A review on wire arc additive manufacturing: Monitoring,control and a framework of automated system

Wire arc additive manufacturing technology (WAAM) has become a very promising alternative to high-value large metal components in many manufacturing industries. Due to its long process cycle time and arc-based deposition, defect monitoring, process stability and control are critical for the WAAM system to be used in the industry. Although major progress has been made in process development, path slicing and programming, and material analysis, a comprehensive process monitoring, and control system are yet to be developed. This paper aims to provide an in-depth review of sensing and control design suitable for a WAAM system, including technologies developed for the generic Arc Welding process, the Wire Arc Additive Manufacturing process and laser Additive Manufacturing. Particular focus is given to the integration of sensor-based feedback control, and how they could be implemented into the WAAM process to improve its accuracy, reliability, and efficiency. The paper concludes by proposing a framework for sensor-based monitoring and control system for the GMAW based WAAM process. This framework provides a blueprint for the monitoring and control strategies during the WAAM process and aims to identify and reduce defects using information fusion techniques.     

Research and application of artificial intelligence techniques for wire arc additive manufacturing: a state-of-the-art review

Recent development in the Wire arc additive manufacturing (WAAM) provides a promising alternative for fabricating high value-added medium to large metal components for many industries such as aerospace and maritime industry. However, challenges stemming from the demand for increasingly complex and high-quality products, hinder the widespread adoption of the conventional WAAM method for manufacturing industries. The development of artificial intelligence (AI) techniques may provide new opportunities to upgrade WAAM to the next generation. Hence, this paper provides a comprehensive review of the state-of-the-art research on AI techniques in WAAM. Firstly, we proposed a novel concept of intelligent wire arc additive manufacturing (IWAAM) and revealed the challenges of developing IWAAM. Secondly, an overview of the research progress of applying AI techniques to several aspects of the WAAM process chain, including fabrication process pre-design, online deposition control and offline parameter optimization is provided. Thirdly, the relevant machine learning algorithms, and the knowledge of corresponding AI techniques, are also reviewed in detail. Through reviewing the current research articles, issues of applying AI techniques to the WAAM process are presented and analysed. Finally, future research perspectives in terms of novel AI technique applications and AI technique enhancement are discussed. Through this systematic review, it is expected that WAAM may gradually develop into a smart/intelligent manufacturing technology in the context of Industry 4.0 through the adoption of AI techniques.     

A knowledge-based process planning framework for wire arc additive manufacturing

Wire arc additive manufacturing (WAAM) provides a rapid and cost-effective solution for fabricating low-to-medium complexity and medium-to-large size metal parts. In WAAM, process settings are well-recognized as fundamental factors that determine the performance of the fabricated parts such as geometry accuracy and microstructure. However, decision-making on process variables for WAAM still heavily relies on knowledge from domain experts. For achieving reliable and automated production, process planning systems that can capture, store, and reuse knowledge are needed. This study proposes a process planning framework by integrating a WAAM knowledge base together with our in-house developed computer-aided tools. The knowledge base is construed with a data-knowledge-service structure to incorporate various data and knowledge including metamodels and planning rules. Process configurations are generated from the knowledge base and then used as inputs to computer-aided tools. Moreover, the process planning system also supports the early-stage design of products in the context of design for additive manufacturing. The proposed framework is demonstrated in a digital workflow of fabricating industrial-grade components with overhang features.     

Optimal droplet transfer mode maintenance for wire + arc additive manufacturing (WAAM) based on deep learning

Journal of Intelligent Manufacturing - In the last decade, wire?+?arc additive manufacturing (WAAM), which is one of the most promising metal additive manufacturing technologies, has...     

Control of deposition height in WAAM using visual inspection of previous and current layers

Journal of Intelligent Manufacturing - Wire plus arc additive manufacturing (WAAM) has been demonstrated to be a powerful technique to produce large-scale metal parts with low cost. However,...     

Investigation of humping phenomenon for the multi-directional robotic wire and arc additive manufacturing

Wire Arc Additive Manufacturing (WAAM) is a promising technology for fabricating medium to large scale metallic parts with excellent productivity and flexibility. Due to the positional capability of some welding processes, WAAM is able to deposit parts with overhanging features in an arbitrary direction without additional support structures. The dimensional quality of the overhanging parts may however deteriorate due to the humping effect, which appears as a series of periodic beadlike protuberances on the weld deposits. There has been significant research on the humping phenomenon in the downhand welding, but it is doubtful whether the existing theories of humping formation can be applied in the positional deposition during WAAM process. This study has therefore provided an experimental work to investigate the formation of the humping phenomena in the positional deposition during additive manufacturing with the gas metal arc welding. Firstly, the mechanism of humping formation was analysed to explain humping occurrence for positional deposition. Then, the mechanism was validated through experiments with different welding parameters and positions. Finally, a series of guidelines are summarised to assist the path planning and process parameter selection processes in multi-directional WAAM.     

Decision-based process planning for wire and arc additively manufactured and machined parts

The conventional manufacturing of aircraft components is based on the machining from bulk material and the buy-to-fly ratio is high. This, in combination with the often low machinability of the materials in use, leads to high manufacturing costs. To reduce the production costs for these components, a process chain was developed, which consists of an additive manufacturing process and a machining process. To fully utilize the process chain’s capabilities, an integrated process planning approach is necessary. As a result, the work sequence can be optimized to achieve the economically most suitable sequence. In this paper, a method for a joint manufacturing cost calculation and subsequent decision-based cost minimization is proposed for the wire and arc additive manufacturing (WAAM) & milling process chain. Furthermore, the parameters’ influence on the results and the magnitude of their influence are determined. These results make it possible to design an economically optimal work sequence and to automate the process planning for this process chain.     

缺陷检测技术的发展与应用研究综述

为满足智能制造企业对产品质量检测的需求, 服务制造企业生产管理, 对缺陷检测技术的研究现状、典型方法和应用进行梳理.首先总结了磁粉检测法、渗透检测法、涡流检测法、超声波检测法、机器视觉和基于深度学习的缺陷检测技术的优缺点; 对比分析了磁粉检测法、渗透检测法、涡流检测法、超声波检测法、机器视觉检测的主流缺陷检测技术和基于深度学习的缺陷检测技术的研究现状; 然后, 梳理了缺陷检测技术在电子元器件、管道、焊接件、机械零件和质量控制中的典型应用; 最后, 对缺陷检测技术的研究情况进行了总结和展望, 指出该研究领域亟需解决的问题和未来发展的方向, 并从高精度、高定位、快速检测、小目标、复杂背景、被遮挡物体检测、物体关联关系等几个方面总结近年来发表在ICCV (International Conference on Computer Vision)和CVPR (International Conference on Computer Vision and Pattern Recognition)等知名国际会议上相关论文的核心思想和源代码, 为缺陷检测技术的进一步发展提供理论和应用上的借鉴与参考.     

Reflective workpiece detection and localization for flexible robotic cells

A smart vision system for industrial robotic cells is presented. It can recognize and localize a reflective workpiece, and allows for automatic adjustments of the robot program. The purpose of the study is to improve industrial robots awareness of the environment and to increase adaptability of the manufacturing processes where full control over environment is not achievable. This approach is particularly relevant to small batch robotic production, often suffering from only partial control of the process parameters, such as the order of jobs, workpiece position, or illumination conditions.A distinguishing aspect of the study is detection of workpieces made of diverse materials, including shiny metals. Reflective surfaces are common in the industrial manufacturing, but are rarely considered in the research on object recognition because they hinder many of the object recognition algorithms. The proposed solution has been qualified and tested on a selected benchmark in a realistic workshop environment with artificial light conditions. The training of the object recognition software is an automatic process and can be executed by non-expert industrial users to allow for recognition of different types of objects.     

基于改进部分卷积的瑕疵布匹图像生成算法

针对工业生产中布匹瑕疵自动化检测模型训练时缺少带瑕疵位置信息的瑕疵布匹图像数据集的问题,本文提出了一种以改进的部分卷积网络作为基本框架的带瑕疵位置信息的瑕疵布匹图像生成模型EC-PConv.该模型引入小尺寸瑕疵特征提取网络,将提取出的瑕疵纹理特征与空白mask拼接起来形成带有位置信息和瑕疵纹理特征的mask,然后以修复方式生成带有瑕疵位置信息的瑕疵布匹图像,另外,本文提出一种结合MSE损失的混合损失函数以生成更加清晰的瑕疵纹理.实验结果表明,与最新的GAN生成模型相比,本文提出的生成模型的FID值降低了0.51;生成的瑕疵布匹图像在布匹瑕疵检测模型中查准率P和MAP值分别提高了0.118和0.106.实验结果表明,该方法在瑕疵布匹图像生成上比其他算法更稳定,能够生成更高质量的带瑕疵位置信息的瑕疵布匹图像,可较好地解决布匹瑕疵自动化检测模型缺少训练数据集的问题.     

A hybrid deep learning model of process-build interactions in additive manufacturing

Laser powder bed fusion (LPBF) is a technique of additive manufacturing (AM) that is often used to construct a metal object layer-by-layer. The quality of AM builds depends to a great extent on the minimization of different defects such as porosity and cracks that could occur by process deviation during machine operation. Therefore, there is a need to develop new analytical methods and tools to equip the LPBF process with the inspection frameworks that assess the process condition and monitor the porosity defect in real-time. Advanced sensing is recently integrated with the AM machines to cope with process complexity and improve information visibility. This opportunity lays the foundation for online monitoring and assessment of the in-process build layer. This study presents the hybrid deep neural network structure with two types of input data to monitor the process parameters that result in porosity defect in cylinders’ layers. Results demonstrate that statistical features extracted by wavelet transform and texture analysis along with original powder bed images, assist the model in reaching a robust performance. In order to illustrate the fidelity of the proposed model, the capability of the main pipeline is examined and compared with different machine learning models. Eventually, the proposed framework identified the process conditions with an F-score of 97.14%. This salient flaw detection ability is conducive to repair the defect in real-time and assure the quality of the final part before the completion of the process.     

铁路路基病害智能检测方法

铁路路基病害不断增加,其中翻浆冒泥病害和路基下沉病害最为常见,严重影响铁路安全运营。车载地质雷达检测方法是铁路路基病害检测的一种常用方法。然而,通过雷达图像对路基病害进行识别仍以人工判别为主,且需要专家丰富的经验。由于路基病害形态复杂、尺度较大,如何对铁路路基病害进行自动识别是一项具有挑战性的任务。针对这些问题,通过探地雷达实地采集数据构建了铁路路基病害数据集,提出了一种铁路路基病害实时智能检测方法（LS-YOLOv3）。该方法针对铁路路基病害的特点设计了深度残差网络提取病害特征,并采用多尺度预测网络在4个尺度上进行特征融合,形成铁路路基病害实时检测模型。实验结果表明,与传统的HOG+SVM算法、双阶段的Faster-RCNN算法、Cascade R-CNN算法、单阶段的YOLOv3算法和轻量化的TinyYOLOv2、TinyYOLOv3算法相比,提出的算法获得了最高的均值平均精度（82.67%）并在配有英伟达GeForce RTX 2080Ti GPU的计算平台上实现了实时检测（32.26 frame/s）。旨在尝试提供一种铁路路基病害检测领域的实时性新方法。     

Automatic visual inspection: An approach with multi-instance learning

One of the industrial applications of computer vision is automatic visual inspection. In the last decade, standard supervised learning methods have been used to detect defects in different kind of products. These methods are trained with a set of images where every image has to be manually segmented and labeled by experts in the application domain. These manual segmentations require a large amount of high quality delineations (on pixels), which can be time consuming and often a difficult task. Multi-instance learning (MIL), in contrast to standard supervised classifiers, avoids this task and can, therefore, be trained with weakly labeled images. In this paper, we propose an approach for the automatic visual inspection that uses MIL for defect detection. The approach has been tested with data from three artificial benchmark datasets and three real-world industrial scenarios: inspection of artificial teeth, weld defect detection and fishbone detection. Results show that the proposed approach can be used with weakly labeled images for defect detection on automatic visual inspection systems. This approach is able to increase the area under the receiver-operating characteristic curve (AUC) up to 6.3% compared with the naïve MIL approach of propagating the bag labels.     

基于激光雷达数据的行人检测

在自动驾驶领域涉及的众多任务中,行人识别是必不可少的技术之一。针对基于图像数据的行人检测算法无法获得行人深度的问题,提出了基于激光雷达数据的行人检测算法。该算法结合传统基于激光雷达数据的运动目标识别算法和基于深度学习的点云识别算法,可以在不依赖图像数据的条件下感知和检测行人,进而获取行人的准确三维位置,辅助自动驾驶控制系统作出合理决策。该算法在KITTI三维目标检测任务数据集上进行性能测试,中等难度测试达到33.37%的平均准确度,其表现领先于其他基于激光雷达的算法,充分证明了该方法的有效性。     

Automatic work objects calibration via a global–local camera system

In a human–robot collaborative manufacturing application where a work object can be placed in an arbitrary position, there is a need to calibrate the actual position of the work object. This paper presents an approach for automatic work-object calibration in flexible robotic systems. The approach consists of two modules: a global positioning module based on fixed cameras mounted around robotic workspace, and a local positioning module based on the camera mounted on the robot arm. The aim of the global positioning is to detect the work object in the working area and roughly estimate its position, whereas the local positioning is to define an object frame according to the 3D position and orientation of the work object with higher accuracy. For object detection and localization, coded visual markers are utilized. For each object, several markers are used to increase the robustness and accuracy of the localization and calibration procedure. This approach can be used in robotic welding or assembly applications.     

一种新型智能图像监控系统

针对目前流行的图像监控系统的缺陷，本论文研制开发了一种新型智能图像监 控系统．该系统实现了监控场景的自动光圈调整和自动聚焦；并能够实时检测、定位监控场 景中的特定颜色目标；能够自动检测跟踪运动目标，并解决了运动目标检测中图像刷新率问 题，极大提高了监控系统的智能化和自动化程度．实践证明，系统工作性能良好．     

晶圆表面缺陷在线检测研究

针对准确与实时检测晶圆表面缺陷的需求,提出了一种基于主成分分析(Principal Component Analysis, PCA)和贝叶斯概率模型(Bayesian Probability Model, BPM)的在线检测算法。首先,改进双边滤波方法以消除晶圆表面图像中的噪声和突出晶圆表面的模式特征。然后,提取晶圆表面缺陷的Hu不变矩、方向梯度直方图(Histogram of Oriented Gradients, HOG)和尺度不变特征变换特征(Scale Invariant Feature Transform, SIFT)。接着,采用PCA方法对特征进行降维。最后,在离线建模阶段构建各种缺陷模式的BPMs;在在线检测阶段采用胜者全取(Winner-take-all, WTA)法判断缺陷的模式和构建新缺陷模式的BPMs。提出算法在WM-811K晶圆数据库中得到了87.2%的检测准确率。单副图像的平均检测时间为40.5ms。实验结果表明,提出算法具有较高的检测准确性与实时性,可以实际应用到集成电路制造产线的晶圆表面缺陷在线检测中。     

基于卷积神经网络的宇航电源光学检测技术

传统自动光学检测（AOI）方法难以适应宇航电源生产线多品种、小批量的特点，具有识别率低、操作复杂等问题。利用卷积神经网络(CNN)学习速度快、特征提取效果好的优势，提出了一种能够对宇航电源产品质量进行可靠检验的光学检测技术。通过对历史生产数据的精细化筛选构建了训练样本库，并设计了宇航电源产品光学检验专用卷积神经网络；将Canny算子边缘检测与CNN图像识别相结合，实现了印制板装配图信息的自动读取。与传统AOI检测方法相比，该方法缺陷识别率高达99%，且检验过程简单，提高了宇航电源产品光学检验工作效率，已应用于宇航电源生产线。     

A comprehensive process of reverse engineering from 3D meshes to CAD models

In an industrial context, most manufactured objects are designed using CAD (Computer-Aided Design) software. For visualization, data exchange or manufacturing applications, the geometric model has to be discretized into a 3D mesh composed of a finite number of vertices and edges. However, the initial model may sometimes be lost or unavailable. In other cases, the 3D discrete representation may be modified, e.g. after numerical simulation, and no longer corresponds to the initial model. A retro-engineering method is then required to reconstruct a 3D continuous representation from the discrete one.In this paper, we present an automatic and comprehensive retro-engineering process dedicated mainly to 3D meshes obtained initially by mechanical object discretization. First, several improvements in automatic detection of geometric primitives from a 3D mesh are presented. Then a new formalism is introduced to define the topology of the object and compute the intersections between primitives. The proposed method is validated on 3D industrial meshes.     

车载探地雷达技术在地铁隧道检测中的应用

车载探地雷达技术在地铁隧道中的检测得到广泛应用,对保障地铁隧道的安全性和可靠性起到重要的作用。为了对地铁隧道缺陷进行精确检测,并提升检测的效率,构建基于Yolov5模型的车载探地雷达检测系统。首先采用零时校正、去直流、背景去除和图像增益方法对信号和图像进行去噪。然后基于Yolov5目标检测模型,引入SPP-Bottleneck模块进行改进,最后构建基于Yolov5模型的车载探地雷达检测系统。结果显示,改进后的Yolov5模型在置信度相同的条件下,相较于原始模型具有更高的F1值。在实例应用中,基于Yolov5模型的车载探地雷达检测系统F1、精确度、召回率平均值分别为0.884、0.873和0.895,该模型对于隧道中的缺陷检测具有有效性。Yolov5目标检测模型的检测时间为0.3s,相较于其他三种检测模型,效率分别提升了93.75%、84.2%和50.0%,更具有实际应用价值。此次研究解决了传统车载探地雷达技术存在的问题,对地铁的运营和维护具有重要的意义。