PCB Inspection Research Articles

Parameter Identification and Refinement for Parallel PCB Inspection in Cyber–Physical–Social Systems

Parameter Identification and Refinement for Parallel PCB Inspection in Cyber–Physical–Social Systems

Shape-from-focus reconstruction using block processing followed by local heat-diffusion-based refinement

Shape from focus (SFF) is a method of recovering the three-dimensional shape of objects from the image sequence through various focusing measurement operators, and is widely used in the fields of medical diagnosis, PCB inspection, industrial manufacturing, and robotic operations. In SFF, the wrong focus measurement causes an inaccurate reconstruction of the object. Generally, to improve the accuracy of focusing measurements, many focus measure (FM) operators are proposed, which is a method that improves the focus volume (FV) performance. However, due to the influence of blur diffusion, which refers to the overlapping of blur circles between different regions, the calculation results of the FM operator in the local window often do not meet the stability requirements of complex scenarios. It is difficult to provide high-precision reconstruction results in practical applications. To overcome this limitation, we proposed an SFF framework based on block processing and heat-diffusion refinement to obtain a refined depth map (RDM). The acquisition of an RDM is mainly divided into two steps. First, the image is divided into blocks to reduce the effect of blur diffusion, and the FM operator is used to calculate the focus measurement value of each block to form the FV. The initial depth map (IDM) is obtained by searching for the best focus position in the FV. The second step is to refine the IDM based on the heat-diffusion principle to obtain the best focus position for all pixels in each block and derive the RDM. The results of experiments conducted on synthetic and real objects demonstrate the superiority of our method in terms of accuracy and its high stability in different application scenarios.

Conditional TransGAN-Based Data Augmentation for PCB Electronic Component Inspection.

Automatic recognition and positioning of electronic components on PCBs can enhance quality inspection efficiency for electronic products during manufacturing. Efficient PCB inspection requires identification and classification of PCB components as well as defects for better quality assurance. The small size of the electronic component and PCB defect targets means that there are fewer feature areas for the neural network to detect, and the complex grain backgrounds of both datasets can cause significant interference, making the target detection task challenging. Meanwhile, the detection performance of deep learning models is significantly impacted due to the lack of samples. In this paper, we propose conditional TransGAN (cTransGAN), a generative model for data augmentation, which enhances the quantity and diversity of the original training set and further improves the accuracy of PCB electronic component recognition. The design of cTransGAN brings together the merits of both conditional GAN and TransGAN, allowing a trained model to generate high-quality synthetic images conditioned on the class embeddings. To validate the proposed method, we conduct extensive experiments on two datasets, including a self-developed dataset for PCB component detection and an existing dataset for PCB defect detection. Also, we have evaluated three existing object detection algorithms, including Faster R-CNN ResNet101, YOLO V3 DarkNet-53, and SCNet ResNet101, and each is validated under four experimental settings to form an ablation study. Results demonstrate that the proposed cTransGAN can effectively enhance the quality and diversity of the training set, leading to superior performance on both tasks. We have open-sourced the project to facilitate further studies.

Current Status and Issues of PCB Inspection as Deciphered from Factual Survey

Current Status and Issues of PCB Inspection as Deciphered from Factual Survey

준 지도 학습 ADDA 신경망을 활용한 PCB 불량검출

준 지도 학습 ADDA 신경망을 활용한 PCB 불량검출

Bare PCB inspection for Track cut, Track Short and Pad Damage using simple Image Processing Operations

In this paper most commonly occurring Bare PCB defects such as Track Cut, Track short and Pad Damages are detected by Image processing techniques. Reference PCB without having any defects is compared with test PCB having defects to identify the defects and x-y coordinates of the center of the defects along with radii are obtained using Difference of Gaussian method and location of the individual type of defects are marked either by similar color or different colors. Result Analysis includes time taken for the inspection of a single defect, multiple similar defects, and multiple different defects. Time taken is ranging from 1.674 to 1.714 seconds if the individual type of defects are marked by different colors and 0.670 to 0.709 seconds if all the identified defects are marked by the same colors.

Automated PCB Inspection System

Development of an automated PCB inspection system as per the need of industry is a challenging task. In this paper a case study is presented, to exhibit, a proposed system for an immigration process of a manual PCB inspection system to an automated PCB inspection system, with a minimal intervention on the existing production flow, for a leading automotive manufacturing company. A detailed design of the system, based on computer vision followed by testing and analysis was proposed, in order to aid the manufacturer in the process of automation.

Coarse Resolution Defect Localization Algorithm for an Automated Visual PCB Inspection

Satu daripada asas utama dalam industri pembuatan elektronik ialah pembuatan papan litar bercetak (PCB). Pembuatan PCB pada masa kini perlu melalui proses kikisan. Ini adalah proses satu hala. Proses cetakan yang dilakukan sebelum proses kikisan adalah penyebab utama kepada kecacatan pada PCB. Setelah PCB dikikis, kecacatan itu, jika ada menyebabkan PCB menjadi tidak berguna lagi. Disebabkan oleh keletihan dan keperluan kecepatan, pemeriksaan secara manual tidak efektif dilakukan untuk memeriksa setiap PCB. Oleh itu, pengilang memerlukan sebuah sistem automatik untuk mengesan kecacatan secara masa nyata yang mungkin berlaku semasa proses percetakan. Kecacatan itu akan dikesan dengan menggunakan algoritma pembezaan imej berasaskan wavelet. Seterusnya, kertas kerja ini mencadangkan satu algoritma untuk pemeriksaan visual PCB secara automatik yang berupaya mengesan dan menyari kecacatan pada PCB. Algoritma ini dijalankan pada resolusi kasar pembezaan imej bertujuan untuk mengesan kawasan kecacatan pada resolusi halus imej PCB yang di periksa. Kata kunci: pengesanan kecacatan; resolusi kasar; wavelets; pemeriksaan PCB One of the backbones in electronic manufacturing industry is the printed circuit board (PCB) manufacturing. Current practice in PCB manufacturing requires an etching process. This process is an irreversible process. Printing process, which is done before the etching process, caused most of the destructive defects found on the PCB. Once the laminate is etched, the defects, if exist would cause the PCB laminate to become useless. Due to the fatigue and speed requirement, manual inspection is ineffective to inspect every printed laminate. Therefore, manufacturers require an automated system to detect the defects online which may occur during the printing process. The defect is detected by utilizing wavelet-based image difference algorithm. Hence, this paper proposes an algorithm for an automated visual PCB inspection that is able to automatically locate and extract any defect on a PCB laminate. The algorithm works on the coarse resolution differenced image in order to locate the defective area on the fine resolution tested PCB image. Key words: defect localization; coarse resolution; wavelets; PCB inspection

인쇄회로기판 검사를 위한 기하학적 영상 왜곡의 보정 방법

The geometric distortion of image is one of the most important parameters that take effect on the accuracy of optical inspection systems. We propose a new correction method of the image distortion to increase the accuracy of PCB inspection systems. The model-free method is applied to correct the randomly distorted image that cannot be represented by mathematical model. To reduce the correction time of inspection system, we newly propose a grid reduction algorithm that minimize the number of grids by the quad-tree approach. We apply the proposed method to a PCB inspection system, and verify its usefulness through experiments using actual inspection images.

Recent Patents on Integrated Software / Hardware GMR - Based Systems and Applications for PCB Inspection

In this paper, the issue of Eddy Current Non-Destructive Testing system exploiting Giant Magneto Resistive sensors is presented for inspection of Printed Circuit Board. We propose a wide view of the state-of-the-art into this interdisciplinary research field, following the chronological path of the major results achieved in recent years. Once the relevant background is depicted, some important patents concerning eddy current probe and, in general, integrated software/hardware Giant Magneto Resistive-based systems are introduced, with particular reference to some patents about crack detection in conducting materials. The advantages of the proposed models and some possible improvements are discussed. Then a final look to the possible developments is given. Keywords: Crack detection, eddy-current testing, giant magneto resistive, printed circuit board, magnetic sensors

Optical Pattern Inspection for Flex PCB — Challenges & Solution

Due to the material properties and technology advancement in printed circuit flex tapes, traditional PCB inspection algorithms using reference image cannot be used. Flex tapes are flexible circuits enabling the design and production of lighter, faster and smaller electronic products. A flex tape is made of flexible polymer film that is laminated onto a thin sheet of conductive material and etched to produce a circuit pattern. The width of fine pitch patterns can be of a few microns. Due to the material characteristics of printed circuit tapes, such as thinness and flexibility, the images captured during inspection are distorted (stretch or shrink, tilt, meandering, etc.). These anomalies and shining tape surface make the possibility of using conventional PCB inspection algorithms using referential methods for pattern inspection, difficult.The goal of pattern inspection is to identify pattern defects — open, short, nick, protrusion, island, pinholes and dust particles. Non-repetitive and non-uniform distortions are some of the main challenges in inspecting these flexible tapes. Some of the other challenges faced during the design of the defect detection algorithm are non-uniform lighting and the gamut of sizes, shapes & orientation of defects as well as features on the printed circuit. Moreover, the algorithms need to take into account the stringent defect tolerance limits followed by the industry.

Development of a comprehensive in‐line quality control system for printed circuit board assemblies

PurposeTo present an overview of the research and development carried out by an EC Framework 6 part funded consortium, known as MICROSCAN, for the implementation of an in‐line PCB inspection prototype system that is capable of offering comprehensive defect detection.Design/methodology/approachFour non‐destructive testing inspection modules based on digital radiography (X‐ray) inspection, thermal inspection, automated‐optical inspection and acoustic inspection have been integrated to form a combined inspection system.FindingsA proof in principle in‐line PCB inspection system, utilising four different inspection techniques, has been developed and demonstrated. The system is based on a generic mechanical, electrical and software communications platform culminating in a flexible system that enables the inspection modules to be used separately, together or interchanged to give the best results in terms of inspection coverage and inspection throughput.Research limitations/implicationsIn its current embodiment, the prototype is suited to inspection of high‐return PCBs, particularly those used in medical and aerospace products, rather than high‐throughput PCB production work. The X‐ray inspection module is the slowest inspection technique and combining four different inspection techniques reduces the inspection throughput of the whole system to that of the X‐ray inspection module. Further, trials and investigations need to be carried out to improve inspection throughput.Originality/valueThe novelty of the system is that it is the first time that four inspection techniques have been combined to give the capability of 100 per cent defect coverage.

Trends in automated visual inspection

Automated visual inspection (AVI) or automated optical inspection (AOI) systems offer significant advantages over human inspection from a fatigue, throughput, speed and accuracy point of view. This area has matured considerably over the last decade or so, due to advances in enabling technologies like sensors, processor hardware, software methodologies, and networking to name a few. These advances in cost, performance and design methodologies have resulted in an explosion of application areas, where AVI and AOI systems have become an integral component of quality control schemes in product inspection and certification. AVI systems represent a quantitative feedback node to identify and eliminate problems at different stages in the production process. Commercial systems The major application areas for AVI include but are not limited to: (a) Packaging: medical containers (pill strips, bottles), food cans (hole detection, shape defects, finish), chips (pad contacts), etc. (b) Electronics: semiconductor wafers, dies, chips, PCB inspection, etc. (c) Web and surface inspection: metal, textiles, paper etc. AVI systems can be further classified based on whether they detect gross defects using relatively global features or fine defects based on fine local features. Print inspection and die inspection are examples of the latter and typically require greater algorithmic support. Commercial systems can also be classified based on the level of integration. Custom systems are complete solutions for a specific industrial application available for high-volume industries like semiconductors. On the other hand, the AVI industry has always had a large number of system integrators and consultants that design systems based on off-theshelf vision processors, sensors, software and varying degrees of proprietary contributions. Commercial AVI systems have always had to operate under ‘‘hard’’ realtime conditions and harsh plant environments and have become mature and reliable over the years. Increasingly, industry trends have led to further de facto requirements: (a) systems have to be networked and accessible remotely, (b) systems have to be integrated with manufacturing software or processes and (c) systems have to interface with databases. While these trends raise the bar for any developer, they have made defect classification and statistical analysis, a real possibility. This presents an opportunity to AVI system developers to ‘‘add value’’ to the manufacturing process.

Image Distortion Compensation by Using a Polynomial Model in an X-Ray Digital Tomosynthesis System

X-ray technology has been widely used in a number of industrial applications for monitoring and inspecting inner defects which can hardly be found by normal vision systems as a ball grid array (BGA) or a flip chip array (FCA). Digital tomosynthesis (DT) is one of the most useful X-ray cross-sectional imaging methods for PCB inspection, and it usually uses an X-ray image intensifier. However, the image intensifier distorts X-ray images severely both of shape and intensity. This distortion breaks the correspondences between those images and prevents us from acquiring accurate cross-section images. Therefore, image distortion compensation is one of the most important issues in realizing a DT system. In this paper, an image distortion compensation method for an X-ray DT system is presented. It is to use a general distortion polynomial model on two dimensional plane that can cope with arbitrary, complex and various forms of distortion. Experimental results show a great improvement in compensation speed and accuracy.

Eddy-Current Testing Probe With Spin-Valve Type GMR Sensor for Printed Circuit Board Inspection

This paper proposes an eddy-current testing (ECT) probe composed of a spin-valve giant magnetoresistance (SV-GMR) sensor and a meander coil for the inspection of bare printed circuit board. The SV-GMR sensor serves as a magnetic sensor for the ECT probe to sense the variation of the magnetic field distribution occurred on the printed circuit board. The SV-GMR sensor is used specifically to detect the changing magnetic field distribution occurred at the defect point. The characteristics of the proposed probe are discussed in this paper. The comparisons of signal-to-noise ratios obtained from ECT probe with SV-GMR sensor and with solenoid coil verify that the applying of SV-GMR sensor to the ECT probe can improve the PCB inspection results.

다중 인식기 및 검증기를 갖는 거버문자 인식 시스템

인쇄회로기판 제작에 사용되는 국제표준규격의 거버 파일로부터 부품 위치 이름을 자동으로 추출하기 위한 문자인식 시스템을 제안한다. 거버 파일은 벡터형식의 그림파일로서, 각종도형 및 기호가 문자와 혼합되어 있으며, 가로쓰기와 세로쓰기 및 역 세로쓰기가 병용된다. 거버문자인식 시스템은 거버 파일에서 문자패턴을 추출하여 분리하는 전 처리 단계와 추출된 패턴을 인식하는 인식단계 및 인식된 문자와 숫자를 조합하여 부품위치이름을 구성하는 후 처리단계로 구성된다. 특히 인식률 향상을 위하여 신경회로망에 의한 다중인식기 및 구조적 특징을 이용한 검증기를 개발한다. 본 논문에서 개발된 거버문자 인식시스템은 인쇄회로기판 조립 및 검사 장비를 위한 자동 프로그래밍 시스템에 사용되어, 전자제품 제조시스템의 생산성 향상에 기여할 수 있다. We propose the character recognition system for Gerber files. The Gerber file is the vector-formatted drawing file for PCB manufacturing, which includes various symbols, figures and characters. Also, the characters are written in horizontal, vertical, and reverse-vortical directions. In this paper, we newly propose the Gerber-character recognition system to recognize all of component names located in PCB. To improve the performance, we develop the multiple recognizers by neural networks and the verifier considering the structural features. The developed system has been installed to the auto-programming software for PCB assembly and inspection machines.

GMR Sensor Utilization for PCB Inspection Based on the Eddy-Current Testing Technique

This paper proposes the utilization of a GMR sensor as a magnetic sensor of an eddy-current testing probe for the detection of defects in printed circuit boards. The proposed probe consists of a meander coil functioning as an exciting coil and a GMR sensor functioning as a magnetic sensor. The GMR sensor has the advantages of high sensitivity to low magnetic fields over a broad range of frequency and very small size, and is therefore very useful for detecting very small cracks in printed circuit boards by means of the eddy-current testing technique. This paper describes the structure of the proposed probe, the inspection principles, and the experimental results achieved with an eddy-current testing probe using a GMR sensor in comparison with one using a solenoid coil senso

A NON-REFERENTIAL MACHINE VISION APPROACH FOR BGA SUBSTRATE INSPECTION

ABSTRACT In this research, a non-referential machine vision method is proposed to detect surface defects on ball grid array (BGA) substrates. Traditional automatic visual inspection systems have used template matching for PCB inspection. They require a large amount of memory storage, and suffer from environmental changes such as alignment, process variations, lighting, etc. Since the layout of BGA substrates is generally composed of basic primitives such as line segments, circular arcs, and other elements of regular shapes, the proposed method uses the Hough transform, similarity measures and geometric constraints to eliminate all regular primitives on BGA substrates. The remaining elements on the resulting image are those that have irregular shapes, and can be easily identified as defects. With the proposed approach, no reference template is required. It provides an efficient and flexible approach for automatic BGA defect inspection. Experimental results from more than 100 BGA substrate samples have shown the efficacy of the proposed method.

Scanner technology cuts PCB inspection time to just a minute

Scanner technology cuts PCB inspection time to just a minute

Isotropic masks make efficient linear feature detectors

It is shown that isotropic masks can be used for the efficient detection of linear features in digital images. Early tests have shown useful performance when applied to the task of locating insects in grain. This work should also be valuable in other applications where line features have to be located, and also those where thin lines have to be tracked, such as document interpretation and PCB inspection.