Automatic recognition of defects in plasma-facing material using image processing technology

Jianhua LYU; Chunjie NIU; Yunqiu CUI; Chao CHEN; Weiyuan NI; Hongyu FAN

doi:10.1088/2058-6272/ace9af

Plasma Science and Technology > 2023 > 25(12): 125603. > DOI: 10.1088/2058-6272/ace9af

Jianhua LYU, Chunjie NIU, Yunqiu CUI, Chao CHEN, Weiyuan NI, Hongyu FAN. Automatic recognition of defects in plasma-facing material using image processing technology[J]. Plasma Science and Technology, 2023, 25(12): 125603. DOI: 10.1088/2058-6272/ace9af

Citation:

PDF (1679 KB)

Automatic recognition of defects in plasma-facing material using image processing technology

1.
School of Electrical Engineering, Dalian University of Technology, Dalian 116024, People's Republic of China
2.
School of Science, Jiangnan University, Wuxi 214122, People's Republic of China

More Information

Corresponding author:
Weiyuan NI, E-mail: nwy@dlut.edu.cn
Received Date: May 05, 2023
Revised Date: July 19, 2023
Accepted Date: July 20, 2023
Available Online: January 04, 2024
Published Date: September 10, 2023

Graphical Abstract

Abstract

Abstract

Observing and analyzing surface images is critical for studying the interaction between plasma and irradiated plasma-facing materials. This paper presents a method for the automatic recognition of bubbles in transmission electron microscope (TEM) images of W nanofibers using image processing techniques and convolutional neural network (CNN). We employ a three-stage approach consisting of Otsu, local-threshold, and watershed segmentation to extract bubbles from noisy images. To address over-segmentation, we propose a combination of area factor and radial pixel intensity scanning. A CNN is used to recognize bubbles, outperforming traditional neural network models such as AlexNet and GoogleNet with an accuracy of 97.1% and recall of 98.6%. Our method is tested on both clear and blurred TEM images, and demonstrates human-like performance in recognizing bubbles. This work contributes to the development of quantitative image analysis in the field of plasma-material interactions, offering a scalable solution for analyzing material defects. Overall, this study's findings establish the potential for automatic defect recognition and its applications in the assessment of plasma-material interactions. This method can be employed in a variety of specialties, including plasma physics and materials science.
- image processing,
- automatic defect analysis,
- object detection,
- convolutional neural network

FullText(HTML)

Acknowledgments

This work is supported by the National Key R&D Program of China (No. 2017YFE0300106), Dalian Science and Technology Star Project (No. 2020RQ136), the Central Guidance on Local Science and Technology Development Fund of Liaoning Province (No. 2022010055-JH6/100), and the Fundamental Research Funds for the Central Universities (No. DUT21RC(3)066).

References (29)

References

[1]	De Temmerman G, Hirai T and Pitts R A 2018 Plasma Phys. Control. Fusion 60 044018 doi: 10.1088/1361-6587/aaaf62
[2]	Kajita S et al 2009 Nucl. Fusion 49 095005 doi: 10.1088/0029-5515/49/9/095005
[3]	Liu L et al 2016 J. Nucl. Mater. 471 1 doi: 10.1016/j.jnucmat.2016.01.001
[4]	Li Y G et al 2020 Tungsten 2 34 doi: 10.1007/s42864-020-00042-w
[5]	Cui Y Q et al 2022 Plasma Phys. Control. Fusion 64 015002 doi: 10.1088/1361-6587/ac36e6
[6]	Li X P et al 2021 J. Nucl. Mater. 557 153319 doi: 10.1016/j.jnucmat.2021.153319
[7]	Niu C J et al 2021 Fusion Eng. Des. 163 112159 doi: 10.1016/j.fusengdes.2020.112159
[8]	Wang S W et al 2020 J. Nucl. Mater. 532 152051 doi: 10.1016/j.jnucmat.2020.152051
[9]	Novotna V et al 2020 Microsc. Today 28 38 doi: 10.1017/S1551929520000875
[10]	Taylor C N 2022 J. Nucl. Mater. 558 153396 doi: 10.1016/j.jnucmat.2021.153396
[11]	de Haan K et al 2019 Sci. Rep. 9 12050 doi: 10.1038/s41598-019-48444-2
[12]	Kajita S et al 2015 New J. Phys. 17 043038 doi: 10.1088/1367-2630/17/4/043038
[13]	Kodera M et al 2018 Jpn. J. Appl. Phys. 57 04FC04 doi: 10.7567/JJAP.57.04FC04
[14]	Chen D L et al 2019 J. Electron. Imaging 28 053018 doi: 10.1117/1.JEI.28.5.053023
[15]	Anderson C et al 2019 arXiv: 1912.04252 [physics. app-ph]
[16]	Shen M R et al 2021 Comput. Mater. Sci. 197 110560 doi: 10.1016/j.commatsci.2021.110560
[17]	Van Roessel A, Von Toussaint U and Manhard A 2021 Nucl. Mater. Energy 29 101082 doi: 10.1016/j.nme.2021.101082
[18]	Niu C J et al 2022 J. Nucl. Mater. 572 154062 doi: 10.1016/j.jnucmat.2022.154062
[19]	Wang M Y et al 2014 A new image denoising method based on Gaussian filter Proc. 2014 Int. Conf. on Information Science, Electronics and Electrical Engineering Sapporo vol 163 (Piscataway, NJ: IEEE)
[20]	Demir Y and Kaplan N H 2023 Digit. Signal Process. 138 104054 doi: 10.1016/j.dsp.2023.104054
[21]	Fan H D et al 2017 Comput. Biol. Med. 85 75 doi: 10.1016/j.compbiomed.2017.03.025
[22]	Niu Z D and Li H D 2019 J. Phys. Conf. Ser. 1237 022122 doi: 10.1088/1742-6596/1237/2/022122
[23]	Zhang Y and Xu D Q 2012 Adv. Mater. Res. 546–547 464
[24]	Vincent L 1993 IEEE Trans. Image Process. 2 176 doi: 10.1109/83.217222
[25]	Krizhevsky A, Sutskever I and Hinton G E 2017 Commun. ACM 60 84 doi: 10.1145/3065386
[26]	Simonyan K and Zisserman A 2014 arXiv: 1409.1556 [cs. CV]
[27]	Khan R U, Zhang X S and Kumar R 2019 J. Comput. Virol. Hack. Tech. 15 29 doi: 10.1007/s11416-018-0324-z
[28]	Wu Z F, Shen C H and van den Hengel A 2019 Pattern Recognit. 90 119 doi: 10.1016/j.patcog.2019.01.006
[29]	Kong J B and Jang M S 2019 J. Korea Inst. Electron. Commun. Sci. 14 1153 doi: 10.13067/JKIECS.2019.14.6.1153

[1]	Jianqing CAI, Yunfeng LIANG, Alexander KNIEPS, Dongkai QI, Erhui WANG, Haoming XIANG, Liang LIAO, Jie HUANG, Jie YANG, Jia HUANG, Jianwen LIU, Philipp DREWS, Shuai XU, Xiang GU, Yichen GAO, Yu LUO, Zhi LI, the EXL-50 Team. Improved training framework in a neural network model for disruption prediction and its application on EXL-50[J]. Plasma Science and Technology, 2024, 26(5): 055102. DOI: 10.1088/2058-6272/ad1571
[2]	Kaixuan YE, Zhen ZHOU, Tao ZHANG, Jiuyang MA, Yumin WANG, Gongshun LI, Kangning GENG, Mingfu WU, Fei WEN, Jia HUANG, Yang ZHANG, Linming SHAO, Shuqi YANG, Fubin ZHONG, Shanlu GAO, Lin YU, Ziqiang ZHOU, Haoming XIANG, Xiang HAN, Shoubiao ZHANG, Guoqiang LI, Xiang GAO, the EAST Team. Experimental study of core MHD behavior and a novel algorithm for rational surface detection based on profile reflectometry in EAST[J]. Plasma Science and Technology, 2024, 26(3): 034010. DOI: 10.1088/2058-6272/ad0f0a
[3]	Shulei ZHENG, Qiuyue NIE, Tao HUANG, Chunfeng HOU, Xiaogang WANG. Improvement of atmospheric jet-array plasma uniformity assisted by artificial neural networks[J]. Plasma Science and Technology, 2023, 25(2): 025403. DOI: 10.1088/2058-6272/ac8dd6
[4]	Hui LI (李慧), Yanlin FU (付艳林), Jiquan LI (李继全), Zhengxiong WANG (王正汹). Machine learning of turbulent transport in fusion plasmas with neural network[J]. Plasma Science and Technology, 2021, 23(11): 115102. DOI: 10.1088/2058-6272/ac15ec
[5]	Kai ZHANG (张凱), Dalong CHEN (陈大龙), Bihao GUO (郭笔豪), Junjie CHEN (陈俊杰), Bingjia XIAO (肖炳甲). Density limit disruption prediction using a long short-term memory network on EAST[J]. Plasma Science and Technology, 2020, 22(11): 115602. DOI: 10.1088/2058-6272/abb28f
[6]	Xueqiang CAO (曹学强), Li ZHANG (张立), Zhongchen WU (武中臣), Zongcheng LING (凌宗成), Jialun LI (李加伦), Kaichen GUO (郭恺琛). Quantitative analysis modeling for the ChemCam spectral data based on laser-induced breakdown spectroscopy using convolutional neural network[J]. Plasma Science and Technology, 2020, 22(11): 115502. DOI: 10.1088/2058-6272/aba5f6
[7]	Baoyue CHAI (柴宝玥), Yingying LI (李颖颖), Ze CHEN (陈泽), Wei TAO (陶巍), Yixuan ZHOU (周艺轩), Shifeng MAO (毛世峰), Zhengping LUO (罗正平), Yi YU (余羿), Bo LYU (吕波), Minyou YE (叶民友). Fast estimation of ion temperature from EAST charge exchange recombination spectroscopy using neural network[J]. Plasma Science and Technology, 2019, 21(10): 105103. DOI: 10.1088/2058-6272/ab2674
[8]	Chengxu LU (吕程序), Bo WANG (王博), Xunpeng JIANG (姜训鹏), Junning ZHANG (张俊宁), Kang NIU (牛康), Yanwei YUAN (苑严伟). Detection of K in soil using time-resolved laser-induced breakdown spectroscopy based on convolutional neural networks[J]. Plasma Science and Technology, 2019, 21(3): 34014-034014. DOI: 10.1088/2058-6272/aaef6e
[9]	GUO Tangtang (郭瑭瑭), LIU Xingliang (刘星亮), HAO Shiqiang (郝世强), et al.. Prediction of Equivalent Electrical Parameters of Dielectric Barrier Discharge Load Using a Neural Network[J]. Plasma Science and Technology, 2015, 17(3): 196-201. DOI: 52.80.?s
[10]	DING Yonghua (丁永华), JIN Xuesong (金雪松), CHEN Zhenzhen (陈真真), ZHUANG Ge (庄革). Neural Network Prediction of Disruptions Caused by Locked Modes on J-TEXT Tokamak[J]. Plasma Science and Technology, 2013, 15(11): 1154-1159. DOI: 10.1088/1009-0630/15/11/14