基于机器视觉的太阳能电池片表面缺陷检测研究现状及展望

钱晓亮; 张鹤庆; 陈永信; 曾黎; 刁智华; 刘玉翠; 杨存祥

doi:10.11936/bjutxb2016040063

基于机器视觉的太阳能电池片表面缺陷检测研究现状及展望

doi: 10.11936/bjutxb2016040063

1.
郑州轻工业学院电气信息工程学院, 郑州 450002
2.
许继集团有限公司, 河南许昌 461000

基金项目: 国家自然科学基金资助项目(61501407)；河南省高等学校重点科研项目(15A413006)；河南省科技厅重点科技攻关项目(132102110150)

详细信息

作者简介:
作者简介: 钱晓亮(1982—), 男, 副教授, 主要从事模式识别与机器学习方面的研究, E-mail:qxl_sunshine@163.com

通讯作者:
杨存祥(1966—), 男, 教授, 主要从事电气测量、智能控制和电气故障诊断方面的研究, E-mail:yangzzha@126.com

中图分类号: TP391.4
计量
- 文章访问数: 346
- HTML全文浏览量: 93
- PDF下载量: 0
- 被引次数: 0
出版历程
- 收稿日期: 2016-04-18
- 网络出版日期: 2022-09-09
- 刊出日期: 2017-01-01

Research Development and Prospect of Solar Cells Surface Defects Detection Based on Machine Vision

1.
College of Electric and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China
2.
Xuji Croup Corporation, Xuchang 461000, Henan,China

摘要

摘要: 鉴于基于机器视觉的太阳能电池片表面缺陷检测方法具有操作简便、检测精度高的优势,对此类方法所涉及的各个环节进行了综述. 首先,对太阳能电池片表面的各种成像方式和常见缺陷类型进行了归纳总结;其次,对现有的检测方法按照数学建模思路的不同进行了分类介绍和对比分析;最后,对内容进行了小结并对太阳能电池片表面缺陷检测方法的后续研究进行了展望. 可以看出:基于机器视觉的太阳能电池片表面缺陷检测方法已经取得了较大的发展,但在特征提取算法设计方面仍有改进空间,如基于深度神经网络的特征提取算法.
- 太阳能电池片 /
- 机器视觉 /
- 表面缺陷 /
- 成像
Abstract: Considering the advantages of simple operation and high detecting accuracy, all aspects involved in solar cell surface defect detection methods based on machine vision were reviewed in this paper. First of all, the various imaging techniques and common defect types of solar cells surface were summarized. Secondly, the existing detection methods were introduced and compared with each other according to the different idea of mathematical modeling. Finally, a brief summary of this article and perspective of future research are presented. It can be concluded that the solar cell surface defect detection methods based on machine vision have made great progress. However, there is still room for improvement in algorithm design of feature extraction, such as feature extraction algorithm based on deep neural networks.
- solar cell /
- machine vision /
- surface defect /
- imaging
The authors have declared that no competing interests exist.

HTML全文

图 1 太阳能电池片的3种成像图像

Figure 1. Three types of images of solar cells

下载: 全尺寸图片幻灯片

图 2 近红外成像各类缺陷示例^[31]

Figure 2. Illustrations of various defects based on near infrared imaging

下载: 全尺寸图片幻灯片

图 3 基于机器视觉的太阳能电池片表面缺陷检测示例

Figure 3. Illustrations of solar cells surface defects detection based on machine vision

下载: 全尺寸图片幻灯片

图 4 Anwar等^[14]算法框图

Figure 4. Block diagram of Anwar etc.^[14]

下载: 全尺寸图片幻灯片

图 5 Demant等^[49]算法流程框图

Figure 5. Flow chart of Demant etc.^[49]

下载: 全尺寸图片幻灯片

表 1 太阳能电池片表面常见缺陷^[36]

Table 1. Common defects of solar cell surface

缺陷类别	缺陷名称	视觉特点	成因
形状缺陷	缺角、破损、裂纹、断栅	与标准片相比,形状上有缺损或者多余部分	误切割、碰撞、生产失误
颜色缺陷	颜色异常、不均匀,边角区域颜色异常	与标准片相比,大部分区域存在着颜色异常或者不均匀	镀膜时化学反应不均匀
纹理缺陷	斑点、指纹、轮印	与标准片相比,存在过亮或者过暗区域,有斑点状或指纹、轮印	人工操作不当、机器压力过大

下载: 导出CSV

表 2 各类检测方法的比较

Table 2. Comparison of various detection methods

类型	梯度特征的检测方法	聚类的检测方法	频域分析的检测方法	矩阵分解的检测方法	机器学习的检测方法
摘要	根据电池片的裂纹、断栅处和背景有明显亮度差异的特点,以梯度特征为核心进行缺陷检测	采用各种聚类算法将电池片表面分成缺陷集合和非缺陷集合,然后采用图像分割得到检测结果	将图像从空间域变换到频率域,通过设定合适的频率值做带通(带阻)滤波,实现预定目标的凸显(移出)	将电池片表面图像数据视作矩阵,通过某些矩阵分解算法分解出仅包含电池片缺陷区域的矩阵,将该矩阵适当处理后作为检测结果	分别收集无缺陷和有缺陷的图像作为训练样本,选择合适的机器学习算法学习分类模型,将测试图像代入该模型即得检测结果
特点	此类方法对裂纹和断栅等亮度对比度较强的缺陷类型检测效果较好	此类方法对不同类型的缺陷有较强的识别能力,但是聚类算法某些关键参数需要手工设定	此类方法复杂度低,实时性较好,对于检测斑点、断栅、裂纹有较好的效果	此类方法适用范围广,算法简洁有效,尤其适合对微小缺陷的检测	此类方法对训练样本中已收集的常见缺陷类型能够较好识别

下载: 导出CSV

参考文献(54)

[1]	CARCIA P F, MCLEAN R S, HEGEDUS S.ALD moisture barrier for Cu(InGa)Se2 solar cells[J]. Ecs Transactions, 2010, 33(2): 237-243.
[2]	DUENAS S, PEREZ E, CASTAN H, et al.The role of defects in solar cells: control and detection defects in solar cells[C]//The Spanish 2013 Conference on Electron Devices (CDE). New York: IEEE, 2013: 301-304.
[3]	ISTROV A A, HIESLMAIR H, VYVENKO O F, et al.Defect recognition and impurity detection techniques in crystalline silicon for solar cells[J]. Solar Energy Materials & Solar Cells, 2002, 72(1): 441-451.
[4]	TSUZUKI K M, TSUTOMU Y, TAKEHIO T, et al. Inspection method and production method of solar cell module: US6271462B1[P].2001-08-07.
[5]	ESQUIVEL O. Contrast imaging method for inspecting specular surface devices: US6433867B1[P].2002-08-13.
[6]	SAWYER D E, KESSLER H K.Laser scanning of solar cells for the display of cell operating characteristics and detection of cell defects[J]. IEEE Transactions on Electron Devices, 1980, 27(4): 864-872.
[7]	CHEN X Y, PEDERSEN A, HELLESØ O G, et al.Electrical noise of laser diodes measured over a wide range of bias currents[J]. Microelectronics Reliability, 2000, 40(11): 1925-1928.
[8]	BELYAEV A, POLUPAN O, OSTAPENKO S, et al.Resonance ultrasonic vibration diagnostics of elastic stress in full-size silicon wafers[J]. Semiconductor Science and Technology, 2006, 21(3): 254.
[9]	BYELYAYEV A.Stress diagnostics and crack detection in full-size silicon wafers using resonance ultrasonic vibrations[D]. Tampa Bay: University of South Florida, 2005.
[10]	OSTAPENKO S, DALLAS W, HESS D, et al.Crack detection and analyses using resonance ultrasonic vibrations in crystalline silicon wafers[C]//The 2006 IEEE 4th World Conference on Photovoltaic Energy Conversion. New York: IEEE, 2006: 920-923.
[11]	DALLAS W, POLUPAN O, OSTAOENKO S.Resonance ultrasonic vibrations for crack detection in photovoltaic silicon wafers[J]. Measurement Science & Technology, 2007, 18(3): 852-858.
[12]	ZHANG X, HU J, WU Y, et al.Direct observation of defects in triple-junction solar cell by optical deep-level transient spectroscopy[J]. Journal of Physics D: Applied Physics, 2009, 42(14): 145401-145405.
[13]	WEN T K, YIN C C.Crack detection in photovoltaic cells by interferometric analysis of electronic speckle patterns[J]. Solar Energy Materials & Solar Cells, 2011, 98(5): 216-223.
[14]	FUYUKI T, KITIYANAN A.Photographic diagnosis of crystalline silicon solar cells utilizing electroluminescence[J]. Applied Physics A: Materials Science & Processing, 2009, 96(1): 189-196.
[15]	XU P, ZHOU W J, FEI M R.Detection methods for micro-cracked defects of photovoltaic modules based on machine vision[C]//The 2014 IEEE 3rd International Conference on Cloud Computing and Intelligence Systems (CCIS). New York: IEEE, 2014: 609-613.
[16]	TSAI D M, WU S C, LI W C.Defect detection of solar cells in electroluminescence images using Fourier image reconstruction[J]. Solar Energy Materials & Solar Cells, 2012, 99(99): 250-262.
[17]	TAKAHASHI Y, KAJI Y, OGANE A, et al.“Luminoscopy”-novel tool for the diagnosis of crystalline silicon solar cells and modules utilizing electroluminescence[C]//The 2006 IEEE 4th World Conference on Photovoltaic Energy Conversion. New York: IEEE, 2006: 924-927.
[18]	GABOR A M, RALLI M, MONTMINY S, et al.Soldering induced damage to thin Si solar cells and detection of cracked cells in modules[C]//The 21st European Photovoltaic Solar Energy Conference. New York: IEEE, 2006: 4-8.
[19]	CHATURVEDI P, HOEX B, WALSH T M.Broken metal fingers in silicon wafer solar cells and PV modules[J]. Solar Energy Materials & Solar Cells, 2013, 108(1): 78-81.
[20]	DEMANT M R S, KRISCH J, SCHOENFELDER S, et al. Detection and analysis of micro-cracks in multi-crystalline silicon wafers during solar cell production[C]//The 2011 37th IEEE Conference on Photovoltaic Specialists Conference (PVSC) . New York: IEEE, 2011: 001641-001646.
[21]	OLSEN E, FL A S.Spectral and spatially resolved imaging of photoluminescence in multicrystalline silicon wafers[J]. Applied Physics Letters, 2011, 99(1): 011903-011903-3.
[22]	SUN Q, MELNIKOV A. MANDELIS A.Camera-based high frequency heterodyne lock-in carrierographic (frequency-domain photoluminescence) imaging of crystalline silicon wafers[J]. Physica Status Solidi(a), 2016, 213(2): 405-411.
[23]	CHEN J T, KE S S, LIN K W, et al.High-performance inspecting system for detecting micro-crack defects of solar wafer[C]//The 2010 IEEE Conference on Sensors. New York: IEEE, 2010: 494-497.
[24]	CHIOU Y C, LIU J, LIANG Y T.Micro crack detection of multi-crystalline silicon solar wafer using machine vision techniques[J]. Sensor Review, 2011, 31(2): 154-165.
[25]	BROOKS W S M, LAMB D A, IRVINE S J C. IR reflectance imaging for crystalline Si solar cell crack detection[J]. IEEE Journal of Photovoltaics, 2015, 5(5): 1271-1275.
[26]	KIM G B.Micro defect detection in solar cell wafer based on hybrid illumination and near-infrared optics[C] ∥The 2013 9th Asian Control Conference(ASCC) . New York: IEEE, 2013: 1-5.
[27]	MAHDAVIPOUR Z, ABDULLAH M Z.Micro-crack detection of polycrystalline silicon solar wafer[J]. Iete Technical Review, 2015, 32(6): 1-7.
[28]	KO S S, LIU C S, LIN Y C.Optical inspection system with tunable exposure unit for micro-crack detection in solar wafers[J]. Optik - International Journal for Light and Electron Optics, 2013, 124(124): 4030-4035.
[29]	TEO T W, MAHDAVIPOUR Z, ABDULLAH M Z.High-speed micro-crack detection of solar wafers with variable thickness[C]//The 2014 IEEE International Conference on Imaging Systems and Techniques (IST) . New York: IEEE, 2014: 237-241.
[30]	DONG D, CHEN G M.A method of silicon solar cells defect detection based on near-infrared images[J]. Information & Electronic Engineering, 2010, 8(5): 539-543. (in Chinese)
[31]	WANG N.Silicon solar cell based on visual detection method[D]. Baoding: Agricultural University of Hebei, 2014. (in Chinese)
[32]	MINKEVI<inline-graphic href="0254-0037-43-1-76/img_6.jpg"/>IUS L, SUZANOVIC<inline-graphic href="0254-0037-43-1-76/img_7.jpg"/>IEN<inline-graphic href="0254-0037-43-1-76/img_8.jpg"/> R, BALAKAUSKAS S, et al. Detection of tab wire soldering defects on silicon solar cells using terahertz time-domain spectroscopy[J]. Electronics Letters, 2012, 48(15): 932-934.
[33]	JEN C Y, RICHTER C.Doping profile recognition applied to silicon photovoltaic cells using terahertz time-domain spectroscopy[J]. IEEE Transactions on Terahertz Science and Technology, 2014, 4(5): 560-567.
[34]	ABBOTT M, COUSINS P, CHEN F, et al.Laser-induced defects in crystalline silicon solar cells[C]//The Thirty-first IEEE Conference on Photovoltaic Specialists. New York: IEEE, 2005: 1241-1244.
[35]	KONTGES M, KUNZE I, KAIARI S S, et al.The risk of power loss in crystalline silicon based photovoltaic modules due to micro-cracks[J]. La Medicina Del Lavoro, 2011, 95(4): 1131-1137.
[36]	WANG H.Polysilicon solar wafer surface defect detection and the design and development of software inspection system[D]. Shanghai: Shanghai Jiao Tong University, 2014. (in Chinese)
[37]	ANWAR S A. ABDULLAH M Z.Micro-crack detection of multicrystalline solar cells featuring an improved anisotropic diffusion filter and image segmentation technique[J]. Eurasip Journal on Image & Video Processing, 2014, 2014(1): 1-17.
[38]	TSAI D M.Micro-crack inspection in heterogeneously textured solar wafers using anisotropic diffusion[J]. Image and Vision Computing, 2010, 28(3): 491-501.
[39]	BAKALEXIS S A, BOUTALIS Y S, MERTZIOS B G.Edge detection and image segmentation based on nonlinear anisotropic diffusion[C]//The 2002 14th International Conference on Digital Signal Processing. New York: IEEE, 2002: 1203-1206.
[40]	TSAI D M, LUO J Y.Mean shift-based defect detection in multicrystalline solar wafer surfaces[J]. IEEE Transactions on Industrial Informatics, 2011, 7(1): 125-135.
[41]	AGHAMOHAMMADI A H, PRABUWONO A S.Solar cell panel crack detection using particle swarm optimization algorithm[C]//The 2011 International Conference on Pattern Analysis and Intelligent Robotics (ICPAIR). Putrajaya: IEEE, 2011: 160-164.
[42]	KENNEDY J, EBERHART R.Particle swarm optimization[C]//The IEEE International Conference on Neural Networks. New York: IEEE, 1995: 1942-1948.
[43]	FU Z, ZHAO Y, LIU Y, et al.Solar cell crack inspection by image processing[C]//The 2004 International Conference on Business of Electronic Product Reliability and Liability. New York: IEEE, 2004: 77-80.
[44]	TSAI D M, LI G N, LI W C, et al.Defect detection in multi-crystal solar cells using clustering with uniformity measures[J]. Advanced Engineering Informatics, 2015, 29(3): 419-430.
[45]	LIW C, TSAI D M.Wavelet-based defect detection in solar wafer images with inhomogeneous texture[J]. Pattern Recognition, 2012, 45(2): 742-756.
[46]	WANG Z.Research on detection technology for solar cells multi-defects in complicated background[J]. Journal of Information & Computational Science, 2014, 11(2): 449-459.
[47]	LU C J, TSAI D M.Automatic defect inspection for LCDs using singular value decomposition[J]. International Journal of Advanced Manufacturing Technology, 2005, 25(1): 53-61.
[48]	YAO M H, LI J, WANG X B.Solar cell surface defects detection using RPCA method[J]. Chinese Journal of Computers, 2013, 36(9): 1943-1952. (in Chinese)
[49]	DEMANT M, WELSCHEHOLD T, OSWALD M, et al.Microcracks in silicon wafers Ⅰ: inline detection and implications of crack morphology on wafer strength[J]. IEEE Journal of Photovoltaics, 2016, 6(1): 1-10.
[50]	GONG F, ZHANG X W, SUN H.Detection system for solar module surface defects based on constrained ICA model and PSO method[J]. Acta Optica Sinica, 2012(4): 169-177. (in Chinese)
[51]	TSAI D M, WU S C, CHIU W Y.Defect detection in solar modules using ICA basis images[J]. IEEE Transactions on Industrial Informatics, 2013, 9(1): 122-131.
[52]	JENSSEN R, ELTOFT T.Independent component analysis for texture segmentation[J]. Pattern Recognition, 2003, 36(10): 2301-2315.
[53]	WANG X B, LI J, YAO M H, et al.Solar cells surface defects detection based on deep learning[J]. PR&AI, 2014, 27(6): 517-523. (in Chinese)
[54]	ZHAO R, OUYANG W, LI H, et al.Saliency detection by multi-context deep learning[C]//The 2015 IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2015: 1265-1274.