摘要
针对目前国内外热电池内部装配缺陷检测准确度不高的问题,研究一种基于图像检测热电池内部的单体热电池缺陷的检测方法。其中分析了单体热电池整体倒装、单体热电池装配次序、单体热电池漏装集流片3种常见的缺陷的特征,利用改进的灰度共生矩阵、HU不变矩和模板匹配三种算法对单体热电池进行缺陷分析。最后利用分类回归树(CART)进行检测,提出一种按权重分配参数的检测方法,实验结果表明,这种方法准确度达到97.5%满足检测要求,为热电池缺陷检测提供了有效途径。
A method for detecting defects of monomer thermal battery inside the thermal battery is proposed in this paper, which aimed at the problem of the low accuracy of internal assembly fault detection at home and abroad. This detection includes three defects, the overall flip-chip of the monomer thermal battery, the assembly sequence of the monomer thermal battery, and the leakage of the monomer thermal battery part are analyzed. Using the improved gray level co-occurrence matrix, HU invariant moment, template matching to analyze the defects of monomer thermal batteries. Finally, proposing a detection method based on weight distribution parameters, which is using CART(Classification and Regression Tree) decision tree for detection. The experimental results show that the accuracy of this method reaches 97.5% and meets the testing requirements, which provides an effective way for thermal battery defect detection.
引文
[1] 王传东.热电池发展综述[J].电源技术,2013,37(11):2077-2079.WANG CH D.Development of thermal battery[J].Chinese Journal of Power Sources,2013,37(11):2077-2079.
[2] 高艳,刘合财,龚敏庆.热电池的可靠性模型[J].贵阳学院学报(自然科学版),2010, 5(3):52-54.GAO Y, LIU H C, GONG M Q. Reliability model of thermal battery[J]. Journal of Guiyang University(Natural Science Edition), 2010, 5(3): 52-54.
[3] 瞿丹晨,刘正国.热电池参数测试与控制系统[J].微计算机信息,2006, 10 (S):91-93.YAN D C, LIU Z G. Thermal battery parameter test and control system [J]. Microcomputer Information, 2006, 10 (S): 91-93.
[4] 刘磊,王冲,赵树旺,等.基于机器视觉的太阳能电池片缺陷检测技术的研究[J].电子测量与仪器学报,2018,32(10):47-52.LIU L,WANG CH,ZHAO SH W.Research on solar cells defect detection technology based on machine vision[J].Journal of Electronic Measurement and Instrumentation,2018,32(10):47-52.
[5] 韩洪伟,赵晓云.基于机器视觉的高速切片机锂电池极片在线检测系统设计[J].电源世界,2017(5):34-36.HAN H W,ZHAO X Y.Design of on-line detection system for lithium battery pole piece of high speed slicer based on machine vision[J].The World of Power Supply,2017(5):34-36.
[6] 方浩,李瑜煜,陈观应,等.一种改进的干电池图像增强方法[J].中国科技信息,2016(9):106-107,12.FANG H,LI Y Y,CHEN G Y, et al.Improved dry battery image enhancement method[J].China Science and Technology Information,2016(9):106-107,12.
[7] 孙智权,周奇,陈震,等.基于CMOS图像传感器的太阳能电池缺陷检测系统设计[J].仪表技术与传感器,2018(1):60-63.SUN ZH Q,ZHOU Q,CHEN ZH,et al.Design of solar cell defects detection system based on CMOS image sensor[J].Instrument Technique and Sensor,2018(1):60-63.
[8] 张伟,何金国.Hu不变矩的构造与推广[J].计算机应用,201O,30(9):2449-2452.ZHANG W, HE J G. Construction and extension of Hu invariant moments[J]. Computer Application, 2010, 30(9): 2449-2452.
[9] 翟俊海,赵文秀,王熙照.图像特征提取研究[J].河北大学学报,2009,29(1):106-110.ZHAI J H,ZHAO W X,WANG X ZH.Research on the image feature extraction [J].Journal of Hebei University 2009,29(1):106-110.
[10] 原玥,王宏,原培新,等.一种改进的Hu不变矩算法在存储介质图像识别中的应用[J].仪器仪表学报,2016,37(5):1042-1048.YUAN Y, Wang H,YUAN P X.An improved Hu invariant moment algorithm for storage mediumImage-recognition[J].Chinese Journal of Scientific Instrument,2016,37(5):1042-1048.
[11] BAGRI N, JOHARI P K.A comparative study on feature extraction using texture and shape for content based image retrieval[J].International Journal of Advanced Science and Technology,2015(80):41-52.
[12] 颜佩,丁亚军,钱盛友,等.基于小波系数Hu矩的生物组织损伤监测方法[J].电子测量与仪器学报,2016,30(7):1062-1067.YAN P,DING Y J,QIAN SH Y,Biological tissue damage monitoring method based on wavelet coefficient Hu moment[J].Journal of Electronic Measurement and Instrumentation,2016,30(7):1062-1067.
[13] 孔月萍,王亚安,王快社.基于不变矩的带钢数字图像的缺陷检测算法[J].无损检测,2010,32(1):6-8.KONG Y P,WANG Y A,WANG K SH.An inspecting algorithm for surface defect of steel strip based on moment invariant[J].Nondestructive Testing,2010,32(1):6-8.
[14] MOHANAIAH P,SATHYANARAYANA P,GURUKUMAR L.Image texture feature extraction using GLCM approach[J].International Journal of Scientific and Research, 2013,3(5):290-294
[15] 景军锋,邓淇英,李鹏飞,等.LBP和GLCM融合的织物组织结构分类[J].电子测量与仪器学报,2015,29(9):1406-1413.JING J F,DENG Q Y,LI P F,et al.Fabric structure classification based on LBP and GLCM fusion[J].Journal of Electronic Measurement and Instrumentation,2015,29(9):1406-1413.
[16] 苏杰,王丙勤,郭立.数字图像的纹理特征提取与分类研究[J].电子测量技术,2008,31(5):52-55.SU J,WANG B Q,GUO L.Textural feature extraction and classification study research of digital image[J].Electronic Measurement Technology,2008,31(5):52-55.
[17] 邹明明,卢迪.基于改进模板匹配的车牌字符识别算法实现[J].国外电子测量技术,2010,29(1):59-61,80.ZOU M M,LU D.Recognition algorithm of car license plate characters based on modified template match[J].Foreign Electronic Measurement Technology,2010,29(1):59-61,80.
[18] 张建华.基于灰度的模板匹配算法研究[D]. 呼和浩特:内蒙古农业大学,2013.ZHANG J H.Study on template matching algorithms based on gray value[D]. Huhehaote: Inner Mongolia Agricultural University,2013.
[19] PERVEEN N,KUMAR D,BHARDWAJ I. An overview on template matching methodologies and its applications[J].International Journal of Research in Computer and Communication Technology,2013,2(10):988-995.