewable Energy. 2005 Nov;30(14):2163–78.
10. 10. Kul M, Oskay K, Erden F, Akça E, Katirci R, Köksal E, et al. Effect of Process Parameters on the Electrodeposition of Zinc on 1010 Steel: Central Composite Design Optimization. Int J Electrochem Sci. 2020 Oct;9779–95.
11. 11. Mirkova L, Maurin G, Krastev I, Tsvetkova C. Hydrogen evolution and permeation into steel during zinc electroplating; effect of organic additives. Journal of Applied Electrochemistry. 2001;31(6):647–54.
12. 12. Arnold JO. The Metallurgy of Steel. Nature. 1912 May;89(2222):315–6.
13. 13. Yang D, Wang X, Zhang H, Yin Z yu, Su D, Xu J. A Mask R-CNN based particle identification for quantitative shape evaluation of granular materials. Powder Technology. 2021 Nov;392:296–305.
14. 14. Kiliçarslan S, Celik M. KAF + RSigELU: A nonlinear and kernel-based activation function for deep neural networks. Neural Comput & Applic. 2022 Aug;34(16):13909–23.
15. 15. Kiliçarslan S, Celik M. RSigELU: A nonlinear activation function for deep neural networks. Expert Systems with Applications. 2021 Jul;174:114805.
16. 16. Adem K, Kilicarslan S. COVID-19 Diagnosis Prediction in Emergency Care Patients using Convolutional Neural Network. Akufemubid. 2021;21(2):300–9.
17. 17. Adem K. Impact of activation functions and number of layers on detection of exudates using circular Hough transform and convolutional neural networks. Expert Systems with Applications. 2022 Oct;203:117583.
18. 18. Simonyan K, Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition. 2014 [cited 2022 Oct 17];
19. 19. He K, Zhang X, Ren S, Sun J. Deep Residual Learning for Image Recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) [Internet]. Las Vegas, NV, USA: IEEE; 2016 [cited 2022 Oct 17]. p. 770–8.
20. 20. Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the Inception Architecture for Computer Vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) [Internet]. Las Vegas, NV, USA: IEEE; 2016 [cited 2022 Oct 17]. p. 2818–26. Available from:
21. 21. Chollet F. Xception: Deep Learning with Depthwise Separable Convolutions. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) [Internet]. Honolulu, HI: IEEE; 2017 [cited 2022 Oct 17]. p. 1800–7.
22. 22. Yu Y, Zhang K, Yang L, Zhang D. Fruit detection for strawberry harvesting robot in non-structural environment based on Mask-RCNN. Computers and Electronics in Agriculture. 2019 Aug;163:104846.
23. 23. Kumar G, Bhatia PK. A Detailed Review of Feature Extraction in Image Processing Systems. In: 2014 Fourth International Conference on Advanced Computing & Communication Technologies [Internet]. Rohtak, India: IEEE; 2014 [cited 2022 Oct 17]. p. 5–12.
24. 24. Hull R. Current Density Range Characteristics, Their Determination and Application. Proc Am Electroplaters Soc. 1939;27:52.
25. 25. Hu J, Sun Y, Li G, Jiang G, Tao B. Probability analysis for grasp planning facing the field of medical robotics. Measurement. 2019 Jul;141:227–34.
26. 26. Reza M, Miri S, Javidan R. A Hybrid Data Mining Approach for Intrusion Detection on Imbalanced NSL-KDD Dataset. ijacsa [Internet]. 2016 [cited 2022 Oct 17];7(6).
27. 27. Vapnik VN. The Nature of Statistical Learning Theory [Internet]. New York, NY: Springer New York; 2000 [cited 2022 Oct 17].
28. 28. Chen T, Guestrin C. XGBoost: A Scalable Tree Boosting System. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining [Internet]. San Francisco California USA: ACM; 2016 [cited 2022 Oct 17]. p. 785–94.
29. 29. Rumelhart DE, Hinton GE, Williams RJ. Learning Internal Representations by Error Propagation. In: Readings in Cognitive Science [Internet]. Elsevier; 1988 [cited 2022 Oct 17]. p. 399–421.