高级检索

基于视觉的动力电池焊后质量检测

吴博尧1,2,秦磊3,张庆茂1,2,马琼雄1,2

吴博尧1,2,秦磊3,张庆茂1,2,马琼雄1,2. 基于视觉的动力电池焊后质量检测[J]. 焊接学报, 2018, 39(9): 122-128. DOI: 10.12073/j.hjxb.2018390237
引用本文: 吴博尧1,2,秦磊3,张庆茂1,2,马琼雄1,2. 基于视觉的动力电池焊后质量检测[J]. 焊接学报, 2018, 39(9): 122-128. DOI: 10.12073/j.hjxb.2018390237
WU Boyao1,2, QIN Lei3, ZHANG Qingmao1,2, MA Qiongxiong1,2. Research on vision-based post-welding quality inspection of power battery[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2018, 39(9): 122-128. DOI: 10.12073/j.hjxb.2018390237
Citation: WU Boyao1,2, QIN Lei3, ZHANG Qingmao1,2, MA Qiongxiong1,2. Research on vision-based post-welding quality inspection of power battery[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2018, 39(9): 122-128. DOI: 10.12073/j.hjxb.2018390237

基于视觉的动力电池焊后质量检测

基金项目: 华南师范大学青年教师科研培育基金(15KJ13);广东省科技项目(2013B090600045、2013B090200003、2014B010131004、2014B010124002、2014B090903014、2015B090920003、2016B090917002、2016B090926004);广东省自然科学基金(2016A030313456)

Research on vision-based post-welding quality inspection of power battery

  • 摘要: 为了对动力电池的焊后质量进行检测,针对检测时对比度低、背景复杂和干扰等问题,提出一种融合了动态阈值与全局阈值、行程处理和主成分分析-支持向量机(PAC-SVM)分类模型的焊后质量检测方法.首先,提出了一种结合动态阈值和全局阈值的混合阈值算法来分割焊缝和瑕疵;其次,利用形态学和行程处理来消除焊缝周边干扰得到更真实的焊缝边缘;最后,融合灰度特征、几何特征和矩特征建立7维特征向量的针孔模型,并采用带主成分分析的支持向量机检测针孔.结果表明,采用文中提出的方法,可获得良好的检测效果.
    Abstract: In order to inspect the post-welding quality of the power battery, this paper proposes a post-weld quality inspection method. This method combines the dynamic threshold and the global threshold, the runs processing and the PCA-SVM classification model for the problems of low contrast, complex background and interference. Firstly, a hybrid threshold algorithm combining dynamic threshold and global threshold is proposed to segment weld seam and defects. Secondly, get a more real edge of the weld seam though use morphology and runs processing to eliminate the interference around the weld seam; Finally, a 7-dimensional feature vector is designed from three aspects:gray features, geometric features and moments. The support vector machine model with principal component analysis is used to inspect pinholes. The results show that the proposed method can achieve good inspection quality.
  • [1] 陈文达. 金属工件表面瑕疵检测技术的研究与开发[D]. 江苏:江南大学, 2013.
    [2] 孙正军. 基于图像边缘提取的电池极片瑕疵检测研究[D]. 湖南:中南大学, 2009.
    [3] 郝淑丽, 赵宇明. 基于支持向量机的瑕疵检测算法[J]. 微计算机信息, 2008, 24(33):191-192 Hao Shuli, Zhao Yuming. Flaw detection based on support vector machine[J]. Microcomputer Information, 2008, 24(33):191-192, doi: 10.3969/j.issn.1008-0570.2008.33.076
    [4] 王雪. 基于主成分分析支持向量机的焊点检测方法的研究[D]. 河北:河北工业大学, 2014.
    [5] 韩青松, 贾振红, 杨杰, 等. 基于改进的Otsu算法的遥感图像阈值分割[J]. 激光杂志, 2010, 31(6):33-34 Han Qingsong, Jia Zhenhong, Yang Jie, et al. Remote sensing image thresholding segmentation based on the modified Otsu algorithm[J]. Laser Journal, 2010, 31(6):33-34, doi: 10.3969/j.issn.0253-2743.2010.06.018
    [6] 蔡梅艳, 吴庆宪, 姜长生. 改进Otsu法的目标图像分割[J]. 电光与控制, 2007, 14(6):118-119 Cai Meiyan, Wu Qingxian, Jiang Changsheng. Target image segmentation based on modified otsu algorithm[J]. Electronics Optics & Control, 2007, 14(6):118-119, doi: 10.3969/j.issn.1671-637X.2007.06.029
    [7] 高晶, 蔡幸福, 刘志强, 等. 基于区域生长的目标检测方法[J]. 北京工业大学学报, 2016, 42(6):856-861 Gao Jing, Cai Xingfu, Liu Zhiqiang, et al. Method of target detection based on region growing[J]. Journal of Beijing University of Technology, 2016, 42(6):856-861
    [8] Haris Kostas, Efstratiadis, Maglaveras Nicos, et al. Hybrid image segmentation using watersheds and fast region merging[J]. IEEE Transactions on Image Processing, 1998, 7(12):1684-1699. doi: 10.1109/83.730380
    [9] Mekhalfa Faiza, Nacereddine Nafaa. Multiclass classification of weld defects in radiographic images based on support vector machines[C]//Signal-Image Technology and Internet-Based Systems. IEEE, 2014.
    [10] Wang Yong, Guo Hui. Weld defect detection of X-ray images based on support vector machine[J]. Iete Technical Review, 2014, 31(2):137-142. doi: 10.1080/02564602.2014.892739
    [11] 朱政. V_支持向量分类机中若干问题的研究[D]. 上海:华东师范大学, 2016.
    [12] 王一丁, 李琛, 王蕴红, 等. 数字图像处理[M]. 西安:西安电子工业出版社, 2015.
    [13] Carsten Steger, Markus Ulrich, Christian Wiedemann, et al. 机器视觉算法与应用[M]. 北京:清华大学出版社, 2008.
    [14] 郭明玮, 赵宇宙, 项俊平, 等. 基于支持向量机的目标检测算法综述[J]. 控制与决策, 2014, 29(2):193-200 Guo Mingwei, Zhao Yuzhou, Xiang Junping, et al. Review of object detection methods based on SVM[J]. Control and Decision, 2014, 29(2):193-200
    [15] 陈英, 杨丰玉, 符祥. 基于支持向量机和灰度共生矩阵的纹理图像分割方法[J]. 传感器与微系统, 2012, 31(9):60-63 Chen Ying, Yang Fengyu, Fu Xiang. Method of texture image segmentation based on SVM and gray level co-occurrence matrix[J]. Transducer and Microsystem Technologies, 2012, 31(9):60-63, doi: 10.3969/j.issn.1000-9787.2012.09.017
    [16] Flusser Jan, Suk Tomas. Pattern recognition by affine moment invariants[J]. Pattern Recognition, 1993, 26(1):168-174.
    [17] 李东红, 宋立新, 牛滨. 一种改进分水岭乳腺肿块图像分割方法[J]. 哈尔滨理工大学学报, 2015, 20(5):25-29 Li Donghong, Song Lixin, Niu Bin. An improved watershed segmentation algorithm for mammographic masses images[J]. Journal of Harbin University of Science and Technology, 2015, 20(5):25-29
    [18] 佟彤. 基于X射线图像的焊缝缺陷检测与识别研究[D]. 上海:上海交通大学, 2014.
    [19] 章毓晋. 图象分割评价技术分类和比较[J]. 中国图像图形学报, 1996, 1(2):151-158 Zhang Yujin. A classification and comparsion of evaluation techniques for image segmentation[J]. Journal of Image and Graphics, 1996, 1(2):151-158
  • 期刊类型引用(2)

    1. 孙树红,徐姗姗. 家蚕嗅觉毛捕捉性信息素的建模与仿真. 计算机与数字工程. 2020(01): 51-56 . 百度学术
    2. 奚小波,史扬杰,单翔,张琦,金亦富,龚俊杰,张剑峰,张瑞宏. 基于Bezier曲线优化的农机自动驾驶避障控制方法. 农业工程学报. 2019(19): 82-88 . 百度学术

    其他类型引用(2)

计量
  • 文章访问数:  813
  • HTML全文浏览量:  18
  • PDF下载量:  282
  • 被引次数: 4
出版历程
  • 收稿日期:  2017-04-25

目录

    /

    返回文章
    返回