Zhou Zhaoqi,Ding Mingyue,Zhu Qingqing,et al.MATLAB image quantitative analysis for 316L stainless steel electrolytic polishing[J].Plating & Finishing,2024,(1):97-104.[doi:10.3969/j.issn.1001-3849.2024.01.015]
316L不锈钢电解抛光的MATLAB图像定量分析
- Title:
- MATLAB image quantitative analysis for 316L stainless steel electrolytic polishing
- 关键词:
- 图像定量分析; MATLAB GUI ; 点蚀; 电解抛光; 316L 不锈钢
- Keywords:
- image quantitative analysis ; MATLAB GUI ; pitting ; electrolytic polishing ; 316L stainless steel
- 分类号:
- TQ153.5
- 文献标志码:
- A
- 摘要:
- 基于机器视觉的不锈钢表面无损检测方法正受到工业界关注并得到研究人员的探索与开发。本研究使用 MATLAB 对电解抛光的 316L 不锈钢表面金相图进行图像二值化处理，保留区域点蚀和过抛腐蚀区的黑色像素点和黑色区域，除去浅色划痕和不明显的凹凸区域。图像腐蚀处理选取半径为 3 个像素点的圆形结构元素为参数，去除图像噪声，增强图像黑色像素区域边界和对比度。选取图像的黑色像素占比和点蚀区域数量作为特征变量，并通过对特征变量进行测量和计数来评估抛光效果。在此基础上，借助 MATLAB GUI 编程平台开发了一个基于图像定量分析过程的抛光效果评估程序，应用该程序可快速获得 316L 不锈钢电解抛光材料点蚀定量数据，使金相图片分析数值化，弥补主观判断的不足。该方法得到的结果与基于探针式粗糙度测量的优化结果一致。
- Abstract:
- ： The non-destructive testing method of stainless steel surface based on machine vision is attracting the attention of the industry and being explored and developed by researchers. In this study ， MATLAB was employed to perform image binarization processing on the metallographic image of electrolytic polished 316L stainless steel surfaces ， retaining dark pixel points and dark regions corresponding to localized pitting and over-polished corrosion areas ， while excluding light-colored scratches and less pronounced surface irregularities. The image erosion process selects a circular structural element with a radius of 3 pixels as a parameter to remove image noise and enhance the boundary and contrast of the black pixel area of the image. The proportion of black pixels and the number of pitting areas of the image are selected as characteristic variables ， and the polishing effect is evaluated by measuring and counting the characteristic variables. On this basis ， a polishing effect evaluation program based on image quantitative analysis process was developed with the help of MATLAB GUI programming platform. The application of this program can quickly obtain the quantitative analysis data of pitting corrosion of 316L stainless steel electrolytic polishing materials ， making the analysis of metallographic pictures numerical ， and making up for the lack of subjective judgment. The results obtained from this method are consistent with the optimized outcomes based on probe-based roughness measurements.
参考文献/References:
[1] 纪刚强 , 孙桓五 , 段海栋 , 等 . 基于响应曲面法的不锈钢电解质等离子体抛光工艺参数优化 [J]. 现代制造工程 , 2022(6): 68-77.
[2] 孙璐 , 曹驰 , 杜金涛 , 等 . AISI 300 系列奥氏体不锈钢渗氮层组织和性能研究 [J]. 表面技术 , 2023, 52(1): 421-431.
[3] Zatkalíková V, Podhorsk? ?, ?trbák M, et al. Plasma electrolytic polishing-an ecological way for increased corrosion resistance in austenitic stainless steels[J].Materials, 2022, 15(12): 4223.
[4] Carolina de Oliveira A, Lopes de Oliveira M C, Ríos C T, et al. The effect of mechanical polishing and finishing on the corrosion resistance of AISI 304 stainless steel [J]. Corrosion Engineering, Science and Technology, 2016, 51(6): 416-428.
[5] Jaffré K, Ter-ovanessian B, Abe H, et al. Effect of mechanical surface treatments on the surface state and passive behavior of 304L stainless steel [J]. Metals, 2021, 11(1): 135.
[6] Rokosz K, Solecki G, Mori G, et al. Effect of polishing on electrochemical behavior and passive layer composition of different stainless steels [J]. Materials, 2020, 13(15): 3402.
[7] Han W, Fang F Z. Eco-friendly NaCl-based electrolyte for electropolishing 316L stainless steel [J]. Journal of Manufacturing Processes, 2020, 58: 1257-1269.
[8] 柳小祥 , 范文俊 , 徐招 , 等 . 316L 不锈钢金属双极板的电解抛光工艺 [J]. 电镀与精饰 , 2020, 42(3): 6-11.
[9] 宣宇娜 , 唐佳斌 , 冯凯 , 等 . 工艺参数对 316L 不锈钢电解抛光效果的影响 [J]. 电镀与涂饰 , 2023, 42(5): 47-55.
[10] Samtas G. Measurement and evaluation of surface roughness based on optic system using image processing and artificial neural network[J]. The International Journal of Advanced Manufacturing Technology, 2014, 73(1-4): 353-364.
[11] Luo Q W, Fang X X, Su J J, et al. Automated visual defect classification for flat steel surface: A survey [J]. IEEE Transactions on Instrumentation and Measurement, 2020, 69(12): 9329-9349.
[12] Tang B, Chen L, Sun W, et al. Review of surface defect detection of steel products based on machine vision [J]. Iet Image Processing, 2023, 17(2): 303-322.
[13] Rifai A P, Aoyama H, Tho N H, et al. Evaluation of turned and milled surfaces roughness using convolutional neural network [J]. Measurement, 2020, 161: 107860.
[14] Tu J V. Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes [J]. Journal of Clinical Epidemiology, 1996, 49(11): 1225-1231.
[15] Liu J, Lu E H, Yi H A, et al. A new surface roughness measurement method based on a color distribution statistical matrix [J]. Measurement, 2017, 103: 165-178.
[16] 劳东青 , 王宗祥 , 王冠军 . 基于 MATLAB 的叶片图像分析系统研究 [J]. 节水灌溉 , 2015(9): 101-104, 108.
[17] 孙鹏崴 , 王俊 , 王树军 , 等 . 基于 MATLAB GUI 的图像处理系统的设计 [J]. 计算机技术与发展 , 2022, 32(4): 215-220.
[18] 王寻 , 王宏哲 , 张泽坤 , 等 . 基于 Matlab GUI 的气泡动力学仿真系统设计 [J]. 实验室研究与探索 , 2022, 41(4): 113-117, 127.
[19] Arunachalaperumal C, Dhilipkumar S. An efficient image quality enhancement using wavelet transform [J]. Materials Today: Proceedings, 2020, 24: 2004-2010.
[20] Lu A Q, Zhang S Z, Tian Q. Matlab image processing technique and application in pore structure characterization of hardened cement pastes[J]. Advanced Materials Research, 2013, 785-786: 1374-1379.
[21] 梁海波 , 黄万伟 , 李浩 , 等 . 基于 MATLAB GUI 的测试数据比对分析软件设计 [J]. 导弹与航天运载技术 , 2022(4): 56-61.
备注/Memo
收稿日期： 2023-06-19 修回日期： 2023-08-14 作者简介： 周赵琪（ 1998 ―），女，硕士研究生， email ： 1669491836@qq.com * 通信作者： 汪玉，讲师，主要研究方向为基于人工智能技术的材料逆向设计， email ： yuwang@sit.edu.cn ；王振卫，副教授，主要研究方向为电镀与精饰， email ： wangzhenwei@sit.edu.cn 316L?/html>