基于图像处理技术的五金件表面缺陷检测研究

为实现图像处理技术在表面缺陷检测中的应用,取代传统人工检测的方式,设计开发了一套五金件表面缺陷检测系统,研究了镀镍五金件表面图像在线处理算法,包括边缘检测算法、位置修正算法、标定算法和检测算法,实现了五金件表面缺陷视觉检测.同时提出一种阈值反馈算法,用实际缺陷值反馈验证理论缺陷值,最终得到可靠的缺陷阈值,判断表面缺陷....     

带钢表面缺陷视觉检测系统关键技术研究

为满足钢板表面缺陷在线检测系统宽幅面、高速、高分辨率的检测要求，讨论了基于线阵CCD的钢板表面缺陷视觉检测系统实现的关键技术；优化设计了视觉检测系统的光学照明部分，以检测不同类型的缺陷。通过软件系统的特殊设计，以保证实时在线检测。针对缺陷图像低对比度、高噪声的特点，提出了基于灰度统计特性的图像边缘检测方法，并实现了对缺陷图像的自适应阈值分割。依据图像的缺陷统计特性，定义了缺陷的灰度、几何等特征量，用于缺陷分类。本系统样机已在实验室环境下运行。     

The Comparison Analysis of Test Result of Ultrasonic △ Technique and TOFD Method

采用超声△衍射法和TOFD法对模拟缺陷进行检测,得出了缺陷检测波形图和B/C扫描图.对比分析了超声△衍射法与TOFD法的检测结果.实验表明利用超声△衍射法能够识别近表面垂直表面的面状缺陷,有效地对缺陷进行定位,能够很好地克服表面盲区,对缺陷的检测识别能力不受缺陷方向限制.从检测结果数据可以看出超声△衍射法的检测灵敏度和缺陷识别能力优于TOFD法.     

超声Δ法与TOFD法在薄壁电子束焊缝上的检测结果对比分析

采用超声Δ衍射法和TOFD法对模拟缺陷进行检测,得出了缺陷检测波形图和B/C扫描图。对比分析了超声Δ衍射法与TOFD法的检测结果。实验表明利用超声Δ衍射法能够识别近表面垂直表面的面状缺陷,有效地对缺陷进行定位,能够很好地克服表面盲区,对缺陷的检测识别能力不受缺陷方向限制。从检测结果数据可以看出超声Δ衍射法的检测灵敏度和缺陷识别能力优于TOFD法。     

基于Blob算法的印刷缺陷在线检测的研究

将常见的印刷缺陷分为点、线、面3类,介绍了印刷缺陷在线检测的基本流程,说明了Blob算法检测缺陷的具体步骤,并运用Blob算法结合缺陷面积及周长的特征,成功对印品缺陷进行了提取及归类,最终得到了缺陷的面积、位置、类型等特征参数,在程序中实现了印刷品缺陷的检测。     

铆接结构缺陷检测中的低频脉冲涡流技术

脉冲涡流是一种可以对飞机多层铆接结构中缺陷进行有效检测的无损检测技术。本文通过研究低频涡流与脉冲涡流检测技术,设计和实现了圆柱形差分检测传感器,对铆钉周围出现的缺陷进行了检测。通过轴向扫描时获得的峰值曲线对缺陷的轴向宽度进行了定量检测。通过缺陷的瞬态感应电压信号,利用峰值、过零时间等特征量对缺陷造成的不连续性和损耗程度进行了检测分析。试验结果证明文中设计的圆柱形差分传感器可以对多层铆接结构中的缺陷进行有效检测,低频脉冲技术在飞机铆接结构缺陷的检测中具有很好的使用前景。     

笔管缺陷自动化检测系统设计与研究

中国已成为笔类产品生产大国与出口大国，而笔管检测是制笔行业的关键工艺技术。针对目前制笔行业中笔管检测的需求，设计了笔管缺陷自动化检测系统，以提高笔管缺陷检测效率及笔管制造企业的生产质量。基于机器视觉及重心分类装置，采取分模块检测系统，对笔管的缺陷形态、类型进行鉴别与统计，高效率、高精度地实现笔管缺陷检测、残次品剔除与自动分拣。采用缺陷自动检测算法，利用计算机视觉检测技术进行缺陷边缘检测，分割出笔管的缺陷区域并定义主要缺陷类型，完成对笔管缺陷的判断与分类。通过构建、训练卷积神经网络，得到了拟合度较高的卷积神经网络模型，用于分析笔管的缺陷情况。实验结果表明，笔管缺陷自动化检测系统可以客观地检测笔管的缺陷，提高笔管生产效率，提升生产线的成品质量，具有较高的工程应用价值。     

基于霍尔传感器的缺陷区域预定位系统研究

为了提高大型检测目标的检测效率,本文提出了在进行缺陷的精确检测前进行缺陷区域的前期定位技术.基于缺陷磁场检测的原理,通过磁场检测和运动控制的结合,建立了基于霍尔传感器和三维机械运动平台的缺陷区域定位系统.实验表明,前期定位结果以云图的形式能够直观有效地给出缺陷的存在区域.进而,缺陷区域前期快速定位和后期精确检测的完美结合,将使得无损检测过程更加高效、实用,具有良好的工业应用前景.     

分区域分等级的印刷品缺陷检测方法

目的为了体现印刷品不同区域的重要性等级,提高印刷品缺陷检测的精度,提出了一种分区域分等级的印刷品缺陷检测方法。方法根据检测区域的特点和重要性不同,把印刷品分成不同的区域进行前景提取,并且设置不同的检测等级;对印刷品进行符合人眼视觉特性的缺陷识别,并对提取缺陷进行特征分析。结果分区域的缺陷检测可以实现不同区域的同时检测,在检测耗时、检测准确率及误检率上都优于不分区域的检测方法。结论基于分区域的印刷品缺陷检测方法能很好地满足印刷品质量检测的需求,提高印刷品缺陷检测的精度和效率。     

高温结构陶瓷缺陷的激光扫描超声显微检测

本文介绍了激光扫描超声显微镜的工作原理和在陶瓷缺陷检测中的应用。讨论了从缺陷的声图像判断缺陷的大小、位置以及性质的方法。通过对各种陶瓷缺陷的检测实验,证实了利用高频(100 MHz)超声对检测陶瓷中<100μm 缺陷的可能性。     

Photoacoustic microscopy of ceramic engine hardware

Scanning photoacoustic microscopy (SPAM) was applied to silicon nitride turbine hardware for purposes of detecting fabrication defects. SPAM traces in selected areas of complex-shaped turbine stator vanes were obtained and indicate that surface-crack detection of the order of tens of microns is possible. Means were devised to allow for multiple scans in areas previously inaccessible to other nondestructive techniques capable of detecting defects in the 25- to 100-µm range. The results show that SPAM is applicable to reaction-bonded silicon nitride turbine components and capable of detecting small surface-related defects.     

基于计算机视觉的印刷包装品缺陷检测系统

介绍了印刷包装品外观缺陷的计算机视觉系统的构成,探讨了应用图像差分原理及图像坐标与空间坐标的变换关系,实现缺陷检测的基本方法.     

Statistics of defects in one-dimensional components

Equations related to spatial statistics of defects and probability of detecting defects in one-dimensional components have been derived. The equations related to spatial statistics of defects allow to estimate the probability of existence of safe, defect-free zones between the defects in one-dimensional components. It is demonstrated that even for a moderate defect number densities, the probability of existence of clusters of two or more defects at a critically small distance is substantial and should not be neglected in calculations related to risks of failure. The formulae derived have also important application in reliability and risk assessment studies related to calculation of the probability of clustering of evens on a given time interval. It is demonstrated that while for large tested fractions from one-dimensional components, the failures are almost entirely caused by a small part of the largest defects, for small tested fractions almost all defects participate as initiators of failure. The problem of non-destructive defect inspection of one-dimensional components has also been addressed. A general equation has been derived regarding the probability of detecting at least a single defect when only a fraction of the component is examined.     

Detection of outer raceway bearing defects in small induction motors using stator current analysis

We investigate the application of induction motor stator current spectral analysis (MCSA) for detection of rolling element bearing damage from the outer raceway. In this work, MCSA and vibration analysis are applied to induction motor to detect outer raceway defects in faulty bearings. Data acquisition, recording, and fast fourier transform (FFT) algorithms are done by using the Lab VIEW programming language. Experimental results verify the relationship between vibration analysis and MCSA, and identify the presence of outer raceway bearing defects in induction machines. This work also indicates that detecting fault frequencies by motor currents is more difficult than detecting them by vibration analysis. The use of intensive resolution FFT is recommended in MCSA for detecting faults easily. Reinstalling a faulty bearing can alter the characteristic frequencies and it is difficult to compare results from different bearings or even from the same bearing in different installations.     

一种基于轮廓配准的包装缺陷检测方法

提出了一种基于包装图像轮廓配准的包装缺陷检测方法.该方法先对包装图像进行轮廓提取,计算目标轮廓的质心,从而得到配准平移参量.围绕目标质心每隔一定角度抽得质心到轮廓的距离值,得到一个距离值的序列.通过计算标准图像和待配准图像的距离值序列的圆周相关的最大值来确定旋转的角度.然后对已配准的包装图像进行缺陷检测,实验证明,本方法对包装缺陷的检测是快速的,有效的.     

A transducer made up of fluxgate sensors for testing wire ropedefects

Based on analyzing the magnetic leakage feature of wire rope defects, the longitudinal resolved vector B_ot of the defect leakage field is taken for the object to be tested. In order to detect the weak magnetic leakage field, a fluxgate sensor of single core and single winding is developed. Using the fluxgate, a new kind of transducer for testing defects of wire rope has been designed. The structure and interface circuit of the transducer are studied. The experimental results of detecting the LF and LMA defects of the wire rope are presented     

基于图像配准的STN-LCD外观缺陷检测

提出了一种基于图像配准的超扭曲向列液晶显示器件(STN-LCD)的外观缺陷自动检测方法.该方法首先对标准模板图像做不均匀光照消除、二值化以及区域信息提取;然后通过控制点检测和仿射变换实现待检测图像和模板图像之间的配准;并利用各图形区域的灰度平均值和标准方差等统计信息,检测缺段、针孔等各类缺陷.为提高图像配准精度,进一步提出了有效控制点筛选方案以及混合插值方法.实验结果表明,该方法设计思路合理,缺陷检测正确率达到98.3%,可代替人眼实现对STN-LCD多种外观缺陷的快速、自动检测,满足实际应用需求.     

小型液晶屏盒内缺陷检测中纹理的消除

提出了一种在小型液晶屏盒内缺陷检测中消除纹理影响的方法,并成功制作了国内首台小型液晶屏盒内缺陷自动光学检测仪.本方法的基本原理是:采集标准液晶屏图像,利用其图像数据建立补偿矩阵,在检测的预处理过程中使用补偿矩阵消除纹理.这种方法有效解决了液晶屏纹理影响检测结果的难题.理论分析及现场实验结果表明,该方法达到消除液晶屏纹理的同时完整保留缺陷的目的,使液晶屏盒内缺陷自动检测的准确性大大提高.     

Line-focusing electromagnetic acoustic transducers for the detection of slit defects

This paper describes the design principles of a line-focusing electromagnetic acoustic transducer (LF-EMAT) and the results of a feasibility test for detecting slit-type defects in metals. The LF-EMAT excites shear vertical (SV) elastic waves and focuses them to a line in a metal body. It consists of a permanent magnet block and a meanderline coil, whose spacing is continuously varied so that the excited SV waves become coherent on a focal line after traveling oblique paths. The measured directivity of generation and reception show a sharp peak at the designed focal line. The LF-EMATs are then applied to detecting slit defects in the bottom surface of steel blocks, on which the focal lines are located. Portions of the scattered defect signals are received by the same EMAT. When operated at 4 MHz, the LF-EMATs are capable of detecting slits deeper than 0.05 mm. The sensitivity decreases with liftoff and the LF-EMATs are usable with liftoff up to 0.6 mm.     

基于无人机图像的风力发电机叶片缺陷识别

针对风力发电机叶片人工检测低效,缺陷诊断难的问题,提出一种基于无人机与图像处理的风力发电机叶片缺陷识别方法。通过Halcon 12与Visual Studio 2015的联合开发,实现图像处理流程、检测结果输出以及缺陷回放等功能,包括相机标定、通过快速自适应加权中值滤波处理图像、动态阈值分割叶片图像缺陷特征,利用区域处理识别裂纹和砂眼等缺陷,并对缺陷进行分类与测量以及输出对叶片质量的分析报告等,实现风力发电机叶片表面缺陷的自动检测功能。通过实例验证了该方法在风力发电机叶片表面缺陷检测中的较高精确性与算法稳定性。