一种ABS齿圈参数检测系统误差校正方法研究

为了纠正ABS齿圈参数检测系统装夹机构旋转时轴承晃动等因素带来的误差,运用最小二乘法曲线拟合原理及空间三维直角坐标系仿射变换方法进行了误差校正。首先,对该方法进行理论分析,推导出系统坐标变换矩阵公式;其次,根据误差校正方法建立了数学模型,推导出变换后坐标计算公式,将测量坐标系中各参数代入变换公式,并计算出轮廓数据变换后坐标;最后,运用Matlab对模型进行了仿真实验。实验结果表明:校正后参数值与实际参数值之间偏差小于1 μm。解决了实际测量过程中各种误差带来的影响,提高了检测系统的测量精度。     

基于深度智能视觉的表面缺陷检测研究进展

基于深度智能视觉的表面缺陷检测研究在制造业中起着越发重要的作用,本文阐述深度智能视觉的表面缺陷检测在现代工业质检中的重要性,对现有研究进展进行梳理总结。深度智能视觉以机器视觉和深度学习为技术基础,为不同工业场景提供高精高效的表面缺陷检测算法。本文从检测细粒度的角度将表面缺陷检测分为表面缺陷分类、定位、分割检测3个部分,并分别对分类、定位、分割方法进行系统综述,梳理现有表面缺陷检测研究的问题和思路。分类检测针对数据和缺陷图形特征问题进行研究,因其基础性和易拓展性于不同工业场景的应用呈现分散发展;定位检测以模型框架、矩形框检测和标注成本为主要问题,表现出追求轻量化和特征融合机制的研究趋势;分割检测更关注图像细节特征。通过研究分类、定位、分割的多任务模型框架以探索分类、分割检测之间的互补性。最后总结目前表面缺陷检测研究存在的问题,并对发展趋势进行展望。     

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。     

基于机器视觉技术的药品质量检测系统

药品质量检测是药品生产领域的重要环节,为药品的安全生产与使用提供了重要保证。药品的外观检测是药品检测的重要环节之一。由于其需求量大,质量检测要求高,以目前的人力方式检测总具有不确定性,缺乏准确度。为此采用机器视觉技术应用于药品的外观检测可以克服人工检测的许多弊端,并提高了其准确度与工作效率,同时也降低了企业的成本,也是未来药品检测发展的趋势。     

基于机器视觉的啤酒金属盖表面缺陷检测方法

目的 为了提高啤酒金属盖表面缺陷检测的精度和准确率,提出一种基于机器视觉的金属盖表面缺陷检测方法。方法 以不同类型的啤酒金属盖表面缺陷为研究对象,利用滤波抑噪和高反差保留算法对图像进行处理,运用YOLO–v5网络完成瓶盖的缺陷检测。通过添加注意力机制SE模块、改进模型损失函数和预测框筛选方式等技术手段对原YOLO–v5模型作出优化,抑制图像中的不重要特征,提升小目标检测的准确率和模型的特征提取能力。结果 改进后的YOLO–v5模型与常用的检测模型的对比结果表明,改进YOLO–v5模型在测试集上的mPA指标为93.10%,检测速度达到了294张/min,优势较为明显。结论 针对不同类型的金属盖表面缺陷,基于机器视觉的检测模型均有较高的检测精度和识别准确率,小目标缺陷的漏检率和误检率情况较少,满足生产线实时、高精度的检测要求。     

强反射复杂表面随机缺陷自动检测系统

系统采用分光照明方式,设计均匀散射光源,通过图像增强预处理,灰度分析,图像二值化,特征提取与图像识别, 自动分选出表面有缺陷的工件。硬软件包括:光学系统;接收系统;控制电路和Visual C 、汇编语言程序等。系统有效解决了强反射光、复杂表面和随机缺陷带来的检测困难,检测精度可达97.3%。     

手机玻璃屏表面缺陷视觉检测方法研究

目的针对手机玻璃屏表面缺陷人工检测存在的准确率低、稳定性差等问题,提出一种基于机器视觉技术的手机玻璃屏表面缺陷检测方法。方法采用统计平均法建立模板图像,以减少外界光照对模板图像的灰度影响。采用基于互信息的配准方法实现模板图像和待测图像的像素对齐,将配准后的待测图像与模板图像进行差分运算,获取残差图像,并采用Niblack方法实现残差图像上的缺陷判断。通过搭建的实验平台获取了300幅手机玻璃屏图像,并采用文中提出的方法、模板匹配法和人工检测法对300幅图像实施缺陷检测。结果实验结果显示,文中方法的真正率为92%,真负率为96.5%和准确率为95%。与模板匹配法和人工检测法相比,文中方法在真正率、真负率和准确率上分别至少提高了5%,4%和4.3%。结论文中方法与人工检测方法相比,提高了手机玻璃屏表面缺陷检测的准确率和稳定性。     

Modified gamma correction method to enhance ball grid array image for surface defect inspection

BGA (Ball Grid Array) surface defect detection requires faster and more accurate methods for semiconductor industry applications. Traditionally, the BGA inspection used gray-scale images. However, the solder pad, wiring and gray scales shown in images depict little variance. Therefore, when the threshold value is poorly set or the contract rate is insignificant, BGA detection may fail to segment an object. This research proposes a modified methodology that uses Gamma correction for image enhancement. Three-color bands were applied to a modified Gamma correction algorithm (i.e. RGB) to better separate the high and low image contrasts. Better results were obtained by dividing the image into background and foreground portions using the Gamma correction. As a result, the proposed method improved the contrast value by 52.09%. After the images were enhanced and segmented, the compactness and internal holes were calculated as features for classification. The results showed that classification correctness was 96.43%. The proposed method used a 640?×?480 pixel image, performing complete defect detection 0.3 seconds faster than the traditional enhancement method, which requires 1?second. The research results provide an effective solution for the detection and classification of the BGA surface tin ball defect problem.     

自适应图像增强的管道机器人缺陷检测方法

针对管道检测过程中图像采集光照不均匀、缺陷边缘提取不准确的问题, 提出一种基于自适应图像增强的管道机器人缺陷检测方法。首先设计单尺度Retinex自适应图像增强算法, 利用引导滤波对图像进行照度分量估计, 经自适应Gamma矫正得到光照均衡图像, 实现自适应图像增强;再对传统Canny边缘检测方法进行改进, 采用双边滤波平滑图像, 通过迭代阈值法进行缺陷图像分割, 根据边缘像素相似性进行连接, 实现缺陷轮廓的有效提取。搭建基于自适应图像增强的管道机器人缺陷检测系统, 利用履带式小车搭载云台摄像机, 对管道内壁缺陷进行全方位视觉检测。实验结果表明, 本文的检测方法可自适应矫正图像亮度, 图像亮度不均匀明显改善, 相比次优算法, 图像信息熵提升2.4%, 图像平均梯度提升2.3%, 峰值信噪比提升4.4%, 可有效提取出管道缺陷边缘, 缺陷识别准确率达到97%。     

Improving visual inspection using binocular rivalry

In this study, we solve the non-identical parallel CNC machine scheduling problem. We have two objectives: minimizing the manufacturing cost (comprising machining, non-machining and tooling costs) and minimizing the total weighted tardiness. The tooling constraints affect the non-machining times as well as the machining conditions, such as cutting speed and feed rate, which in turn specify the machining times and tool lives. We propose a two-stage algorithm to find optimal machining conditions and to determine machine allocation, tool allocation and part scheduling decisions. The proposed algorithm generates different schedules according to the relative importance of the objectives.     

Selection of inspector for visual inspection

This paper presents a statistical method for selecting the best inspector for visual inspection having the highest defect-finding ability among k(≥2) prospective inspectors.

A sample containing known number of defects are submitted to each of k prospective inspectors. As the sample size is increased, sampling variation decreases so that we have a better chance of selecting the truly best inspector, but at the same time the cost of sampling is also increased, The problem is how to determine the sample size required for selecting the best inspector with specified probability P*.

This problem is formulated from the indifference zone point of view with an application of the loss function which takes into consideration the opportunity cost of making a wrong selection and the cost of sampling. Minimax solution is obtained under the restriction that the best inspector is to be selected with the specified probability P*. The selection procedure is applied to the visual inspection of car body painting.     

刨齿刀的三维可视化设计

三维参数化、可视化设计是现代机械设计的发展趋势之一。在AutoCAD软件的二次开发工具VBA(visual basic for application)中,开发了刨齿刀三维参数化和可视化设计软件。在AutoCAD软件中进行刨齿刀三维参数化建模,利用生成的刨齿刀三维实体模型,在Pro/Engineer,ANSYS软件中进行刨齿刀有限元分析。制造了硬齿面圆锥直齿轮刨齿刀,对刀具的磨损进行分析,为刀具的快速开发提供条件。     

Development of a surface defect inspection system using radiantlight from steel products in a hot rolling line

The steel industry is constantly trying to reduce production cost and improve quality by making the steel manufacturing processes continuous and faster. Currently, the rolling process of steel production is largely automated, while the finishing process is not yet appreciably automated. The finishing processes involve many tasks difficult to automate, such as defect inspection and repairing the detected defects. In recent years, however, many automated and labor-saving systems have been developed for use in the finishing processes. The surface defect inspection of steel products is the largest bottleneck in the finishing process. This paper describes an inspection system of steel surface defects for large sections, such as wide flange beams and I-beams. This system is based on applied radiant light and it senses the temperature deviation caused by defects. The wavelength of the detector is optimized to improve the signal-to-noise ratio. An optical attenuator was developed to compensate for the known temperature distribution across the product immediately after rolling. The image processor takes only 50 ms per image frame. Each time frame has the necessary image information to detect defects     

Relay failure prevention by internal visual inspection

There is an evident lack of information about military-type relays regarding their reliability, failure mechanisms and modes. In trying to fill this gap, even partially, this paper deals with different findings of internal visual inspection (IVI), failure analysis (FA) and a proposal for screening tests of relays as have been carried out in our laboratory. Likewise, it includes recommendations for quality assurance improvements. A special emphasis is placed on failure predictions by analysis of the IVI findings. This paper is based on a paper presented at the Seventh International Conference of the Israel Society for Quality Assurance (Tel-Aviv, 8–10 November 1988).     

燃机叶片型面三维光学扫描检测方法研究

针对工业生产中提高燃气轮机叶片型面检测效率、实现叶片整体尺寸检测的实际需求,提出基于激光和光栅两种三维光学扫描的叶片型面检测方法。采集燃气轮机叶片三维点云数据,用统一采样和设定点云间最大偏差值的方法进行点云精简。根据6点定位原理和最小二乘法将精简点云与设计模型进行配准,提取叶片型面轮廓度和检测截面特征参数进行分析,并与三坐标检测结果对比。结果表明:两者检测叶片型面轮廓度在相同偏差范围内点云所占比例偏差都在1%以内,叶片型面特征参数尺寸相差都在0.02 mm以内。经试验证明,三维光学扫描方法检测速度快、适应性强、可靠性高,可为高效准确地进行叶片型面检测提供有效的技术手段。     

Extension of the visual search models of inspection

Human performance in a visual search task is generally measured by a cumulative probability distribution of locating a target in a given time period. In this paper, this cumulative probability function has been derived for two systematic search strategies, non-overlapping and overlapping; with both infinitesimal and finite defect length. Moreover, for the infinitesimal defect size case, economic models are derived under the assumption that the number of defects on the search line follows a one-dimensional Spatial Poisson distribution to determine the best inspection stopping time. This research first extends the typical infinitesimal defect size assumption to a finite defect length assumption. Then, it extends the single infinitesimal defect case to the case of random number of infinitesimal defects and develops economic models for two extreme systematic search strategies.     

自动PCB外观检测仪中的图像采集研究

为了增强对PCB板检测的准确性和有效性,研制了自动外观检测仪.文章介绍了外观检测仪中图像实时采集和传输的实现.主要讨论了系统设计、检测和驱动开发.采用ALTERA公司的新型CYCLONE FPGA系列简化本地逻辑,大大缩短了硬件开发周期.工具DriverStudio的使用降低了驱动开发的难度.桥芯片PEX8111的使用和DMA传输方式的设计满足了高速、实时、准确的图像采集要求.