基于射线照相的石墨电极缺陷检测与识别

兰州理工大学学报 ›› 2021, Vol. 47 ›› Issue (1): 16-21.

基于射线照相的石墨电极缺陷检测与识别

张鹏林¹, 姚吉², 牛显明², 陈开旺², 张伟平²

1.兰州理工大学省部共建有色金属先进加工与再利用国家重点实验室, 甘肃兰州 730050;
2.兰州理工大学材料科学与工程学院, 甘肃兰州 730050

收稿日期:2020-06-16 出版日期:2021-02-28 发布日期:2021-03-11
作者简介:张鹏林(1973-),男,甘肃景泰人,副研究员.

Defect detection and recognition of graphite electrode based on radiography

ZHANG Peng-lin¹, YAO Ji², NIU Xian-ming², CHEN Kai-wang², ZHANG Wei-ping²

1. State Key Laboratory of Advanced Processing and Recycling of Nonferrous Metals, Lanzhou Univ. of Tech., Lanzhou 730050, China;
2. College of Materials Science and Engineering, Lanzhou Univ. of Tech., Lanzhou 730050, China

Received:2020-06-16 Online:2021-02-28 Published:2021-03-11

摘要/Abstract

摘要： 针对石墨电极内部缺陷无损检测难题,提出采用射线检测与深度信念网络相结合的电极缺陷检测方法.为此制作了石墨电极曝光曲线,利用曝光曲线为预制带有不同缺陷的电极试块选取合理的工艺参数、并进行X射线检测.采用去噪增强处理方法改善电极射线图像对比度弱、信噪比低等问题;应用改进的Canny算子边缘检测方法对电极射线图像进行边缘提取,随后对缺陷特征进行选取、计算,并应用深度信念网络对电极缺陷进行智能识别.结果表明:将射线照相技术应用于石墨电极缺陷的检测是可行的;采用改进的Canny算子提取缺陷边缘,质量得到了很大提高,实现了特征参数的准确计算;将深度信念网络应用于电极缺陷的识别,精度可达96.67%,准确率较高.

关键词: X射线检测, 石墨电极, 特征提取, 深度信念网络, 缺陷识别

Abstract: In order to solve an existing problem in non-destructive testing of defects in graphite electrode, an electrode defect detection method based on the combination of X-ray detection and deep belief network is proposed in this paper. For this reason, an exposure curve of graphite electrode is made for the graphite electrode, and the exposure curve is used to select reasonable process parameters for prefabricated electrode blocks with different defects, and X-ray inspection is also carried out for the graphite electrode. The de-noising enhancement method is then utilized to improve the weak contrast and low signal-to-noise ratio of the electrode ray image, and the improved Canny operator edge detection method is also adopted to extract the edge of the electrode ray image, then the defect features can be selected and calculated easily. This is due to application of the deep belief network to identify intelligently electrode defects. All results from this research make us believing that it is feasible to apply the radiographic technology to detect graphite electrode defects. The improved Canny operator may be used to extract defect edges. The quality of the extraction has been improved greatly, and the accurate calculation of the characteristic parameters may be realized as a result. The deep belief network can be employed to identify electrode defects with an accuracy of 96.67%, which is a higher accuracy rate indeed.

Key words: X-ray detection, graphite electrode, feature extraction, deep belief network, defect identification

中图分类号:

TG115

张鹏林, 姚吉, 牛显明, 陈开旺, 张伟平. 基于射线照相的石墨电极缺陷检测与识别[J]. 兰州理工大学学报, 2021, 47(1): 16-21.

ZHANG Peng-lin, YAO Ji, NIU Xian-ming, CHEN Kai-wang, ZHANG Wei-ping. Defect detection and recognition of graphite electrode based on radiography[J]. Journal of Lanzhou University of Technology, 2021, 47(1): 16-21.

参考文献

[1] 李文可,凌振宝,王君,等.一种石墨电极缺损音频检测系统设计[J].中国测试,2016,42(4):86-88.
[2] 李平,于立群,李婉秋.炭制品的均质质量与超声波声速检测[J].炭素,2002(2):41-43.
[3] WANG Y,SUN Y,LV P,et al.Detection of line weld defects based on multiple thresholds and support vector machine[J].NDT&E Int,2008,41(7):517-524.
[4] 周贤,刘义伦,李学军.炭素制品X射线图像缺陷的自动提取与分割[J].计算机应用,2006,26(5):1214-1216.
[5] 唐圣学. X射线底片图像处理系统 [D].长沙:湖南大学,2004.
[6] 刘辉,万文,熊震字.X射线焊缝图像的缺陷检测与识别技术[J].电焊机,2017,47(4):89-93.
[7] 禹晶,孙卫东,肖创柏.数字图像处理 [M].北京:机械工业出版社,2015:72-75.
[8] KALRA A,CHHOKAR R L.A hybrid approach using sobel and canny operator for digital image edge detection[C]//International Conference on Micro-Electronics and Telecommunication Engineering (ICMETE).IEEE,India:IEEE,2016:305-310.
[9] 陈顺,李登峰.融合Canny算子和形态学的齿轮图像边缘检测研究[J].机电工程,2020,37(7):821-825.
[10] XU J,WANG H S,HUANG H.Research of adaptive threshold edge detection algorithm based on statistics canny operator[C]//Ninth International Symposium on Multispectral Image Processing and Pattern Recognition(MIPPR).[S.l.]:SPIE,2015.
[11] 卞桂平,秦益霖.基于Canny算法的自适应边缘检测方法[J].电子设计工程,2017,25(10):53-56.
[12] 李丹丹,侯涛,魏世鹏.基于改进Canny算子的铁轨边缘检测算法[J].电视技术,2015,39(8):55-58.
[13] 杨帆. 数字图像处理与分析 [M].2版.北京:北京航空航天大学出版社,2010:240-243.
[14] 雷芳,熊建斌,柯文德.基于图像特征提取的管道X射线底片缺陷识别[J].广东石油化工学院学报,2016,26(6):24-27.
[15] 仲晓庆,蔡朝晖.基于MATLAB的几个图像处理实例[J].信息系统工程,2018(12):96-98.
[16] YE D,HONG G S,ZHANG Y,et al.Defect detection in selective laser melting technology by acoustic signals with deep belief networks[J].The International Journal of Advanced Manufacturing Technology,2018,96(1):2791-2801.
[17] CHEN Z,DENG S,CHEN X,et al.Deep neural networks-based rolling bearing fault diagnosis[J].Microelectronics Reliability,2017,75(8):327-333.
[18] 张艳霞. 基于受限玻尔兹曼机的深度学习模型及其应用 [D].成都:电子科技大学,2016.