Automated X-ray Defect Inspection on Occluded BGA Balls Using Hybrid Algorithm

Automated X-ray defect inspection of occluded objects has been an essential topic in semiconductors,autonomous vehicles,and artificial intelligence devices.However,there are few solutions to segment occluded objects in the X-ray inspection efficiently.In particular,in the Ball Grid Array inspection of X-ray images,it is difficult to accurately segment the regions of occluded solder balls and detect defects inside solder balls.In this paper,we present a novel automatic inspection algorithm that segments solder balls,and detects defects fast and efficiently when solder balls are occluded.The proposed algorithm consists of two stages.In the first stage,the defective candidates or defects are determined through the following four steps:(i)image preprocessing such as noise removal,contrast enhancement,binarization,connected component,and morphology,(ii)limiting the inspec-tion area to the ball regions and determining if the ball regions are occluded,(iii)segmenting each ball region into one or more regions with similar gray values,and(iv)determining whether there are defects or defective candidates in the regions using a weighted sum of local threshold on local variance.If there are defective candidates,the determination of defects is finally made in the following stage.In the second stage,defects are detected using the automated inspection technique based on oblique computed tomography.The 3D precision inspection process is divided into four steps:(i)obtaining 360 projection images(one image per degree)rotating the object from 0 to 360 degrees,(ii)reconstructing a 3D image from the 360 projected images,(iii)finding the center slice of gravity for solder balls from the axial slice images in the z-direction,and getting the inspection intervals between the upper bound and the lower bound from the center slice,and(iv)finally determining whether there are defects in the averaged image of solder balls.The proposed hybrid algorithm is robust for segmenting the defects inside occluded solder balls,and improves the performance of solder ball segmentation and defect detection algorithm.Experimental results show an accuracy of more than 97%.

Real-time Monitoring of Subsea Gas Pipelines,Offshore Platforms,and Ship Inspection Scores Using an Automatic Identification System

The aim of this research is to develop an algorithm and application that can perform real-time monitoring of the safety operation of offshore platforms and subsea gas pipelines as well as determine the need for ship inspection using data obtained from automatic identification system(AIS).The research also focuses on the integration of shipping database,AIS data,and others to develop a prototype for designing a real-time monitoring system of offshore platforms and pipelines.A simple concept is used in the development of this prototype,which is achieved by using an overlaying map that outlines the coordinates of the offshore platform and subsea gas pipeline with the ship’s coordinates(longitude/latitude)as detected by AIS.Using such information,we can then build an early warning system(EWS)relayed through short message service(SMS),email,or other means when the ship enters the restricted and exclusion zone of platforms and pipelines.The ship inspection system is developed by combining several attributes.Then,decision analysis software is employed to prioritize the vessel’s four attributes,including ship age,ship type,classification,and flag state.Results show that the EWS can increase the safety level of offshore platforms and pipelines,as well as the efficient use of patrol boats in monitoring the safety of the facilities.Meanwhile,ship inspection enables the port to prioritize the ship to be inspected in accordance with the priority ranking inspection score.

Development of Automatic Phased Array Inspection System for Long-distance Pipeline

In the paper the development of phased array technique home and abroad is summarized, the overall structure and main research on phased array inspection system are introduced,and meanwhile the future field of study and development of phased array ultrasonic inspection technique is pointed out.

Application of ultrasonic inspection in monitoring dynamic healing of mandibular fracture in rabbit model

Objective:To investigate the feasibility of ultrasonic diagnosis for monitoring fracture healing. Methods:Thirty rabbit models with fraction of mandible body were established by surgically removing partial lower jawbone.At the 1st,2nd,4th,6th,8th and 12th week after the operation, they were examined by X-ray and ultrasound,respectively.All detection results were scored according to a generally accepted standard.Spearman rank correlation analysis was conducted to explore the relationship between the results of the two inspection methods.Results:In each healing stage,the results of the ultrasonic inspection were basically consistent with those of the X-ray examination,as supported by a Spearman rank correlation coefficient of 0.892(P【0.001). Conclusions:Non-invasive ultrasonic inspection can be used instead of X-ray examination to monitor and diagnose fracture healing.

RULE-BASED FABRIC INSPECTION USING MACHINE VISION

Automatic visual inspection of fabric is not only one of the potential application of machinevision but a considerable challenge in textile engineering as well.This paper mainly discusses howto inspect fabric defects using machine vision.The introduced inspection system has a feature of:(?)Categorizing the fabric defects into 4 groups,for each group diffcrent image processing and recog-nizing methods are designed for fast and efficient inspection:2.The inspection and recognitionparameters are determined by training and self learning,these parameters vary with different kindsof fabric;3.Human inspetor’s experiences are summed up as rules to ensure the system has a s(?)lar evaluation performance of human inspector.This system can detect most of the fab(?) defects.the total recognition error is less than 5% except for the detection error of yarn irregularity,whichcould be as high as 20%.

Automatic Modification of Local Drilling Holes via Double Pre-Assembly Holes

Manufacturing accuracy, especially position accuracy of fastener holes, directly affects service life and security of aircraft. The traditional modification has poor robustness, while the modification based on laser tracker costs too much. To improve the relative position accuracy of aircraft assembly drilling, and ensure the hole-edge distance requirement, a method was presented to modify the coordinates of drilling holes. Based on online inspecting two positions of pre-assembly holes and their theoretical coordinates, the spatial coordinate transformation matrix of modification could be calculated. Thus the straight drilling holes could be modified. The method improves relative position accuracy of drilling on simple structure effectively. And it reduces the requirement of absolute position accuracy and the cost of position modification. And the process technician also can use this method to decide the position accuracy of different pre-assembly holes based on the accuracy requirement of assembly holes.

A Review of the Application of Computer Vision to the Inspection and Assessment of Textiles Apparent Properties

Due to its advantages of objectiveness, automation, accuracy and fastness in various applications, the technology of computer vision has become one of the studying hotspots in the area of the objective inspection and assessment of textiles apparent properties during the past two decades in the world. Both a brief review of its applications in the recent decade both at home and abroad to the automatic inspection and assessment of the various apparent properties of the textiles, such as yarn, woven fabrics and knitting fabrics, carpet fabrics, nonwoven fabrics and textile webs, etc., and a detailed introduction to the research work including the objective evaluation of fabric wrinkle grade, automatic fabric defects detection and assessment of fabric pilling grade, etc., that was conducted by our research section, i.e., Computer Vision’s Textiles Application Research Section, College of Textiles, Dong Hua University, have been provided. Experimental results have proved the feasibilities of the approaches used by us in the applications to the objective inspection and assessment of fabric apparent properties, and also indicated that the technology of computer vision is a power tool for the objective and automatic inspection and assessment of textiles apparent properties, and that it has a bright application future.

Research on Operation Safety of Urban Rail Transit Based on Automatic Ticket Checking(AFC)System

At present,after the actual inspection of the rail transit automatic ticket checking system,some security vulnerabilities have appeared,and there are also some defects in information security.For example,the database and virus protection need to be analyzed and upgraded in order to cope with the increasing number of information security risks.This article analyzes the security problems in the AFC system,and puts forward related suggestions and solutions,hoping to provide some reference for technical developers.

桁架式机器人视觉巡检系统设计

针对当前智能制造装备存在传感器监测盲区且人工点检效率低、易出错的现状,设计一套桁架式移动机器人视觉巡检系统,实现自动监测生产线设备上电气、机械关键部位易松动易错位等问题。该系统安装在生产线上方,具有可达范围广、无拍照死角、适用场景广和不影响生产线设备动作等优点,解决传统地面移动巡检机器人占用生产线空间、拍照角度受限、无法进入复杂生产线内部点检等缺点。在智能制造技术升级的背景下,该系统具有较高的实用价值及推广意义。

民机外表面上部自主视觉检查中的降维路径规划研究

传统的民机外表面检查过程中,人工目视检查存在成本高、效率低、工作时间长等诸多不足,而带有机载视觉系统的机器人可以安全、快速、准确地检查民机外表面。本文提出一种用于民机外表面上部自主视觉检查的三维覆盖路径规划方法。通过对民机外表面上部进行初步点云获取,对机身、机翼区域切片,将三维点云映射到平面,然后进行二维覆盖路径的规划及三维空间的路径复原,快速生成优化的三维全覆盖检查路径。结果表明,该方法可以缩短三维覆盖路径规划的时间,较大程度地降低民机外表面上部自主视觉检查的成本,推动自动化检查民机表面技术的发展。

面向堤坝监测的无人机自动巡检系统设计

针对人工巡检监测堤坝费时费力,存在安全风险,还可能会造成堤坝损害等问题,设计一种无人机大坝自动巡检系统:首先对搜索区域进行建模,采用基于栅格的技术,为每架无人机划分待搜索区域,然后采用牛耕法对区域进行全覆盖搜索;通过改进的yolov5算法对裂缝图像进行快速识别,利用MAD中值滤波和广义形态学滤波对红外图像进行预处理,实现了对堤坝渗漏区域的快速准确识别。

基于计算机视觉的工业金属表面缺陷检测综述

针对平面及三维结构金属材料的工业表面缺陷检测,概述了视觉检测技术的基本原理和研究现状,并总结出视觉自动检测系统的关键技术包括光学成像技术、图像预处理技术与缺陷检测器.首先介绍了如何根据检测对象的光学特性选择合适的二维、三维光学成像技术;其次介绍了图像降噪、特征提取、图像分割和拼接等预处理技术的重要作用;然后根据缺陷检测器的实现原理将其分为模板匹配、图像分类、图像语义分割、目标检测和图像异常检测五类,并对其中的经典算法进行了归纳分析.最后,探讨了工业场景下金属表面缺陷检测技术实施中的关键问题,并对该技术的发展趋势进行了展望.

圣女果温室巡检机器人系统设计与试验

为解决传统农业生产方式中人工巡检成本高、劳动强度大、速度慢等问题,设计一种圣女果温室巡检机器人系统,融合自动控制技术、机器视觉技术和深度学习技术,实现对圣女果的准确识别和计数。通过机器视觉提取工作路径和红外传感器避障实现机器人自动导航功能;并提出一种改进型YOLOv4-tiny模型对圣女果进行检测,该模型在YOLOv4-tiny的基础上增加52×52的特征层和注意力机制,提高小目标检测的识别精度。试验结果表明,该巡检机器人以0.2 m/s的速度行进时可以准确沿着预定路径工作,改进的YOLOv4-tiny-Tomato模型在温室环境中对成熟和未成熟圣女果的平均识别精度分别为98.7%和98.0%,F 1值分别达到96.71%和95.8%,实时帧率达到36帧/s。本研究可为农业领域的智能化巡检和精细管理提供新的思路和技术支持。

基于机器视觉的量规测位偏差自动调整装置研究

设计基于机器视觉的量规自调位装置,该装置在视觉检测部分标定后,对采集到的图像利用双边滤波Canny、加权Turkey算法和切线法自动识别量规的型号及量规偏离待测位置的位移与角度信息,并通过上位机将参数信息传递至三菱GX Works2软件,三菱FX3U-48MT-ES模块将处理完毕的信号发送给电机,驱动电机使四自由度夹具自动调位进入待测位置,并在C#窗口界面实时显示。实验表明,该系统调位后15次实验的离待测位置偏差量均小于0.3mm,符合理论不确定度范围,优于人工放置,识别量规表面标志有效率达97.33%,实现了设备的数字化改造。

触发开关自动化装配与调测系统设计

在触发开关生产过程中,实现自动化和智能化是提升产能保证装调质量的先决条件。针对触发开关自动装调和检测的问题,设计一套触发开关自动化装调系统,提出一种动作过载调测自主学习算法,实现触发开关螺钉拧紧距离的自动调测。利用机器视觉方法对装配过程中的关键部件进行缺陷检测,以快速完成装配质量检测。该系统可实现触发开关的自动装配、铆接、检测、调测、灌封和固化等功能。

刀具损伤视觉检测系统自动对准对焦研究

为解决数控机床刀具无拆卸条件下,基于机械臂的刀具损伤视觉检测系统对准对焦调节耗时长、计算分析方法鲁棒性差等难题,提出了一种融合YOLOv5网络智能感兴趣区域(region of interest, ROI)的机器人视觉系统自动对准对焦方法。首先,利用ROI模型检测并定位刀具中心,通过九点标定法计算机械臂末端对准坐标;然后自适应筛选ROI对焦窗口,采用改进的Laplacian函数计算清晰度评价值以确定最佳刀具图像。在实际设备上开展实验后结果表明,所提方法比一般方法灵敏度至少提高1.63倍,平均中心点误差为3.76像素,有效提升了刀具损伤视觉检测系统的准确度和灵活性。

手卷雪茄在线质量检测技术的研究与应用

为解决手卷雪茄人工质检效率低、成本高问题,设计并实现了基于机器视觉和传感器技术的手卷雪茄在线质量检测系统。该系统首先对雪茄进行激光打标,其次系统通过高速线阵CCD相机动态获取手卷雪茄图像,基于改进的机器视觉方法实时分析雪茄茄衣颜色及瑕疵,基于微波传感器,系统采用谐振法实现手卷雪茄含水量与密度的量测,然后基于CCD激光测微仪,通过对射式LED光幕实现手卷雪茄烟支外径高速测量,最终基于高精度重量传感器实现流水线手卷雪茄的快速称重工序,实现对雪茄质量的在线自动化质检。经过测试,该系统可满足流水线工况下实时、高精度的手卷雪茄质检工作,有效提升质检效率。

物流仓库无线传感网络与自动巡检小车监测系统设计

针对物流仓库潜在的安全隐患问题,设计了Zigbee无线传感网络和自动巡检智能小车相结合的仓库监测系统.首先使用多个Zigbee终端节点连接环境参数传感器套件,分布到仓库货架上实现静态监测;其次,设计了自动循迹智能小车搭载热像仪和传感器实现仓库环境动态监测.通过增量式PID对电机进行闭环控制,使小车的速度和转向角度沿着预定路径前进.经测试,该系统可以实现物流仓库静态和动态全方位监测和及时预警,为保障仓库安全提供了一种技术管理手段.

基于工艺设计的无线远传水表自动化装配设备研制

传统水表制造由人工装配完成,存在生产周期长、生产效率低、生产费用高等问题。分析了水表的结构组成和各零件之间的相互配合,以国内主流的无线远传水表为例,设计了一款由6个设备组成的自动化装配生产线。完成了生产线的整体布局和物料在各个设备之间的流转,经过现场安装和运行调试,实现了自动化生产装配线的可靠稳定运行。有效提高了生产效率和装配精度,适应企业产业升级的需求,为自动化生产装配线提供了设计新思路,具有实际借鉴意义。

立式水轮发电机定子内膛及端部清扫检查装置的研究

立式水轮发电机在B级检修期间,需拔出一对磁极后,对定子绕组端部、定子通风槽等进行人工清扫检查,常规方式采用带电清洗剂进行人工冲洗,并对定子槽口、定子内膛等进行重点检查,存在工作效率低、清洗剂影响作业人员呼吸道健康、空间狭小导致检查不充分等问题,为此研制了自动清扫装置。该装置的投入,减轻了作业人员劳动强度,缩短了清洗检查时间,提高了检修效率。