Method for Detecting Industrial Defects in Intelligent Manufacturing Using Deep Learning

With the advent of Industry 4.0,marked by a surge in intelligent manufacturing,advanced sensors embedded in smart factories now enable extensive data collection on equipment operation.The analysis of such data is pivotal for ensuring production safety,a critical factor in monitoring the health status of manufacturing apparatus.Conventional defect detection techniques,typically limited to specific scenarios,often require manual feature extraction,leading to inefficiencies and limited versatility in the overall process.Our research presents an intelligent defect detection methodology that leverages deep learning techniques to automate feature extraction and defect localization processes.Our proposed approach encompasses a suite of components:the high-level feature learning block(HLFLB),the multi-scale feature learning block(MSFLB),and a dynamic adaptive fusion block(DAFB),working in tandem to extract meticulously and synergistically aggregate defect-related characteristics across various scales and hierarchical levels.We have conducted validation of the proposed method using datasets derived from gearbox and bearing assessments.The empirical outcomes underscore the superior defect detection capability of our approach.It demonstrates consistently high performance across diverse datasets and possesses the accuracy required to categorize defects,taking into account their specific locations and the extent of damage,proving the method’s effectiveness and reliability in identifying defects in industrial components.

Research on Computer Vision Detection Technology and Applications on Machinery Manufacturing and Automation

In this paper, we conduct research on general computer vision detection technology and the applications on machinery manufacturing and automation. Mechanical design manufacturing and the automation has profound connotation and good development prospects. Master its development trend can be more clear understanding of mechanical design and manufacturing and its automation in the future, it will open up a broader space for development. The development of modern science and basic technology, greatly promote the cross of different subjects and general penetration, the technology of the mechanical industry structure, product structure, function and structure, mode of production and the management system has changed dramatically.

A Hybrid Deep Learning and Machine Learning-Based Approach to Classify Defects in Hot Rolled Steel Strips for Smart Manufacturing

Smart manufacturing is a process that optimizes factory performance and production quality by utilizing various technologies including the Internet of Things(IoT)and artificial intelligence(AI).Quality control is an important part of today’s smart manufacturing process,effectively reducing costs and enhancing operational efficiency.As technology in the industry becomes more advanced,identifying and classifying defects has become an essential element in ensuring the quality of products during the manufacturing process.In this study,we introduce a CNN model for classifying defects on hot-rolled steel strip surfaces using hybrid deep learning techniques,incorporating a global average pooling(GAP)layer and a machine learning-based SVM classifier,with the aim of enhancing accuracy.Initially,features are extracted by the VGG19 convolutional block.Then,after processing through the GAP layer,the extracted features are fed to the SVM classifier for classification.For this purpose,we collected images from publicly available datasets,including the Xsteel surface defect dataset(XSDD)and the NEU surface defect(NEU-CLS)datasets,and we employed offline data augmentation techniques to balance and increase the size of the datasets.The outcome of experiments shows that the proposed methodology achieves the highest metrics score,with 99.79%accuracy,99.80%precision,99.79%recall,and a 99.79%F1-score for the NEU-CLS dataset.Similarly,it achieves 99.64%accuracy,99.65%precision,99.63%recall,and a 99.64%F1-score for the XSDD dataset.A comparison of the proposed methodology to the most recent study showed that it achieved superior results as compared to the other studies.

Intelligent Metal Detection and Disposal Automation Equipment Based on Geometric Optimization Driving Algorithm

In order to solve the problem of metal impurities mixed in the production line of wood pulp nonwoven raw materials,intelligent metal detection and disposal automation equipment is designed.Based on the principle of electromagnetic induction,the precise positioning of metal coordinates is realized by initial inspection and multi-directional re-inspection.Based on a geometry optimization driving algorithm,the cutting area is determined by locating the center of the circle that covers the maximum area.This approach aims to minimize the cutting area and maximize the use of materials.Additionally,the method strives to preserve as many fabrics at the edges as possible by employing the farthest edge covering circle algorithm.Based on a speed compensation algorithm,the flexible switching of upper and lower rolls is realized to ensure the maximum production efficiency.Compared with the metal detection device in the existing production line,the designed automation equipment has the advantages of higher detection sensitivity,more accurate metal coordinate positioning,smaller cutting material areas and higher production efficiency,which can make the production process more continuous,automated and intelligent.

Battery health management-a perspective of design,optimization,manufacturing,fault detection,and recycling

This paper explores the key aspects of battery technology,focusing on lithium-ion,lead-acid,and nickel metal hydride(NiMH)batteries.It delves into manufacturing processes and highlighting their significance in optimizing battery performance.In addition,the study investigates battery fault detection,emphasizing the importance of early diagnosis using artificial intellignece(AI)and machine learning(ML)methods.This paper also addresses battery recycling techniques,discussing methods such as pyrometallurgy,hydrometallurgy,mechanical separation,and electrodialysis,considering their environmental impact.This comprehensive analysis sheds light on the evolution of battery technology and its role in sustainable energy systems.

Predictive defect detection for prototype additive manufacturing based on multi-layer susceptibility discrimination

This paper presents a predictive defect detection method for prototype additive manufacturing(AM)based on multilayer susceptibility discrimination(MSD).Most current methods are significantly limited by merely captured images,disregarding the differences between layer-by-layer manufacturing approaches,without combining transcendental knowledge.The visible parts,originating from the prototype of conceptual design,are determined based on spherical flipping and convex hull theory,on the basis of which theoretical template image(TTI)is rendered according to photorealistic technology.In addition,to jointly consider the differences in AM processes,the finite element method(FEM)of transient thermal-structure coupled analysis was conducted to probe susceptible regions where defects appeared with a higher possibility.Driven by prior knowledge acquired from the FEM analysis,the MSD with an adaptive threshold,which discriminated the sensitivity and susceptibility of each layer,was implemented to determine defects.The anomalous regions were detected and refined by superimposing multiple-layer anomalous regions and comparing the structural features extracted using the Chan-Vese(CV)model.A physical experiment was performed via digital light processing(DLP)with photosensitive resin of a non-faceted scaled V-shaped engine block prototype with cylindrical holes using a non-contact profilometer.This MSD method is practical for detecting defects and is valuable for a deeper exploration of barely visible impact damage(BVID),thereby reducing the defect of prototypical mechanical parts in engineering machinery or process equipment via intellectualized machinevision.

基于改进YOLOv5s的玻璃盖板划伤检测算法

针对当前玻璃盖板检测速度较慢、精确率较低的问题,提出一种基于YOLOv5s算法的玻璃盖板划伤检测改进模型。首先,借鉴ResNeXt结构和大核注意力(largekernelattention,LKA)结构改进原C3模块,增强网络对于特征的检测和提取能力;其次,向网络中引入BiFPN模块,提高网络的特征融合能力和小目标检测能力;最后,使用EIOU损失函数替换原网络中的CIOU损失函数,提高锚框生成的准确性和模型收敛速度。结果表明,改进后模型,精确率达到98.2%,召回率达到98.4%,实现玻璃盖板划伤的高效检测。

焊接智能化监测技术研究现状与展望

在国家“十四五”智能制造和2035制造业高质量发展远景目标规划下,智能化焊接技术的重要性不言而喻.首先,分析了该技术在学术界和工业界的成果发表情况,对目前成果分布的特点进行了总结.此外,列出了该学科方向举办的系列重要学术会议,充分展示了该学科的研究热度.其次,分别从声音、光谱、视觉、热学及多信息融合监测角度出发,综述了焊接/增材技术在缺陷在线检测、过程动态表征、质量监控等方面最新的国内外研究进展,表明了多源信息融合技术是焊接智能化监测技术未来发展的主流.最后,总结了现阶段国内焊接智能化-缺陷在线监测基础研究存在的“六多六少”现象,并从多场景拓展应用出发,指出了焊接智能监测技术的未来发展目标与重点突破问题.

基于虚拟仿真技术的智能制造生产线自动控制系统

针对智能制造生产线中视觉分拣容易产生漏检和误检的问题,提出一种基于虚拟仿真技术的智能制造生产线自动控制系统。系统创新地使用云端PLC结合人工智能进行虚拟仿真,提高了自动控制的算力,使整体系统控制更加灵活可控。同时结合YOLOv5算法进行目标检测,在保证检测精确度的同时,进一步提高目标检测效率。经过实际仿真实验,设计的自动控制系统召回率、精确率以及平均精度均值等指标均符合实际生产需求,控制系统更加精确。

基于数字孪生的矿山散料堆场堆取料机智能监测系统

在许多涉及散料装卸作业的大型储料场中,斗轮堆取料机被视为当前最为理想的大型可连续作业机械,为了延长其使用寿命,降低维修成本并解决人工巡检不便的问题,提出了一种基于五维数字孪生的智能健康监测系统。通过机身外部布设光纤光栅传感器以及内置电机实时运转数据获取堆取料机的当前工作状态,并将数据传入内部信息交互通信网络进行数据的分离存储与融合处理,在消除双光栅由于机械疲劳所带来的温度补偿误差后,构建了多数据融合的、立体化的堆取料机数字健康模型,实现了堆取料机健康状态的智能化预测与立体化监测。通过在秦皇岛港散料矿物储料场的QL6000.55型斗轮堆取料机进行全系统的安装运行,极大促进了料场数字化进程,改变了管理模式,提高了生产效率,直接增加了经济效益。研究表明:该系统能够可靠地提供斗轮取料机的实时工作状态,对基本的故障类型有着一定的预警效果,降低了堆取料机维护的人力与物力投入,为矿区大型机械健康监测提供了有益参考。

基于质量4.0的印制电路板智能缺陷检测研究

新一代信息技术的高速发展为制造业的转型与发展提供了机遇,同时也推动了制造质量管理方式的重大变革。本文结合制造业发展实际情况,概述了质量4.0的基本理论及关键技术,并进一步探讨了质量4.0的实施与落地应用。具体而言,将印制电路板(printed circuit board,PCB)缺陷检测作为研究案例,设计了基于质量4.0的PCB智能缺陷检测方案,并提出了缺陷检测的5个关键评价标准;提出的检测方案可有效帮助PCB制造企业过滤缺陷假点、控制产品良率、获取缺陷解决建议,并为员工掌握专业检测技能提供学习和培训平台。本文旨在研究质量4.0环境下的智能缺陷检测及其PCB中的应用,以推动制造业质量管理数字化和智能化转型。

基于三维激光扫描技术的智能制造生产线目标检测研究

智能制造生产线目标图像数据采集过程受到噪声、光照变化等问题,导致输入图像的质量不佳,进而影响目标检测的准确性,对此,设计一种基于三维激光扫描技术的智能制造生产线目标检测方法。首先,采用三维激光扫描仪获取待检测目标点云数据,通过点云变换准则计算数据之间的拓扑关联,生成完整三维激光图像。然后,利用杂交小波变换对三维激光目标图像进行去噪处理。最后,使用能量、熵、对比度、相关性4种参数提取图像纹理特征并采取归一化处理,创建最优分类函数,并运用支持向量机算法划分生产线目标样本图像数据,完成智能制造生产线目标检测工作。实验结果表明,所提方法的交并比值最高时达到0.97,F1值最高时达到0.96,平均检测耗时仅为0.53 s,说明所提方法的检测精度高、效率快,鲁棒性强,在实际操作中具备相当的可用性,为智能制造产业提供技术支持。

增材制造小缺陷的显微CT检测

通过高精度金属增材制造技术设计制造了两组不同类型的缺陷试件,并基于显微CT检测技术和缺陷解剖金相检测方式,研究显微CT对增材制造小缺陷的实际检测能力。试验结果表明,显微CT在体素尺寸5μm下能有效检出尺寸为20μm的人工缺陷;金相检测与CT检测结果基本一致,缺陷尺寸测量差小于10μm;由于部分体积效应的影响,更小尺寸缺陷的尺寸测量结果误差更大。

Deep Industrial Image Anomaly Detection: A Survey

The recent rapid development of deep learning has laid a milestone in industrial image anomaly detection(IAD).In this pa-per,we provide a comprehensive review of deep learning-based image anomaly detection techniques,from the perspectives of neural net-work architectures,levels of supervision,loss functions,metrics and datasets.In addition,we extract the promising setting from indus-trial manufacturing and review the current IAD approaches under our proposed setting.Moreover,we highlight several opening chal-lenges for image anomaly detection.The merits and downsides of representative network architectures under varying supervision are discussed.Finally,we summarize the research findings and point out future research directions.More resources are available at https://github.com/M-3LAB/awesome-industrial-anomaly-detection.

Defect detection and repair algorithm for structures generated by topology optimization based on 3D hierarchical fully convolutional network

Customized 3D-printed structural parts are widely used in surgical robotics.To satisfy the mechanical properties and kinematic functions of these structural parts,a topology optimization technique is adopted to obtain the optimal structural layout while meeting the constraints and objectives.However,topology optimization currently faces some practical challenges that must be addressed,such as ensuring that structures do not have significant defects when converted to additive manufacturing models.To address this problem,we designed a 3D hierarchical fully convolutional network(FCN)to predict the precise position of the defective structures.Based on the prediction results,an effective repair strategy is adopted to repair the defective structure.A series of experiments is conducted to demonstrate the effectiveness of our approach.Compared to the 2D fully convolutional network and the rule-based detection method,our approach can accurately capture most defect structures and achieve 89.88%precision and 95.59%recall.Furthermore,we investigate the impact of different ways to increase the receptive field of our model,as well as the trade-off between different defect-repairing strategies.The results of the experiment demonstrate that the hierarchical structure,which increases the receptive field,can substantially improve the defect detection performance.To the best of our knowledge,this paper is the first to investigate 3D defect prediction and repair for topology optimization in conjunction with deep learning algorithms,providing practical tools and new perspectives for the subsequent development of topology optimization techniques.

广西17家胶合板生产企业的主要职业卫生问题调查分析

目的:探讨广西17家胶合板生产企业存在的主要职业危害因素、职业防护设施效果以及对工人健康的影响,为减少职业性危害、保护工人身心健康提供科学依据。方法:以17家胶合板生产企业为观察对象,通过职业病危害因素检测和职业卫生调查,对主要职业卫生问题进行综合分析评价。结果:17家胶合板生产企业木粉尘、甲醛、噪声、高温的超标率分别为5.6%、28.1%、24.9%、29.1%。17家噪声超标,5家木粉尘和甲醛超标,仅2家高温超标。生产防护设施的防尘、防毒符合率为98.3%,防暑设施符合率为88.2%,噪声防护设施符合率为76.5%。个人防护用品佩戴与使用符合率为52.9%,安装洗眼喷淋装置符合率为58.8%。17家企业总体检率为42.6%(705/1654),体检异常检出率为14.6%,其中听力、胸部X线片、肺功能异常检出率分别为7.4%、2.1%、1.7%。结论:广西17家胶合板生产企业的主要职业卫生问题是木粉尘、甲醛、噪声、高温,尤以噪声较为突出。针对木粉尘、甲醛的防控效果较好,对于高温、噪声的防控措施需要进一步加强。

金属异物缺陷演化特性及其对产线K值的影响机制

电池制造过程出现的缺陷问题会极大影响电池产品的安全性等,其中产线金属异物侵入可能导致自发性内短路甚至引发热失控,然而目前关于在电池内部的演化机理及相应的外在表征的研究较少,尤其是针对微小金属异物的研究。因此本研究在电池中植入百微米直径铜颗粒,模拟产线金属异物侵入形成缺陷电池,分析了缺陷电池内短路电流特征,拆解研究了内短路区域的微观结构,通过模型仿真了内短路区域的电位分布,综合解释了缺陷对产线关键检测指标K值(电压下降率)的影响规律与机制,并在实际试制线大容量电池上进行了验证。相关研究成果可用于提高产线缺陷检出率,预防潜在的安全事故。研究结果表明,铜颗粒等金属异物侵入电池后,可能导致正极-颗粒-负极和正极-负极两种模式的内短路,内短路电流在正极中产生的电位梯度可抑制颗粒的进一步溶解,从而使得在K值测试条件下的两种内短路模式均会达到平衡状态。两种模式的内短路程度相近,内短路电流处在0.1~1 mA量级。相同的内短路电流对于不同容量单体的K值影响不同,产线上为保证检测效果,随着电池产品容量的增加,K值检测阈值及正常电池的基准值需要相应降低。

汽车前底盘装配视觉检测系统设计与应用

为解决汽车底盘混流装配错装、漏装和人工检测效率低的问题,设计了基于YOLOv3-Tiny的在线检测系统。该检测系统利用4套光源-相机组合的成像系统,从多角度获取前底盘模块的全貌图像,利用基于差分统计的条纹识别算法剔除低质量图像;根据检测目标特性,简化非极大值抑制算法,优化检测过程。实验和现场运行结果表明:检测系统目标无遮挡检出率达到100%,综合识别准确率达到99.95%,平均检测时间3.5 s,较之前人工检测效率提升94.55%,检测系统具有较高的准确度和检测效率,在汽车工业中实现了柔性化和智能化的目标检测应用。

电机制造中检测技术及设备应用

在电机制造过程中做好电机检测,有效保证电机的生产制造质量,为后续改进电机设计方案提供可靠的数据支持。如果要保证检测结果的精确性和可靠性,就必须选择合理的检测技术及相关设备,并对这些设备加以有效应用。在科技迅速发展的背景下,电机检测技术与设备得到创新发展,类型丰富多样,需要结合电机制造的实际需求来针对性选用,主要对电机制造中检测技术及设备应用进行详细阐述。

基于有监督对比学习的焊缝缺陷X射线检测方法

【目的】基于深度学习的表面缺陷检测算法广泛应用于表面缺陷检测。然而,在焊缝缺陷检测领域,焊缝缺陷外观特征上具有同类别样本偏差大而不同类别样本偏差小的特点,这给焊缝缺陷的有效识别带来了挑战。【方法】为此,提出一种有监督对比学习的焊缝缺陷检测方法(SCL-DD),将有监督对比学习拓展到焊缝缺陷检测领域,通过正负样本进行有效的相似计算,使同一类别的缺陷样本在嵌入空间上更加接近,不同类别的缺陷彼此远离,降低类间偏差和跨类偏差对检测性能的不良影响。【结果】引入余弦分类器,通过计算特征编码与分类原型之间的余弦相似度,提高差异性缺陷样本的检测性能。在钢管焊缝表面缺陷数据集上验证所提出方法的性能。【结论】SCL-DD方法平均精度为96.9,优于其他深度学习网络。