Automatic Inspection Research Articles

Investigation of solder beading phenomenon under surface-mounted electrolytic capacitors

PurposeThe purpose of this paper is to study the solder beading phenomenon (referring to larger-sized solder balls) of surface-mounted electrolytic capacitors. Solder beading could induce failures by violating the minimal electrical clearance on the printed circuit board (PCB). In modern lead-free reflow soldering, especially in high-reliability industries, such as automotive, aeroplane and aerospace, detecting and preventing such defects is essential in reliable and cost-effective manufacturing.Design/methodology/approachThe large size of the involved components may block the view of automatic optical inspection; therefore, X-ray inspection is necessary. To detect the failure mode, X-ray imaging, cross-section grinding, optical microscopy and Fourier transformed infrared spectroscopy were used. High-resolution noncontact profilometry and optical microscopy were used to analyse component designs. The surface mounting process steps were also analysed to reveal their dependence on the issue. Test methods were designed and performed to reveal the behaviour of the solder paste (SP) during the reflow soldering process and to emphasise the component design relevance.FindingsIt was found that the reduction of SP volume only reduces the failure rate but does not solve the problem. Results show that excessive component placement pressure could induce solder beading. Statistical analysis revealed that differences between distinct components had the highest effect on the solder beading rate. Design aspects of solder beading-prone components were identified and discussed as the primary source of the problem.Practical implicationsThe findings can be applied in surface-mount technology production, where the total failure count and resulting failure costs could be reduced according to the findings.Originality/valueThis paper shows that component design aspects such as the low distance between the underside of the component and the PCB and blocked proper outgassing of volatile compounds of the SP can be root causes of solder beading under surface-mounted electrolytic capacitors.

Power Line-Guided Automatic Electric Transmission Line Inspection System

The existing unmanned aerial vehicle (UAV)-based electric transmission line inspection systems generally adopt manual control and follow the predefined path, which reduces the efficiency and makes a high inspection cost. In this article, a UAV system with advanced embedded processors and binocular visual sensors is developed to generate guidance information from power lines in real-time and achieve automatic transmission line inspection. To realize 3-D autonomous perception of power lines, we first propose an end-to-end convolutional neural network (CNN) to extract complementary information from multilevel features and detect power lines with different pixel widths and orientations. Specifically, multilevel feature aggregation module fuses multilevel features within the same stage by learning the weight vector related to the content. The joint attention (JA) module is proposed to extract rich semantic information and suppress the background noises. Meanwhile, multistage detection results are fused to enhance the robustness of the proposed network. Subsequently, power lines are grouped according to the morphological characteristics of thinning detection results, and 3-D point sets of power lines are constructed based on the epipolar constraint of binocular images. Finally, the target point of current stereo images is generated by projecting 3-D power line points to the horizontal and vertical planes. The few-waypoint trajectory is generated based on continuous target points, and automatic inspection is finished with the proposed real-time motion planning strategy. Experimental results on four datasets show that the proposed power line detection method outperforms other state-of-the-art methods. The developed UAV platform and the proposed autonomous inspection strategy are evaluated in practical environments to validate the robustness and effectiveness.

A System Deployment Model of Multi-CCD Automatic Optical Inspection for Economical Operations

Overkill and leakage are common problems in automated optical inspection (AOI) systems that have harmed firms to devote in intensive manual reinspection and seek the best CCD setting, resulting in more costly and less effective AOI operations. This study proposed a two-stage AOI based inspection system deployment model of multi-charge coupled device (CCD) for cost reduction; that is, the strictness decision model of a single CCD in the operational stage and switch on/off decision model of a set of CCDs in the strategic stage. The strictness decision model identifies the best strictness level of individual CCD by analyzing a confusion matrix according to the true defect rate of products. The multi-CCD switch decision model suggests the best switch on/off decision of multiple CCDs. Experiments in an electrical connector manufacturing plant revealed that the total inspection cost was the lowest when the strictness level was set close to the true defect rate. The best multi-CCD on/off strategy was more cost-effective than was the all CCDs-on mode under various strictness settings, by cost reduction up to 23.49%. In general, the proposed two-stage model achieves flexible multi-CCD settings of AOI systems and operations at a low cost. The proposed model can be extended to different applications of overkill and leakage problems. In this study, the proposed VGG-like convent five-layer convolution model learns from the experience of quality re-inspection personnel, which can be applied to the re-inspection line to identify AOI as defective images for re-inspection. The best accuracy reaches 99.21%.

A Practical Micro Fringe Projection Profilometry for 3-D Automated Optical Inspection

As an important defect detection technology, automated Optical Inspection (AOI) is widely used in the quality control of Printed Circuit Board Assembly (PCBA) and precision electronic manufacturing. To meet the requirement of 3D AOI with large measurable volume, high speed and high precision, a practical structured light imaging system based on the micro fringe projection profilometry is proposed. To be compatible with the traditional 2D AOI system, an optical configuration with an axial bi-telecentric lens camera and a lateral Scheimpflug projector is adopted, which helps to achieve a large Depth of Field (DOF). Adapting to the constraint of limited space for calibration target movement, a simplified and precise telecentric camera calibration method is proposed, which requires no auxiliary device like the micro-positioning stage. Then, an improved Bundle-Adjustment method is introduced to globally optimize the calibration parameters. To accelerate the 3D reconstruction, we further propose a ray backtracking algorithm after the corresponding point matching by using a modified telecentric camera model. It is demonstrated in experiments using real PCBA and micro-structure components that the system DOF is 8 mm with a Field of View of 32 mm × 28 mm. The reconstruction time is shortened to 40% of the traditional method.

A Systematic Review of the Benefits of Automation Inspection Tools for Quality Housing Delivery

Efficient and effective inspection is vital for the quality delivery of housing construction. Houses are being inspected less frequently due to incapacitated inspectorates, high cost, and the long duration of the current inspection process. Furthermore, traditional inspection processes often contribute to poor quality housing delivery are inspector dependent and complex and unsafe working environment is exposed to inspectors. Automated inspection technologies play a vital role in the inspection of housing construction. Automation-assisted technologies such as laser scanners, drones and Augmented Reality (AR)-based inspection equipped with multiple imaging and sensing systems have been developed to mitigate some of these issues with the traditional method of inspection processes. This paper reviews relevant peer-reviewed articles to explore automation inspection process tools and technologies and highlight their benefits in the housing construction process. Following the systematic literature assessment methodology, five (5) databases were queried, based on the specific search string. Specifically, 26 journal articles satisfying a set of inclusion criteria were reviewed, its results highlighting the benefits of adopting an automated inspection process for quality housing delivery. The review of the journal articles revealed that the automation inspection process is available with several benefits demonstrating the potential to improve the quality housing delivery with the aid of tools and technologies like Augmented Reality (AR)-based inspection, 3D laser scanning, Drones, and BIM-based inspection. Benefits such as time-saving, limited human intervention during the construction process, inspection accuracy, reduced resource requirements, and improved collaboration between stakeholders. This study also revealed that while new technologies are evolving with benefits to improve the inspection process, there is still a gap in the practical application of these automated inspection process technologies during housing construction. The outcome of this study would benefit both the housing owners (clients), building inspection entities, building construction researchers, and the industry professionals to realise the potential of the automation inspection process and understand the requirements and benefits for their successful implementation.

Development of tethered 2 wheeled robot aimed at automation of slope inspection

In this research, we develop a two-wheeled wire traction vehicle to support the automation of slope inspection. By using the information from the tension sensor and the acceleration sensor, we have shown that the vehicle can move on the slope. Then we have shown methods that the vehicle overcome the slope with steps, and step over the steps on slope with a height of 200mm. In addition, we propose what type of input needs to further automate the system and how to get input. Then we also propose how to enable it to move in a two-dimensional plane field.

PCBNet: A Lightweight Convolutional Neural Network for Defect Inspection in Surface Mount Technology

Prereflow automatic optical inspection (AOI) has been widely used to ensure product quality in surface mount technology (SMT). When confronted with a complex industrial environment, traditional hand-designed visual inspection algorithms may lack robustness and generalizability. In this article, PCBNet, a convolutional neural network (CNN) method that combines data preprocessing, detection network, and visualization, is proposed to localize electronic components and recognize defects. In the data preprocessing stage, raw images are segmented into several regions of interest (ROIs). The ROI patches are inspected by a CNN-based detection system, which is capable of classifying defects and positioning components. After inspection, the reporting system visualizes the results via the human–computer interface. In comparative studies, the effectiveness of the proposed PCBNet was validated on a large-scale PCB component defect dataset. The PCBNet backbone outperforms other well-known lightweight CNN backbones in terms of accuracy and latency on <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$4\times $ </tex-math></inline-formula> ARM Cortex A72 CPU @ 1.5 GHz. Compared to other learning-based methods on the small-scale benchmark dataset, the PCBNet also achieves the best balance between inference speed and accuracy. In addition, extensive experiments demonstrate the superior efficiency of PCBNet in comparison to some famous traditional object detectors and novel oriented object detection algorithms.

Error Calibration Method Based on Perspective Mapping for Wafer Automatic Optical Inspection System

In the manufacturing process of the wafer, the positioning accuracy of the wafer automatic optical inspection (AOI) system affects the detection of die surface defect directly. Most existing error compensation methods generally analyze specific error or main sources of error and can improve the positioning accuracy in most of the applications. However, to fulfill the requirement of higher positioning accuracy of the wafer AOI system, in this article, we propose an error calibration method based on perspective mapping (ECM-PM), which only requires to focus on the total error of the system, regardless of the multiple error sources of the system. First, the error cause of the wafer AOI system is analyzed and the total error of the system is measured using the designed high-precision glass checkerboard calibration board. Then, the mapping model between motor coordinate system and checkerboard coordinate system is established. In addition, the total error of the system is calibrated based on the perspective mapping principle. Finally, the experimental results show that the proposed method obviously decreased the total error of the system and it is robust to the parameter of different recipe motor coordinates.

Application of Machine Learning for Automatic Image Analysis Inspection Complexes

Strategy for the development of the customs service until 2030 provides for the development and implementation of a model of an intelligent checkpoint across the state border. The expected results of the introduction of the new model are the reduction of the time of control measures at checkpoints and the creation of conditions for non-stop traffic when moving goods while simultaneously providing the provided control functions in automatic mode. One of the most difficult tasks to be solved when creating an intelligent checkpoint is the task of automatic X-ray inspection using inspection and inspection complexes (IDCs) of a new (portal) type that allow receiving X-rays in streaming mode. Taking into account the current level of development of science and technology in the field of computer vision systems, the most effective methods of solving the problem of automatic analysis of IDC images and creating an appropriate service that allows increasing the speed and objectivity of customs control are machine learning methods. The article shows that the most promising area of research in the field of creating automatic image recognition systems for IDCs is the study and application of neural networks implementing deep learning algorithms. It is also proved that among the well-known architectures of neural networks with deep learning, convolutional neural networks show the highest quality results in image processing.

A deep learning-based approach to extraction of filler morphology in SEM images with the application of automated quality inspection

Abstract Automatic extraction of filler morphology (size, orientation, and spatial distribution) in Scanning Electron Microscopic (SEM) images is essential in many applications such as automatic quality inspection in composite manufacturing. Extraction of filler morphology greatly depends on accurate segmentation of fillers (fibers and particles), which is a challenging task due to the overlap of fibers and particles and their obscure presence in SEM images. Convolution Neural Networks (CNNs) have been shown to be very effective at object recognition in digital images. This paper proposes an automatic filler detection system in SEM images, utilizing a Mask Region-based CNN architecture. The proposed system can simultaneously classify, detect, and segment fillers in SEM images, making it suitable for morphology analysis of fillers and automatic quality inspection. We also propose a novel SEM image simulation procedure to overcome the data scarcity for training a deep CNN architecture. The proposed filler detection system is trained on the simulated images. It is shown that the trained network can detect and segment fillers with higher accuracy even in the overlapping and obscure situations. The performance and robustness of the proposed system are evaluated using both simulated and real microscopic images.

Exploring quality inspection and grade judgment of distortion defects in the fabrication of spectacle lenses

This study explores the quality control system featuring visual inspection and grade judgment for detecting distortion defects in spectacle lens fabrication. Spectacle lenses must be precisely curved to help accommodate nearsightedness and farsightedness. The curved shape allows the lens to have different curvatures in different areas during grinding. The spectacle lens will be prone to optical distortion when the curvature changes abnormally. Accordingly, this study proposes an automatic distortion flaw inspection system for spectacle lenses to substitute professional inspectors who rely on empirical judgment. We first apply the digital imaging of a concentric circle pattern through a testing lens to create an image of that lens. Second, the centroid–radii model is employed to stand for the shape property of each concentric circle in the image. Third, by finding the deviations of the centroid radii for detecting distortion flaws through a small variation control method, we obtain a different image showing the detected distortion regions. Four, based on the distortion amounts and locations, we establish the fuzzy membership functions and inference rulesets to measure distortion severity. Finally, the GA-ANFIS model is applied to determine the quality levels of distortion severity for the detected distortion flaws. Trial outcomes reveal that the proposed automatic inspection system can help practitioners in spectacle lens fabrication, for it attains a high 94% correct classification rate of quality grades in distortion severity, 81.09% distortion flaw detection rate, and 10.94% fake alert rate, in distortion inspection of spectacle lenses.

A Ubiquitous Service-Oriented Automatic Optical Inspection Platform for Textile Industry

Within a highly competitive market context, quality standards are vital for the textile industry, in which related procedures to assess respective manufacture still mainly rely on human-based visual inspection. Thereby, factors such as ergonomics, analytical subjectivity, tiredness and error susceptibility affect the employee’s performance and comfort in particular and impact the economic healthiness of each company operating in this industry, generally. In this paper, a defect detection-oriented platform for quality control in the textile industry is proposed to tackle these issues and respective impacts, combining computer vision, deep learning, geolocation and communication technologies. The system under development can integrate and improve the production ecosystem of a textile company through a properly adapted information technology setup and associated functionalities such as automatic defect detection and classification, real-time monitoring of operators, among others.

Automatic Vision-Based Online Inspection System for Broken-Filament of Carbon Fiber With Multiscale Feature Learning

This paper aims at solving the problem of broken-filament online detection and tracking during the process of carbon fiber production. Owing to the complex background and unique broken-filament shape, it is challenging to achieve the broken-filament online detection with high accuracy via classical machine vision methods, even general CNN-based methods. Moreover, the carbon fiber strands are usually merged during the winding process, which would lead to broken-filament location and tracking errors due to wrong segmentation and numbering of carbon fiber strands. To address these problems, we propose a vision-based method to achieve broken-filament online detection and tracking. At first, an image collection module is designed to capture high resolution carbon fiber strand data. Then, a novel Broken-filament Detection Network (BFDNet) is proposed to detect broken-filaments, including a feature learning part and a new anchor generation scheme, which is implemented based on the RetinaNet framework. Especially, the feature learning part contains several Multi-scale Kernel Fusion Blocks (MKFBs), which are composed of convolution kernels of different sizes. Finally, a pixel projection method is proposed to segment and number carbon fiber strands for tracking. Our method achieves satisfactory performance for broken-filament online detection in terms of accuracy when compared with several state-of-the-art methods designed for feature learning based on the classical object detection framework. Moreover, our method has been applied in practical applications for broken-filament inspection tasks in factories.

Practical Application of Automatic Rebar Arrangement Inspection System in the Civil Engineering and Architectural Sector

Practical Application of Automatic Rebar Arrangement Inspection System in the Civil Engineering and Architectural Sector

Performance comparison of various techniques for automatic licence plate recognition systems

Automatic licence plate recognition (ALPR) system is direly needed nowadays for various applications like toll collection system, parking system, identification of stolen cars, incident management, electronic payment service, electronic customs clearance of commercial vehicle, automatic security roadside inspection, security monitoring in a car, emergency notification, and personal security, etc. An automatic licence plate recognition system performs three important processing steps on the input image, i.e., extraction, segmentation, and recognition. A number of algorithms are developed for these steps in the last few years. The result of which is significant improvement in the licence plate recognition. The aim of this study is a survey of the existing techniques for licence plate recognition. In this paper, a number of existing techniques for automatic licence plate recognition are presented and their benefits and limitations are discussed. Further, the paper also foresees the future scope in the area of automatic licence plate recognition system.

Insulator Semantic Segmentation in Aerial Images Based on Multiscale Feature Fusion

As one of the important components in the transmission line, the insulator is related to the safe and reliable operation of the entire transmission line. Aerial images are characterized by complex backgrounds, multiple pseudotargets, and low signal‐to‐noise ratios. Rapid and accurate localization of insulators in aerial images is a critical and challenging task in automatic inspection of transmission lines. Most insulator localization methods suffer from the loss of target edge detail information and large amount of model parameters. To solve these problems, this paper adopts an Encoder‐Decoder architecture, called ED‐Net, to realize end‐to‐end intelligent and accurate identification of insulators in aerial images. Firstly, Initial Module and CA‐Bottleneck which are used to extract features from images to generate finer feature maps are proposed in the Encoder path. Meanwhile, global average pooling is used to preserve the maximum receptive field. Secondly, in the Decoder path, Refinement Boundary Module and Asymmetric Convolution Module are given to perform boundary optimization on the feature map, which are generated by the Encoder path. Finally, the Attention Feature Fusion Module is introduced into the Decoder path to combine high‐level features with low‐level features better and reduce the gap between features of different levels. The proposed model architecture keeps a suitable balance between the model parameters and insulator segmentation performance on insulator test datasets. Specifically, for a 512 × 512 input image, 95.12% mean intersection over union is achieved on the insulator test datasets with different environments and model parameters size being only 13.61 M. Compared with the current state‐of‐the‐art semantic segmentation methods, the results show that the proposed method has higher efficient and accuracy.

A New Multilabel Recognition Framework for Transmission Lines Bolt Defects Based on the Combination of Semantic Knowledge and Structural Knowledge

Automatic inspection of transmission lines has received extensive attention in recent years. Bolts are widely used as fasteners in transmission lines, and their defect images have the characteristics of large intra-class differences and small inter-class differences. In view of this, we proposed a multilabel image recognition framework for bolt defects (RFBD). The framework consists of a visual feature and semantic knowledge network (VFSKnet) and a visual feature and position knowledge network (VFPKnet). To learn the relationship between bolt labels, the VFSKnet utilizes the relation between bolt defect labels as professional posterior knowledge to guide the model. To capture the structured fine-grained features, the VFPKnet extracts and utilizes the significant structural features of bolts. Finally, these two sub-networks, VFSKnet and VFPKnet, are combined into a framework after weighting, i.e. RFBD, for the final recognition. By using the proposed RFBD, the label-level accuracy reaches 93.91%, and the image-level accuracy reaches 83.29%. Experimental results well demonstrate the superiority of the proposed model for bolt defect recognition.

Artificial vision system for the automatic inspection of preforms

The preforming consists of processing the reinforcement to obtain a geometry of the dry fiber, close to that of the final product before being impregnated by the resin during the injection process. During the process, the fibers are manipulated to reach the desired shape are subjected to tensile, shear and torsion stresees that can cause changes in the orientation of the fibers, misalignments,or other defects such as wrinkles or fiber breakage that can affect the performance of the preform . In this work a solution for the automation of the quality control of the preforming process by artificial vision is investigated.. Two approaches are proposed, 3D vision for the geometric and superficial inspection of the fibers and machine learning aproach based on Deep Learning (DL) to detect irregularities in the orientation. The solution based on 3D vision automatically detects defects based on the comparison of a theoretical 3D model and a 3D reconstruction of the real part. A structured light system is used to generate dense and precise point clouds. Once aligned, the dissimilarities between both surfaces are analyzed. The solution is complemented by a 2D vision system based on DL that classifies the irregularities in the orientations of the fabric. The model is trained with images of classified fiber orientations to automatically identify areas of fiber whose orientation does not correspond to the expected one. The combination of both technologies allows to give a complete solution to the automated quality inspection of preforms for manufacturing or defects.

Automatic Inspection of Green Concrete Quality Using Machine Learning and Cobot

Automatic Inspection of Green Concrete Quality Using Machine Learning and Cobot

Analyse the surface quality in the milling process by soft computing approaches

In recent years manufacturing industries move towards the automatic inspection process for achieving higher efficiency and maximum profit. These papers proposed the methodology of analysing the surface roughness in the milling process through soft computing approaches. The Adaptive Neuro-Fuzzy inference system (ANFIS) model was developed with the input parameters (Spindle Speed, Depth of Cut, Feed Rate) and output parameters (Surface Roughness). The surface roughness value is measured by the traditional stylus probe method,which values consider a reference value for the training process. Finally, the surface roughness output which is produced by the ANFIS algorithm was compared with the reference value for calculating the accuracy range. The outcome of the accuracy level is above 97% by using ANFIS model.