An Example of Machine Vision Applied in Printing Quality Checking——Research on the Checking of Printing Quality by Image Processing

The traditional printing checking method always uses printing control strips,but the results are not very well in repeatability and stability. In this paper,the checking methods for printing quality basing on image are taken as research objects. On the base of the traditional checking methods of printing quality,combining the method and theory of digital image processing with printing theory in the new domain of image quality checking,it constitute the checking system of printing quality by image processing,and expound the theory design and the model of this system. This is an application of machine vision. It uses the high resolution industrial CCD(Charge Coupled Device) colorful camera. It can display the real-time photographs on the monitor,and input the video signal to the image gathering card,and then the image data transmits through the computer PCI bus to the memory. At the same time,the system carries on processing and data analysis. This method is proved by experiments. The experiments are mainly about the data conversion of image and ink limit show of printing.

Machine learning-enabled optimization of melt electro-writing three-dimensional printing

Melt electrowriting(MEW)is a solvent-free(i.e.,no volatile chemicals),a high-resolution three-dimensional(3D)printing method that enables the fabrication of semi-flexible structures with rigid polymers.Despite its advantages,the MEW pro-cess is sensitive to changes in printing parameters(e.g.,voltage,printing pressure,and temperature),which can causefluid column breakage,jet lag,and/orfiber pulsing,ultimately deteriorating the resolution and printing quality.In spite of the commonly used error-and-trial method to determine the most suitable parameters,here,we present a machine learning(ML)-enabled image analysis-based method for determining the optimum MEW printing parameters through an easy-to-use graph-ical user interface(GUI).We trainedfive different ML algorithms using 168 MEW 3D print samples,among which the Gaussian process regression ML model yielded 93%accuracy of the variability in the dependent variable,0.12329 on root mean square error for the validation set and 0.015201 mean square error in predicting line thickness.Integration of ML with a control feedback loop and MEW can reduce the error-and-trial steps prior to the 3D printing process,decreasing the printing time(i.e.,increasing the overall throughput of MEW)and material waste(i.e.,improving the cost-effectiveness of MEW).Moreover,embedding a trained ML model with the feedback control system in a GUI facilitates a more straightforward use of ML-based optimization techniques in the industrial section(i.e.,for users with no ML skills).

Applying Neural-Network-Based Machine Learning to Additive Manufacturing:Current Applications,Challenges,and Future Perspectives

Additive manufacturing(AM),also known as three-dimensional printing,is gaining increasing attention from academia and industry due to the unique advantages it has in comparison with traditional subtractive manufacturing.However,AM processing parameters are difficult to tune,since they can exert a huge impact on the printed microstructure and on the performance of the subsequent products.It is a difficult task to build a process-structure-property-performance(PSPP)relationship for AM using traditional numerical and analytical models.Today,the machine learning(ML)method has been demonstrated to be a valid way to perform complex pattern recognition and regression analysis without an explicit need to construct and solve the underlying physical models.Among ML algorithms,the neural network(NN)is the most widely used model due to the large dataset that is currently available,strong computational power,and sophisticated algorithm architecture.This paper overviews the progress of applying the NN algorithm to several aspects of the AM whole chain,including model design,in situ monitoring,and quality evaluation.Current challenges in applying NNs to AM and potential solutions for these problems are then outlined.Finally,future trends are proposed in order to provide an overall discussion of this interdisciplinary area.

3D printing for ultra-precision machining:current status,opportunities,and future perspectives

Additive manufacturing,particularly 3D printing,has revolutionized the manufacturing industry by allowing the production of complex and intricate parts at a lower cost and with greater efficiency.However,3D-printed parts frequently require post-processing or integration with other machining technologies to achieve the desired surface finish,accuracy,and mechanical properties.Ultra-precision machining(UPM)is a potential machining technology that addresses these challenges by enabling high surface quality,accuracy,and repeatability in 3D-printed components.This study provides an overview of the current state of UPM for 3D printing,including the current UPM and 3D printing stages,and the application of UPM to 3D printing.Following the presentation of current stage perspectives,this study presents a detailed discussion of the benefits of combining UPM with 3D printing and the opportunities for leveraging UPM on 3D printing or supporting each other.In particular,future opportunities focus on cutting tools manufactured via 3D printing for UPM,UPM of 3D-printed components for real-world applications,and post-machining of 3D-printed components.Finally,future prospects for integrating the two advanced manufacturing technologies into potential industries are discussed.This study concludes that UPM is a promising technology for 3D-printed components,exhibiting the potential to improve the functionality and performance of 3D-printed products in various applications.It also discusses how UPM and 3D printing can complement each other.

Hierarchical planning for a surface mounting machine placement

For a surface mounting machine (SMM) in printed circuit board (PCB) assembly line, there are four problems, e.g. CAD data conversion, nozzle selection, feeder assignment and placement sequence determination. A hierarchical planning for them to maximize the throughput rate of an SMM is presented here. To minimize set-up time, a CAD data conversion system was first applied that could automatically generate the data for machine placement from CAD design data files. Then an effective nozzle selection approach was implemented to minimize the time of nozzle changing. And then, to minimize picking time, an algorithm for feeder assignment was used to make picking multiple components simultaneously as much as possible. Finally, in order to shorten pick-and-place time, a heuristic algorithm was used to determine optimal component placement sequence according to the decided feeder positions. Experiments were conducted on a four head SMM. The experimental results were used to analyse the assembly line performance.

Role of three-dimensional printing and artificial intelligence in the management of hepatocellular carcinoma:Challenges and opportunities

Hepatocellular carcinoma(HCC)constitutes the fifth most frequent malignancy worldwide and the third most frequent cause of cancer-related deaths.Currently,treatment selection is based on the stage of the disease.Emerging fields such as three-dimensional(3D)printing,3D bioprinting,artificial intelligence(AI),and machine learning(ML)could lead to evidence-based,individualized management of HCC.In this review,we comprehensively report the current applications of 3D printing,3D bioprinting,and AI/ML-based models in HCC management;we outline the significant challenges to the broad use of these novel technologies in the clinical setting with the goal of identifying means to overcome them,and finally,we discuss the opportunities that arise from these applications.Notably,regarding 3D printing and bioprinting-related challenges,we elaborate on cost and cost-effectiveness,cell sourcing,cell viability,safety,accessibility,regulation,and legal and ethical concerns.Similarly,regarding AI/ML-related challenges,we elaborate on intellectual property,liability,intrinsic biases,data protection,cybersecurity,ethical challenges,and transparency.Our findings show that AI and 3D printing applications in HCC management and healthcare,in general,are steadily expanding;thus,these technologies will be integrated into the clinical setting sooner or later.Therefore,we believe that physicians need to become familiar with these technologies and prepare to engage with them constructively.

3D打印膝关节曲面磨粒流抛光数值模拟及实验研究

目的解决磨粒流加工3D打印制造的TC4钛合金膝关节时存在配合端面抛光效率低以及表面质量不均匀的问题。方法运用FLUENT软件并结合非牛顿流体的Carreau-Yasuda方程对有、无仿形工装的磨粒流加工3D打印膝关节进行对比分析,研究仿形工装对磨粒流加工的影响规律,并通过单因素实验确定颗粒直径倍数与流道间隙大小的关系,从而完成最佳仿形工装设计。结果仿真对比分析结果表明,仿形工装有助于减小压力损失,并且膝关节表面的切削量显著提升,最大提升了182.92%。同时,在双向磨粒流工艺下,膝关节表面切削量的不均匀程度平均降低73%,提升了表面质量的均匀性,证实了仿形工装的有效性。加工结果表明,当仿形流道间隙大小为5倍Si C颗粒直径、工作压力为2 MPa、加工时间为45 min、使用双向磨粒流工艺时,3D打印膝关节的整体表面粗糙度显著降低,平均表面粗糙度为0.67μm。主要配合曲面呈现镜面效果,表面粗糙度达0.38μm与0.46μm。结论当仿形工装的流道间隙为5倍SiC颗粒直径时,磨粒流抛光效果最优。采用双向磨粒流工艺,获得了优于单向磨粒流工艺的均匀表面压力,从而有效提升了表面质量的均匀性,为3D打印钛合金人工骨复杂曲端面的光整加工提供了理论参考和实验依据。

基于在机测量的曲面共形电路3D打印误差补偿方法

基于3D打印技术制备曲面共形电路具有广阔的应用前景,然而,由于曲面基材加工误差和导电线路定位误差的影响,导致曲面电路3D打印头高度难以精确控制,进而影响打印精度。为此,本文以气动式直写打印为研究对象,提出了一种“在机测量+线路模型重构”的打印头高度误差补偿方法。设计了一种曲率自适应测量点选取方法,利用NURBS曲线反算法对测量数据进行重构,还原真实线路模型。通过生成真实线路的打印轨迹,替换原始理论打印轨迹,补偿了打印头高度误差。自主搭建了一套集成了在机测量系统的曲面共形电路3D打印平台,设计了直线、圆弧与NURBS自由曲线3种形状的线路,进行补偿前后电路打印的对比实验。结果表明,未进行补偿前,在线路曲率较大的地方,线路在基板上的波峰处会产生拉丝现象,波谷处会产生堆叠现象,而补偿后的导线线宽比较均匀;进一步对每条导线的电阻进行测量,发现各条线路补偿前的电阻值波动较大,补偿后的电路的电阻值均匀,且相较补偿前平均降低65.99%,最大电阻降幅达85.75%。

融合自注意力与残差神经网络的3D打印激光在机测量误差修正方法

激光测量能够实现高效地非接触实时测量,被广泛应用于3D打印领域,但激光测量容易受测量条件、外部环境等多种因素的干扰,这些因素错综复杂,难以量化分析。为此,结合直射式激光三角测量原理,在分析测量精度影响因素的基础上,提出了一种基于融合自注意力和残差神经网络的3D打印在机测量误差修正方法。首先,将影响测量精度的因素作为输入变量,采集激光测量值,得到样本数据集;然后利用残差网络提取出样本数据的深层次特征,并引入自注意力机制建立影响因素之间的联系,得到带权重的提取特征;再通过全连接网络对带权重特征进行学习,得到测量误差的预测值,基于该预测值完成对测量误差的修正。自主搭建了一套激光在机测量系统,采用红、绿、紫3种同材质彩色卡纸进行实验验证。结果表明,所提的方法与卷积神经网络和自注意力神经网络相比,均方误差、均方根误差和平均绝对误差均最小,稳定性最好,修正结果最接近真实值;对激光测量结果进行校正后,使其误差由原来的±28μm减小到±9μm以下,显著提高了3D打印激光在机测量的精度和稳定性。

面向纺织印染的新一代数字制造系统

针对纺织印染业数据感知、信息融合、知识推理、业务交互、人机协同等网络化、智能化产业升级需求,提出纺织印染新一代数字制造系统框架,结合业务生产全流程建立数据中台实现跨系统融合的综合智能决策;面向全生产决策领域构建决策支持组件池,推进业务系统与控制系统的融合;基于全业务生产流程数据的感知融合,搭建经营驾驶舱、订单数字化管控系统、设备数字化管控系统、能源数字化管控系统与环保安防数字化管控系统等,形成决策-执行闭环反馈的模式,实现业务和生产全流程信息管控。广东某纺织染整有限公司基于该纺织印染新一代数字制造系统框架对染色车间进行数字制造技术升级,与2019年度相比,该企业2021年度智能染色和定形示范车间人均产值提升145.0%和129.9%,良品率提升9.1%和2.6%,能源利用率提升31.9%和34.9%,在生产效率、产品质量、能源利用方面获得显著提升。

基于机器视觉的数码印花工厂自动报工系统

针对纺织行业中现有人工布匹生产订单报工管理困难的问题,设计并实现了一个基于机器视觉的数码印花工厂自动报工系统,将正在生产的布匹图像与订单库中的花型图案进行智能匹配,从而对生产订单进行快速准确的报工管理;首先系统客户端使用工业相机实时采集生产线上的印花布匹图像,并对图像进行滤波、归一化等预处理;然后将图像通过HTTP协议发送至系统服务端,利用基于Vision Transformer的神经网络模型进行特征提取和多层特征融合,再与订单库中的花型图案进行匹配,找出待报工订单;最后对匹配结果进行数据库管理,并将匹配结果返回客户端用于报工结果展示与确认操作;实验结果表明,该自动报工系统的订单匹配TOP-3命中率达到90.4%,满足工厂布匹生产需求。

基于高光谱成像的光敏印油种类区分实验

印油种类区分是法庭科学文件检验领域的重要一环,为研究无损高效区分光敏印油种类的方法。以33种不同品牌光敏印油的原始光谱数据当作对照组,对原始数据进行t-SNE降维和UMAP降维后,选择XGBoost、SVM和MLP三种分类算法,以1∶4的比例确定测试集和训练集,对原始数据和降维后的数据进行分类,同时使用网格搜索和五倍交叉验证来优化模型的性能和泛化能力。结果表明,上述三种分类算法对降维后光谱数据区分的平均准确率高于对原始光谱数据区分的平均准确率,且UMAP-MLP分类模型的区分准确率最高,可达到98%。提出的分类模型可用于光敏印油种类的快速区分。

印花面料的边缘轮廓快速提取方法

工业协作型缝纫机器人代替操作工自动完成缝合是未来发展的必然趋势,但当前的工业协作型缝纫机器人难以快速精准地定位面料边缘轮廓信息,影响缝纫效率与缝纫质量。针对印花面料提出线下使用深度学习建立面料检测模型,线上调用面料检测模型分割面料与背景并结合传统轮廓检测算法快速准确提取面料边缘轮廓的方法。首先,建立面料图像数据集,并通过卷积拆分和融合损失函数对VGG-UNet模型进行优化,将面料数据集输入至优化的VGG-UNet模型进行训练学习并构建最优面料检测模型;其次,利用最优面料检测模型分割面料与背景;然后,采用数学形态学算法对分割后的面料图像进行自适应开运算去除面料边缘的毛边;最后,利用Canny算子对去除毛边后的面料图像进行轮廓提取。实验结果表明,本文方法可较好去除面料毛边并快速精准提取印花面料的边缘轮廓,所提取的轮廓与面料边缘轮廓高度拟合,轮廓提取精度高于99%,轮廓提取时间仅需0.216 s。本文研究可为后续机器人的轨迹规划提供快速准确的坐标信息,提高缝合质量和效率,推进无人化、自动化缝合生产线的实现。

基于图案解析与视觉在线检测的电喷印控制方法

随着柔性传感器的发展,传统加工工艺难以满足其高精度生产要求。电喷印作为一种新兴的微纳加工工艺,在复杂图案加工和高精度加工方面具备明显优势。研发了一种具备反馈功能的电喷印软件控制系统,实现了图案解析和机器视觉的在线监测。首先研究了不同形式打印目标的复杂图案解析方法,进行了响应曲面法设计实验,设计了对应的实时在线视觉监测算法和复杂图案的打印路径的优化算法,建立了电喷印关键工作参数的预测数学模型,并进行了测试分析。结果表明:该控制系统实现了打印过程的自动反馈,显著缩短了工作时间,使得电喷印过程的泰勒锥可准确地按需控制,打印线段相对偏差的统计值由±11%左右,减小至±6%左右,并打印出了最小半径为103μm的液滴和最小线宽为151μm的线段。研究成果为柔性微纳制造工艺提供了更高效、精确的生产方法。

机组式柔印机压印辊的动态特性实验研究

压印辊动态特性对机组式柔印机印刷质量有重要影响,针对静态径向跳动难以反映印刷机的动态特性问题,研究高速生产状态下压印辊的动态精度一致性及其与墙板振动相关性,为柔印机的结构优化及状态监测提供参考依据。在分析压印辊结构、运动参数与采样频率关系的基础上建立数据采集分析模型,运用相关分析法构建动态径向跳动与墙板振动的相关性模型,开展动态跳动与振动测试研究。测试分析结果:压印辊主体动态径向跳动值约0.005至0.025mm,压印辊转动一个周期径向跳动值会突变4次。研究表明:机组式柔印机压印辊动态径向跳动以及墙板振动呈非周期性特征,各向加速度曲线均存在突变,压印辊动态径向跳动与支撑墙板X、Z向加速度呈强正相关。

椭圆形印花机台板机构的设计

椭圆形印花机台板机构在运行过程中需要能够顺利沿着直线和圆弧导轨进行,为防止运行过程中卡死,设计过程中总结了椭圆形印花机台板机构的设计方法,该设计保证了椭圆形印花机台板机构能够满足正常运行需求。通过试验表明,该设计方法较好地实现了椭圆形印花机的功能需求,为设计类似的设备提供借鉴。

基于有限元理论的胶印机橡皮滚筒模态分析

胶印机橡皮滚筒作为胶印机的关键部件影响着印刷精度。本文基于有限元理论,对胶印机橡皮滚筒进行了模态分析。首先利用Solidworks对滚筒进行了几何建模,并且导入Ansys软件中进行静力学特性分析以及振动特性分析,得出了应力、应变云图、固有频率和模态振型图。静力学分析得出,最大等效应力值为280.61MPa,小于屈服极限强度370MPa,达到实际运用的要求。模态分析结果得出滚筒前三阶主要为滚筒中间弯曲变形,最大振型主要发生在中间部分;后三阶滚筒的扭转弯曲变形,最大振型主要发生在滚筒两端和轴头。得到橡皮滚筒的一阶固有频率为380.08Hz,远远低于橡皮滚筒临界转速,为胶印机橡皮滚筒的可靠性分析提供了计算依据。

基于改进Faster RCNN的PCB表面缺陷检测研究

印刷电路板(PCB)在制造过程中不可避免地存在焊点缺焊、短路、毛刺、缺口、开路、余铜等微小缺陷。传统的基于机器视觉检测的缺陷检测方法存在检测速度慢、误检率和漏检率高、抗干扰能力弱等问题。为解决上述问题,提出一种基于改进快速区域卷积神经网络(Faster RCNN)的PCB表面缺陷检测方法。首先,在传统Faster RCNN框架的基础上,融入扩展特征金字塔网络(EFPN)以实现特征提取与融合,并进行多尺度检测,从而尽可能保留图像细节信息以提高检测性能。其次,利用K-means算法结合交并比(IoU)优化区域建议网络(RPN)结构中的锚框参数,使得生成的锚框方案更有针对性。试验结果表明,改进Faster RCNN在PCB缺陷数据集上的全类平均正确率(mAP)值达到93.4%、检测速度达到每秒21.79帧。所提方法可推广应用至芯片、光学器件表面微小缺陷在线检测,从而提升工业生产效率。

基于机器学习的PCB缺陷检测与分类方法研究

印制电路板(PCB)在制造过程中难免会产生各种缺陷。为了提高生产效率和产品质量,针对PCB制造中常见的缺陷进行检测与分类。通过构建深度学习模型,采用图像处理技术,对PCB图像进行全面而高效的缺陷检测。通过大量的训练数据,模型能够学习各类缺陷的特征,包括但不限于短路、断路、焊接不良等。使用举例说明和推导论证等方法对PCB缺陷进行分类研究,在深度学习模型的巧妙构建和分类算法的优化应用相辅相成的应用基础上,为提高生产效率和产品质量提供了可行的解决方案,推动了PCB制造业智能化方向的发展。

四足机器人仿生腿增强碳纤维3D打印技术及其实验研究

为了提高四足机器人仿生腿的使用性能,使其腿部结构满足高承载、轻量化要求,提出一种以连续碳纤维(CCF)为增强材料,以短切碳纤维增强尼龙为基体材料的混合增强3D打印技术,通过样条拉伸实验对碳纤维复合材料的伸性能进行了验证。使用连续与短切碳纤维混合增强3D打印制备四足机器人仿生腿,对四足机器人常见4种工况进行了静力学仿真,选取两类典型工况进行载荷测试实验,可知在站立工况下承载力提升了19.05%,变形量减少了50.70%,在30°外展工况下承载力提升了3.14%,变形量减少了43.05%,且重量减轻了18.83%,验证了连续碳纤增强材料替代传统铝合金材料的可能性。