基于机器视觉的荧光磁粉自动检测系统设计
|
摘要
现有荧光缺陷检测技术主要采用人眼视觉判定与半自动化等方式,针对目前存在的检测效率低、对人体辐射损伤大等问题,提出一种基于机器视觉的荧光磁粉自动检测流水线系统。该系统具备自动磁化、缺陷检测及智能分拣等功能,实现检测过程的全自动;采用基于梯度聚类算法的磁痕缺陷识别方法,可根据缺陷特征进行检测模式分类,以提高缺陷检测的准确性。实验结果表明:该系统实现工件缺陷的全自动化检测,平均识别正确率高达98. 53%,检测效果较好,具有较高推广价值。
The existing fluorescence defect detection technology mainly uses the method of human eye vision judgment and semi-automation,aiming at the existing problems of low detection efficiency and large radiation damage to human body,a fluorescent magnetic powder automatic detection pipeline system based on machine vision is proposed. The system has the functions of automatic magnetization,defect detection and intelligent sorting to realize the automatic detection process; the magnetic trace defect identification method based on gradient clustering algorithm can classify the detection mode according to the defect characteristics in order to improve the accuracy of defect detection. The experimental results show that the system realizes the complete automatic detection of workpiece defects,the average recognition accuracy rate is up to 98. 53 %,the detection effect is good,and it has high popularization value.
The existing fluorescence defect detection technology mainly uses the method of human eye vision judgment and semi-automation,aiming at the existing problems of low detection efficiency and large radiation damage to human body,a fluorescent magnetic powder automatic detection pipeline system based on machine vision is proposed. The system has the functions of automatic magnetization,defect detection and intelligent sorting to realize the automatic detection process; the magnetic trace defect identification method based on gradient clustering algorithm can classify the detection mode according to the defect characteristics in order to improve the accuracy of defect detection. The experimental results show that the system realizes the complete automatic detection of workpiece defects,the average recognition accuracy rate is up to 98. 53 %,the detection effect is good,and it has high popularization value.
引文
[1]牛乾,刘桂华,康含玉.磁粉探伤钢轴表面裂纹智能识别方法研究[J].自动化仪表,2018,39(3):55-59.
[2]李建文.磁粉探伤缺陷识别自动化系统设计与开发[D].南京:南京理工大学,2012.
[3]王姮,卜燕,张华,等.基于分形维数的磁痕图像缺陷检测[J].计算机应用研究,2015,32(2):603-605.
[4]杨志军,陈亮,刘延雷,等.焊缝裂纹缺陷的磁粉检测自动识别方法研究[J].制造业自动化,2016,38(4):22-25.
[5]林果.基于荧光磁粉的智能无损检测技术研究及实现[D].绵阳:西南科技大学,2016.
[6]高敏杰,卜雄洙,孙斌,等.荧光磁粉表面缺陷检测系统[J].无损检测,2017,36(2):67-70,73.
[7] ZHAO X M,ZUO M J,LIU Z L,et al. Diagnosis of artificial created surface damage levels of planet gear teeth using ordinal ranking[J]. Measurement,2013,46(1):132-144.
[8]刘姝,路锦正,王利龙.基于类间相对均匀性的纸张表面缺陷检测[J].传感器与微系统,2018,37(7):123-126.
[9]王松林,蒋峥.改进的自适应加权中值滤波算法[J].传感器与微系统,2016,35(11):128-131.
[10] NIE F Y,ZHANG P F,LI Q J,et al. A novel generalized entropy and its application in image thresholding[J]. Signal Prcessing,2017,134(C):23-24.
[11]杨恢先,颜微,谭正华,等.改进的灰度—局部方差二维直方图图像分割[J].计算机工程与应用,2017,53(4):209-213,222.
[12]许江淳,岳秋燕,任向阳,等.基于机器视觉的药片表面缺陷识别与分拣系统设计[J].传感器与微系统,2017,36(6):90-93.
[13]马涛,孙振国,陈强.基于几何与纹理特征相融合的磁粉探伤裂纹提取算法[J].清华大学学报:自然科学版,2018,58(1):50-54.
[14]张昊,金冠,蒋毅,等.基于SVM特征点分类的机器视觉外螺纹参数检测[J].传感器与微系统,2019,38(4):121-124.
[15]彭赶,张平,潘奕创.基于机器视觉的手机屏幕缺陷检测系统研究[J].自动化技术与应用,2018,37(9):104-108.
[2]李建文.磁粉探伤缺陷识别自动化系统设计与开发[D].南京:南京理工大学,2012.
[3]王姮,卜燕,张华,等.基于分形维数的磁痕图像缺陷检测[J].计算机应用研究,2015,32(2):603-605.
[4]杨志军,陈亮,刘延雷,等.焊缝裂纹缺陷的磁粉检测自动识别方法研究[J].制造业自动化,2016,38(4):22-25.
[5]林果.基于荧光磁粉的智能无损检测技术研究及实现[D].绵阳:西南科技大学,2016.
[6]高敏杰,卜雄洙,孙斌,等.荧光磁粉表面缺陷检测系统[J].无损检测,2017,36(2):67-70,73.
[7] ZHAO X M,ZUO M J,LIU Z L,et al. Diagnosis of artificial created surface damage levels of planet gear teeth using ordinal ranking[J]. Measurement,2013,46(1):132-144.
[8]刘姝,路锦正,王利龙.基于类间相对均匀性的纸张表面缺陷检测[J].传感器与微系统,2018,37(7):123-126.
[9]王松林,蒋峥.改进的自适应加权中值滤波算法[J].传感器与微系统,2016,35(11):128-131.
[10] NIE F Y,ZHANG P F,LI Q J,et al. A novel generalized entropy and its application in image thresholding[J]. Signal Prcessing,2017,134(C):23-24.
[11]杨恢先,颜微,谭正华,等.改进的灰度—局部方差二维直方图图像分割[J].计算机工程与应用,2017,53(4):209-213,222.
[12]许江淳,岳秋燕,任向阳,等.基于机器视觉的药片表面缺陷识别与分拣系统设计[J].传感器与微系统,2017,36(6):90-93.
[13]马涛,孙振国,陈强.基于几何与纹理特征相融合的磁粉探伤裂纹提取算法[J].清华大学学报:自然科学版,2018,58(1):50-54.
[14]张昊,金冠,蒋毅,等.基于SVM特征点分类的机器视觉外螺纹参数检测[J].传感器与微系统,2019,38(4):121-124.
[15]彭赶,张平,潘奕创.基于机器视觉的手机屏幕缺陷检测系统研究[J].自动化技术与应用,2018,37(9):104-108.