枪械内膛疵病检测系统的设计与实现
|
摘要
自动检测系统的设计与实现在实际生产中具有重要的意义。随着计算机视觉技术的快速发展,工业自动化检测已被列为世界各国着重的发展对象。目前疵病检测技术在工业自动化检测中是一个新兴的方向,它综合不同领域的背景知识,检测技术和检测方法都在进一步的探索和试验中。
本文研究了一个针对于枪械内膛的疵病检测系统。枪械内膛的制造工艺,使得枪械内膛的疵病检测具有较为复杂的背景环境。算法的设计与实现主要是针对于这种复杂的检测环境。算法的执行过程中主要用到了彩色图像的灰度化、二值化、连通区域的标记、小面积疵病的统计和去除、连通区域的特征参数的提取、判决识别较大面积的疵病、图像细化和角点检测等相关技术。算法分阶段分步骤的将图像中的不同疵病识别或判决出来。连通区域特征参数的提取主要用到了连通区域的矩形度、圆形度、不变矩和长宽比等变量,通过这些变量不同的阈值将疵病分离出来。在检测系统的设计与实现中,还涉及到图像的采集和存储,串口编程,系统界面设计等相关的编程方法。
疵病检测算法能够检测到疵病的严重程度,从定性和定量的角度给出检测的结果值。能够识别出80%以上的疵病,具有实际应用价值。
Design and implementation of automated detection system has significance in actual production. As the rapid development of computer vision technology, the industrial automation detection has been listed as the object of development which the world focuses on. Defect detection is an emerging technology in the direction of industrial automation detection, it is combined with different professional background in the field of knowledge, detection technology and method is in further explored and experiment.
In this paper, defect detection system of the barrell is studied. Due to the manufacturing process, the defect detection system has a more complex content. In order to achieve a better non-destructive testing, a detection algorithm based on image processing for barrel wall is designed in the paper. The design of algorithm mainly use image graying, image binarization, marking connected region, defect of little area statistics and remove, image thinning, corner detection technology and so on. This algorithm process is designed to solve different defect types. The extraction of characteristic parameter is mainly used in the connected region squareness, circularity, the invariant moment, aspect ratio and other variables, this method can be separated from the defect and rifling. In the implementation and design of detect system, image acquisition and storage will be involved, and the same with system interface design and serial programming.
The various functions of the system already completely implement, the defect detection algorithm is able to detect the severity of the defect, and reference value is given from the view of qualitative and quantitative point. This algorithm can recognize more than eighty percent defect, and have actual use value.
本文研究了一个针对于枪械内膛的疵病检测系统。枪械内膛的制造工艺,使得枪械内膛的疵病检测具有较为复杂的背景环境。算法的设计与实现主要是针对于这种复杂的检测环境。算法的执行过程中主要用到了彩色图像的灰度化、二值化、连通区域的标记、小面积疵病的统计和去除、连通区域的特征参数的提取、判决识别较大面积的疵病、图像细化和角点检测等相关技术。算法分阶段分步骤的将图像中的不同疵病识别或判决出来。连通区域特征参数的提取主要用到了连通区域的矩形度、圆形度、不变矩和长宽比等变量,通过这些变量不同的阈值将疵病分离出来。在检测系统的设计与实现中,还涉及到图像的采集和存储,串口编程,系统界面设计等相关的编程方法。
疵病检测算法能够检测到疵病的严重程度,从定性和定量的角度给出检测的结果值。能够识别出80%以上的疵病,具有实际应用价值。
Design and implementation of automated detection system has significance in actual production. As the rapid development of computer vision technology, the industrial automation detection has been listed as the object of development which the world focuses on. Defect detection is an emerging technology in the direction of industrial automation detection, it is combined with different professional background in the field of knowledge, detection technology and method is in further explored and experiment.
In this paper, defect detection system of the barrell is studied. Due to the manufacturing process, the defect detection system has a more complex content. In order to achieve a better non-destructive testing, a detection algorithm based on image processing for barrel wall is designed in the paper. The design of algorithm mainly use image graying, image binarization, marking connected region, defect of little area statistics and remove, image thinning, corner detection technology and so on. This algorithm process is designed to solve different defect types. The extraction of characteristic parameter is mainly used in the connected region squareness, circularity, the invariant moment, aspect ratio and other variables, this method can be separated from the defect and rifling. In the implementation and design of detect system, image acquisition and storage will be involved, and the same with system interface design and serial programming.
The various functions of the system already completely implement, the defect detection algorithm is able to detect the severity of the defect, and reference value is given from the view of qualitative and quantitative point. This algorithm can recognize more than eighty percent defect, and have actual use value.
引文
[1]刘立欣,王文生,刘广利.枪械内膛疵病图像的边缘检测算法.兵工学报.2005,26(1)：105-107.
[2]张洪伟,任现君.新型枪械内膛疵病检测设备.飞行器测控学报.2002.21(2)：87-90.
[3]杨滨峰.枪械内膛测量技术的研究[硕士论文].长春理工大学硕士论文.2008.
[4]韩保军,拜丽萍,刘上乾,吴志鹏.基于人眼视觉特性的火炮内膛图像增强方法.应用光学.2005,26(1)：36-38.
[5]谭振江,王锡龙,白宝兴.枪管内膛图像处理与识别系统.松辽学刊.1997,1：45-49.
[6]于彬.基于数字图像处理技术的陶瓷裂纹检测研究.武汉理工大学自动化学院控制理论与控制工程专业硕士学位论文.2007.
[7]卢斌.基于视觉的圆筒内壁均匀度在线检测系统.沈阳工业大学硕士学位论文.2010.
[8]蔡立晶.图像处理技术在指纹仪检测系统中的应用.长春理工大学硕士学位论文.2004.
[9]李久政.钢管漏磁探伤中的内外伤区分方法.华中科技大学硕士学位论文.2009.
[10]Wang Xuanyin, Liang Dongtai. Packaging cans inner surface inspection system based on multivariate image analysis. Transactions of the Chinese Society for Agricultural Machinery. 2009,40(6):222-226.
[11]Hu Liang, Duan Fa-jie, Ding Ke-qin, Ye Sheng-hua. The application of FPGA-Based image processing technology in surface defect detection system for steel strip. Chinese Journal of Sensors and Actuators.2006,19(3):694-696.
[12]Hua Jun, Yang Shutang, Li Jianhua. Method of video captures and encoding based on DirectShow technology. Computer Engineer,2004,30(12):143-146.
[13]Zhang Fan, Li Bo. Medical video stream transmission via internet. Microelectronics & Computer.2008,25(8):25-28.
[14]Zhang Wen-wei, Zhang Yan-xi. Laser Measuring system for the inner wall of a pipe based on ring optical cutting image method. Acta Metrologica Sinica.2001,22(4):284-287.
[15]Xing Chun-fei, Li Yan-hong, Chen Da-peng, Zou Peng. Ultrasonic infrared technology for checking inner wall of metal pipeline. Journal of Applied Optics.2009,30(3):465-468.
[16]Mao Yue-juan, Yuan Bao-chen. The ultrasonic detection method of the large ratio of thickness to diameter tube. Metallurgical Analysis.2010,30:1469-1471.
[17]张望鹏,杨光,王晨升.一种面向对象知识的模型数据库管理系统的设计与实现[C].第四届图像图形技术与应用学术会议,2009,北京.中国.
[18]王晨升,徐新国,朱廷劭.基于IEC61131-3的通用工业组态软件系统设计研究,2009中国自动化大会暨两化融合高峰会议(CAAC2009)杭州,中国.2009.
[19]陈亮,王晨升,王伟.一种基于双路视觉实时立体显示的交互界面设计,第四届图像图形技术与应用学术会议(IGTA2009)2009.北京.中国.
[20]刘运周,王飞,王晨升The Research on Visual Fatigue Factor in Stereoscopic Image Observation,2009 IEEE 10th International Conference on Computer-aided Industrial Design &Conceptual Design (CAID&CD2009), Wenzhou, CHINA, October 2009.
[21]Lei Li,Chensheng Wang,Xingyuan Kou, et.al. NC Machining Optimization based on Processing Parameter DB and PSO[C]//2012 the 3rd International Conference on Mechanic Automation and Control Engineering (MACE 2012) July 27th -29th 2012 Baoding China.
[22]Xingyuan Kou, ChenshengWang, Lei Li. A Detection System of Tool Condition Based on Image Processing Technology [C], Advanced Materials Research Vol.510 (2012):375-379.
[23]Liang Ming Tet Yeap , Saeed Rahmati et al.Fuzzy control of spindle power in end milling processes[J].International Journal of Machine Tools & Manu 2002 42:1487.
[24]RC Eberhart and J Kennedy. A New Optimizer Using Particles Swarm Theory. Proc.Sixth International Symposium on Micro Machine and Human Science, Nagoga, Japan,1995.
[25]Wu Meiping.Cui Jianjun,Liao Wenhe. The optimization research of cutting parameters in NC Machining[J].China Construction Machinery 2003 15(3):235-237.
[26]X. Desforges, B. Archime' de, Multi-agent framework based on smart sensors/actuators for machine tools control and monitoring, Engineering Applications of Artificial Intelligence 19 (2006) 641-655.
[27]Wen Zhang, Chensheng Wang, Guang Yang, Zhiqiang Chen, Lei Li.The Defect-Detection System for Firearms Bore. Power Engineering and Automation Conference(PEAM).2012.Wuhan.China.
[28]陈志强,王晨升,杨光,张稳,杨沐.铸件表面工件号识别的预处理及分割算法研究.第七届图像图形技术与应用学术会议.北京.
[29]张伟,何金国.Hu不变矩的构造与推广[J].计算机应用,2010,30(9)：2449-2452.
[30]赵万金,龚声蓉,刘纯平等.一种自适应的Harris角点检测算法[J].计算机工程,2008,34(10)：212-214,217.
[31]罗志灶,周赢武,郑忠楷等.基于区域增长的连通域标记算法的优化[J].闽江学院学报,2011,32(2)：41-44.
[32]张宏光,李运洛,姚红岩等.国外水下枪械及枪弹发展研究[C].//中国科协2005年学术年会论文集.2005：95-100.
[33]工坚,单长胜.新型火炮缠角测量系统设计[J].中国测试技术,2006,32(1)：32-33,41.
[34]钱成越.基于图像噪声检测的Harris角点提取方法[J].电脑开发与应用,2010,23(8)：29-31.
[35]魏伟波,芮筱亭.不变矩方法研究[J].火力与指挥控制,2007,32(11)：114-117.
[36]王静.二值图像连通域的分段标记算法及实现[J].红外与激光工程,2010,39(4)：761-765.
[37]张进猛,张进秋.基于OpenCV的图像采集和处理[J].软件导刊,2010,09(1)：164-165.
[38]赵辉煌,孙雅琪,张珍来等.基于OpenCV的双幅图像采集系统设计与实现[J].计算机与数字工程,2012,40(9)：97-98,150.
[39]周颖慧,夏丽娟.基于CMOS和USB2.0的人脸检测系统[J].电子器件,2009,32(2)：258-261.
[40]安宝林,杨耿,薛晋生等.基于CCD成像技术的枪械射击准确度验收系统[J].兵工学报,2010,31(2)：239-241
[41]杨滨峰.枪械内膛测量技术综述[J].赤峰学院学报：自然科学版,2011,(9)：208-209.
[42]曾朝阳,赵继广.火炮身管疵病深度测量系统[J].光学精密工程,2010,18(10)：2221-2230.DOI：10.3788/OPE.20101810.2221.
[43]于正林,姜涛,曹国华等.基于二维光扫描的细长孔内壁疵病检测技术[J].仪器仪表学报,2008,29(3)：487-491.
[44]程晓锋,徐旭,张林等.基于高分辨力CCD的大口径光学元件疵病检测[J].强激光与粒子 束,2009,21(11)：1677-1680.
[45]郭琦,傅建平,雷洁等.基于遗传算法与支持向量机的火炮内膛疵病分类方法研究[J].军械工程学院学报,2011,23(2)：46-48.
[46]李玉兰,郑海起,王平等.基于功率-幅值谱的炮膛疵病图像识别[J].光电工程,2010,37(5)：37-40,79.DOI：10.3969/j.issn.1003-501X.2010.05.007.
[47]雷洁,傅建平,张培林等.基于Contourlet变换的火炮内膛疵病分割方法[J].军械工程学院学报,2011,23(5)：26-28.
[48]李玉兰,郑海起,栾军英等.火炮身管内膛疵病检测现状与展望[J].军械工程学院学报,2009,21(1)：48-52.
[49]原瑞宏,刘军卿,董自卫等.基于图像纹理特征的炮膛疵病检测方法[J].兵上自动化,2012,31(1)：78-80.DOI：10.3969/j.issn.1006-1576.2012.01.023.
[50]于洪龙,吴永亮,但伟等.基于拼接算法的炮膛疵病自动识别技术[J].装甲兵工程学院学报,2012,26(5)：51-54,58.
[51]史金霞,赵继广.火炮内膛疵病检测系统的设计[J].兵工自动化,2005,24(4)：31-32.
[52]原瑞宏,余能国,唐力伟等.炮膛疵病图像的去噪研究[J].火炮发射与控制学报,2011,(2)：71-73.
[53]孙浩,唐勇,李京展等.硬盘盘片表面疵病检测装置的光学系统设计[J].激光技术,2012,36(1)：118-119,123.DOI：10.3969/j.issn.1001-3806.2012.01.030.
[54]谢志江,任铮,王雪等.基于Canny算子的机械元件广义疵病无损检测系统关键技术[J].机械与电子,2010,(6)：14-17.
[55]陆春华.基于机器视觉的大口径精密表面疵病检测系统研究[D].浙江大学信息学院,2008.
[56]郭晓晶.图像角点检测方法的研究[D].青岛大学,2009.
[57]武跃华.机器视觉划痕检测技术及应用研究[D].广东工业大学,2011.
[58]黄米青.基于弹体外表面疵病检测系统的图像处理技术[D].长春理工大学,2003.
[59]金鑫.炮弹装药疵病自动识别技术[D].太原理工大学,2003.
[60]刘思.黄心汉.复杂背景下钢板表面缺陷检测的图像增强方法[J].华中科技大学学报(自然科学版),2011,39(z2)：141-143.
[2]张洪伟,任现君.新型枪械内膛疵病检测设备.飞行器测控学报.2002.21(2)：87-90.
[3]杨滨峰.枪械内膛测量技术的研究[硕士论文].长春理工大学硕士论文.2008.
[4]韩保军,拜丽萍,刘上乾,吴志鹏.基于人眼视觉特性的火炮内膛图像增强方法.应用光学.2005,26(1)：36-38.
[5]谭振江,王锡龙,白宝兴.枪管内膛图像处理与识别系统.松辽学刊.1997,1：45-49.
[6]于彬.基于数字图像处理技术的陶瓷裂纹检测研究.武汉理工大学自动化学院控制理论与控制工程专业硕士学位论文.2007.
[7]卢斌.基于视觉的圆筒内壁均匀度在线检测系统.沈阳工业大学硕士学位论文.2010.
[8]蔡立晶.图像处理技术在指纹仪检测系统中的应用.长春理工大学硕士学位论文.2004.
[9]李久政.钢管漏磁探伤中的内外伤区分方法.华中科技大学硕士学位论文.2009.
[10]Wang Xuanyin, Liang Dongtai. Packaging cans inner surface inspection system based on multivariate image analysis. Transactions of the Chinese Society for Agricultural Machinery. 2009,40(6):222-226.
[11]Hu Liang, Duan Fa-jie, Ding Ke-qin, Ye Sheng-hua. The application of FPGA-Based image processing technology in surface defect detection system for steel strip. Chinese Journal of Sensors and Actuators.2006,19(3):694-696.
[12]Hua Jun, Yang Shutang, Li Jianhua. Method of video captures and encoding based on DirectShow technology. Computer Engineer,2004,30(12):143-146.
[13]Zhang Fan, Li Bo. Medical video stream transmission via internet. Microelectronics & Computer.2008,25(8):25-28.
[14]Zhang Wen-wei, Zhang Yan-xi. Laser Measuring system for the inner wall of a pipe based on ring optical cutting image method. Acta Metrologica Sinica.2001,22(4):284-287.
[15]Xing Chun-fei, Li Yan-hong, Chen Da-peng, Zou Peng. Ultrasonic infrared technology for checking inner wall of metal pipeline. Journal of Applied Optics.2009,30(3):465-468.
[16]Mao Yue-juan, Yuan Bao-chen. The ultrasonic detection method of the large ratio of thickness to diameter tube. Metallurgical Analysis.2010,30:1469-1471.
[17]张望鹏,杨光,王晨升.一种面向对象知识的模型数据库管理系统的设计与实现[C].第四届图像图形技术与应用学术会议,2009,北京.中国.
[18]王晨升,徐新国,朱廷劭.基于IEC61131-3的通用工业组态软件系统设计研究,2009中国自动化大会暨两化融合高峰会议(CAAC2009)杭州,中国.2009.
[19]陈亮,王晨升,王伟.一种基于双路视觉实时立体显示的交互界面设计,第四届图像图形技术与应用学术会议(IGTA2009)2009.北京.中国.
[20]刘运周,王飞,王晨升The Research on Visual Fatigue Factor in Stereoscopic Image Observation,2009 IEEE 10th International Conference on Computer-aided Industrial Design &Conceptual Design (CAID&CD2009), Wenzhou, CHINA, October 2009.
[21]Lei Li,Chensheng Wang,Xingyuan Kou, et.al. NC Machining Optimization based on Processing Parameter DB and PSO[C]//2012 the 3rd International Conference on Mechanic Automation and Control Engineering (MACE 2012) July 27th -29th 2012 Baoding China.
[22]Xingyuan Kou, ChenshengWang, Lei Li. A Detection System of Tool Condition Based on Image Processing Technology [C], Advanced Materials Research Vol.510 (2012):375-379.
[23]Liang Ming Tet Yeap , Saeed Rahmati et al.Fuzzy control of spindle power in end milling processes[J].International Journal of Machine Tools & Manu 2002 42:1487.
[24]RC Eberhart and J Kennedy. A New Optimizer Using Particles Swarm Theory. Proc.Sixth International Symposium on Micro Machine and Human Science, Nagoga, Japan,1995.
[25]Wu Meiping.Cui Jianjun,Liao Wenhe. The optimization research of cutting parameters in NC Machining[J].China Construction Machinery 2003 15(3):235-237.
[26]X. Desforges, B. Archime' de, Multi-agent framework based on smart sensors/actuators for machine tools control and monitoring, Engineering Applications of Artificial Intelligence 19 (2006) 641-655.
[27]Wen Zhang, Chensheng Wang, Guang Yang, Zhiqiang Chen, Lei Li.The Defect-Detection System for Firearms Bore. Power Engineering and Automation Conference(PEAM).2012.Wuhan.China.
[28]陈志强,王晨升,杨光,张稳,杨沐.铸件表面工件号识别的预处理及分割算法研究.第七届图像图形技术与应用学术会议.北京.
[29]张伟,何金国.Hu不变矩的构造与推广[J].计算机应用,2010,30(9)：2449-2452.
[30]赵万金,龚声蓉,刘纯平等.一种自适应的Harris角点检测算法[J].计算机工程,2008,34(10)：212-214,217.
[31]罗志灶,周赢武,郑忠楷等.基于区域增长的连通域标记算法的优化[J].闽江学院学报,2011,32(2)：41-44.
[32]张宏光,李运洛,姚红岩等.国外水下枪械及枪弹发展研究[C].//中国科协2005年学术年会论文集.2005：95-100.
[33]工坚,单长胜.新型火炮缠角测量系统设计[J].中国测试技术,2006,32(1)：32-33,41.
[34]钱成越.基于图像噪声检测的Harris角点提取方法[J].电脑开发与应用,2010,23(8)：29-31.
[35]魏伟波,芮筱亭.不变矩方法研究[J].火力与指挥控制,2007,32(11)：114-117.
[36]王静.二值图像连通域的分段标记算法及实现[J].红外与激光工程,2010,39(4)：761-765.
[37]张进猛,张进秋.基于OpenCV的图像采集和处理[J].软件导刊,2010,09(1)：164-165.
[38]赵辉煌,孙雅琪,张珍来等.基于OpenCV的双幅图像采集系统设计与实现[J].计算机与数字工程,2012,40(9)：97-98,150.
[39]周颖慧,夏丽娟.基于CMOS和USB2.0的人脸检测系统[J].电子器件,2009,32(2)：258-261.
[40]安宝林,杨耿,薛晋生等.基于CCD成像技术的枪械射击准确度验收系统[J].兵工学报,2010,31(2)：239-241
[41]杨滨峰.枪械内膛测量技术综述[J].赤峰学院学报：自然科学版,2011,(9)：208-209.
[42]曾朝阳,赵继广.火炮身管疵病深度测量系统[J].光学精密工程,2010,18(10)：2221-2230.DOI：10.3788/OPE.20101810.2221.
[43]于正林,姜涛,曹国华等.基于二维光扫描的细长孔内壁疵病检测技术[J].仪器仪表学报,2008,29(3)：487-491.
[44]程晓锋,徐旭,张林等.基于高分辨力CCD的大口径光学元件疵病检测[J].强激光与粒子 束,2009,21(11)：1677-1680.
[45]郭琦,傅建平,雷洁等.基于遗传算法与支持向量机的火炮内膛疵病分类方法研究[J].军械工程学院学报,2011,23(2)：46-48.
[46]李玉兰,郑海起,王平等.基于功率-幅值谱的炮膛疵病图像识别[J].光电工程,2010,37(5)：37-40,79.DOI：10.3969/j.issn.1003-501X.2010.05.007.
[47]雷洁,傅建平,张培林等.基于Contourlet变换的火炮内膛疵病分割方法[J].军械工程学院学报,2011,23(5)：26-28.
[48]李玉兰,郑海起,栾军英等.火炮身管内膛疵病检测现状与展望[J].军械工程学院学报,2009,21(1)：48-52.
[49]原瑞宏,刘军卿,董自卫等.基于图像纹理特征的炮膛疵病检测方法[J].兵上自动化,2012,31(1)：78-80.DOI：10.3969/j.issn.1006-1576.2012.01.023.
[50]于洪龙,吴永亮,但伟等.基于拼接算法的炮膛疵病自动识别技术[J].装甲兵工程学院学报,2012,26(5)：51-54,58.
[51]史金霞,赵继广.火炮内膛疵病检测系统的设计[J].兵工自动化,2005,24(4)：31-32.
[52]原瑞宏,余能国,唐力伟等.炮膛疵病图像的去噪研究[J].火炮发射与控制学报,2011,(2)：71-73.
[53]孙浩,唐勇,李京展等.硬盘盘片表面疵病检测装置的光学系统设计[J].激光技术,2012,36(1)：118-119,123.DOI：10.3969/j.issn.1001-3806.2012.01.030.
[54]谢志江,任铮,王雪等.基于Canny算子的机械元件广义疵病无损检测系统关键技术[J].机械与电子,2010,(6)：14-17.
[55]陆春华.基于机器视觉的大口径精密表面疵病检测系统研究[D].浙江大学信息学院,2008.
[56]郭晓晶.图像角点检测方法的研究[D].青岛大学,2009.
[57]武跃华.机器视觉划痕检测技术及应用研究[D].广东工业大学,2011.
[58]黄米青.基于弹体外表面疵病检测系统的图像处理技术[D].长春理工大学,2003.
[59]金鑫.炮弹装药疵病自动识别技术[D].太原理工大学,2003.
[60]刘思.黄心汉.复杂背景下钢板表面缺陷检测的图像增强方法[J].华中科技大学学报(自然科学版),2011,39(z2)：141-143.