PCB Defect Detection Based on Deep Learning Algorithm

Automatic optical inspection (AOI) of micro drill bit becomes more and more important with the rapid expanding of printed circuit board (PCB) manufacturing industry. Distinguished from most traditional manual inspection approach, AOI is time-saving, objective and non contact. In this work, a pattern classification method is proposed for the AOI of micro drill bit in PCB manufacturing, in which three features of drill bit blade are extracted for classification. In order to be independent on the clamp that can guarantee the exact position of drill bit blade for photography, and reduce the cost of the AOI system, an image registration method is used to align the drill bit blade, which can also make the feature extraction much easier. The evaluation result indicates that the approach works well for the AOI of micro drill bit. It is real time, more detailed result providing and low requirement on photographic device.

PurposeTo present and discuss open trace defects uncovered in an FR4 assembly during electrical testing.Design/methodology/approachThis paper presents open trace defects observed in FR4 assemblies and analyses the distribution of defects. The paper also discusses possible root causes for their occurrence.FindingsThe open trace defects that occurred during printed circuit board (PCB) fabrication should have been observed by the board manufacturer. It appears that the PCB manufacturer did not perform automatic optical inspection (AOI) and electrical testing during the manufacturing of the boards. The cost due to the rejected PCBAs was approximately 3x times that of the PCB cost.Originality/valueThe paper highlights the costly impact of uncovering a PCB defect after assembly. Based on the results of this study, the implementation of electrical testing and AOI for PCBs is recommended.

In computer vision, shape recovery is a classic problem. The shape from shading problem aims to reconstruct a 3D shape from one or more intensity images. Inspection of solder joint is a critical step in the assembly of PCB (Printed Circuit Board). So, non-destructive inspection technology has been widely used in a production of PCB. In automated optical inspection (AOI) field 2D inspection appears to be more prevalent industry-wide than 3D inspection, but the limit of 2D inspection in some defects is apparent. This paper deals with the reconstruction of the solder joint's surface in PCB based on shape form shading technology. The advantages of SFS method are analyzed firstly. Then, theory and survey of SFS method is introduced. To overcome the disadvantages existing in conventional SFS methods, some improved algorithms are provided and proved by experiments. Experimental results reveal that the proposed method shows practical value in solder joint inspection.

Automated Optical Inspection (AOI) Systems are commonly used on Printed Circuit Boards (PCB) manufacturing. The use of this technology has been proven as highly efficient for process improvements and quality achievements. The correct extraction of the component for posterior analysis is a critical step of the AOI process. Nowadays, the Pattern Matching Algorithm is commonly used, although this algorithm requires extensive calculations and is time consuming. This paper will present an improved algorithm for the component localization process, with the capability of implementation in a parallel execution system.

The objective of this study is to investigate the environmental impacts of a printed circuit board (PCB) manufacturing plant through streamlined life cycle assessment approach. As a result, the most effective recommendations on minimizing the environmental impacts for the mentioned sector are revealed and first steps towards establishing a country specific database are taken. The whole PCB production consists of two consecutive stages: namely board fabrication followed by the manufacturing of PCB. Manufacturing of PCB contributes the highest shares to freshwater aquatic ecotoxicity potential (FAETP) and ozone layer depletion potential (ODP). Eighty-nine percent of FAETP is found to be generated from the manufacturing of PCB. Almost all of this contribution can be attributed to the disposal of copper containing wastewater treatment sludge from etching operations to incineration. On the other hand, PCB manufacturing has 73% share in total ODP. Within the manufacturing of PCB, as etching operations are found to be of importance for all the impact categories except eutrophication potential (EP), it is recommended to focus further studies on in-plant control of etching.

The research object in the work is the printed circuit boards (PCB) Production technological process using the additive technology of photopolymer 3D printing. The existing problem is that the manufacturing process of single-sided and double-sided PCBs, simple in technology, from the third to the fifth accuracy class, requires the use of a large amount of consumables and technological equipment. In turn, this affects the cost of the product. The research subject is models and methods for manufacturing PCB using photopolymer 3D printing. In order to reduce the cost of materials: film or aerosol photoresist, as well as reduce the number of technological operations, applying photoresist and for the manufacture of PCBs stencils, it is proposed to use photopolymer 3D printing technologies for the manufacture of PCBs. The paper analyzes the costs of Plexiwire Resin Basic Orange Transparen photopolymer resin for the manufacture of single-sided PCBs and calculates the cost of the consumable (resin) compared to the costs of dry film photoresist. 60 % cost of consumables (photopolymer resin) compared to dry film photoresist for making single-sided PCBs. The work is aimed at determining the dependence of the geometric dimensions of the PСВs topology and the consumption of photopolymer resin on the technological parameters of photopolymer exposure. A regression correlation model of the dependence of resin consumption on exposure parameters has been developed and correlation coefficients have been calculated. It has been established that with an increase in the exposure time of the photopolymer resin, the consumption of the photopolymer resin increases and the deviation of the geometric dimensions of the PCBs topology increases, which in turn negatively affects the quality of the product. Therefore, using the obtained regression model, it is possible to calculate the influence of parameters on the PCB topology and reduce the deviation of conductor sizes and resin consumption.

Defect inspection is essential in the semiconductor industry to fabricate printed circuit boards (PCBs) with minimum defect rates. However, conventional inspection systems are labor-intensive and time-consuming. In this study, a semi-supervised learning (SSL)-based model called PCB_SS was developed. It was trained using labeled and unlabeled images under two different augmentations. Training and test PCB images were acquired using automatic final vision inspection systems. The PCB_SS model outperformed a completely supervised model trained using only labeled images (PCB_FS). The performance of the PCB_SS model was more robust than that of the PCB_FS model when the number of labeled data is limited or comprises incorrectly labeled data. In an error-resilience test, the proposed PCB_SS model maintained stable accuracy (error increment of less than 0.5%, compared with 4% for PCB_FS) for noisy training data (with as much as 9.0% of the data labeled incorrectly). The proposed model also showed superior performance when comparing machine-learning and deep-learning classifiers. The unlabeled data utilized in the PCB_SS model helped with the generalization of the deep-learning model and improved its performance for PCB defect detection. Thus, the proposed method alleviates the burden of the manual labeling process and provides a rapid and accurate automatic classifier for PCB inspections.

The process of manufacturing printed circuit boards and printed circuit board assemblies is very complex. There are numerous process variables with all levels of interactions. These interactions can be difficult to understand and control within a printed circuit board manufacturing facility or printed circuit assembly manufacturing facility. When the interactions span facilities and companies, it takes understanding and controls to prevent latent defects from occurring downstream. What happens when a defect appears that is new, unique and different enough from the typical defect that it is not readily apparent what caused the defect and whether it was caused during the printed circuit board manufacturing process, during the assembly process or, in fact, by an interaction between the two processes? A unique plated-through-hole solder void which did not meet IPC Class II printed circuit board Workmanship requirements as per IPC A610, Acceptability of Electronic Assemblies, occurred on a large number of assemblies.1 There are several questions which immediately arise: What caused the defect? Is the product acceptable for customer shipment? Can the defective product be reworked? Is this a seasonal defect (e.g. laminate voids caused by high levels of moisture in the laminate) or has a variable in the process shifted? A team of engineers from multiple companies worked together to answer these questions.

A popular soldering technique for printed circuit boards (PCB) is the so-called surface-mounted technology. After the soldering process an automated optical inspection (AOI) is the common method determining whether a PCB shall go to a manual inspection and rework station (MIS) or can directly go further to the next process step. Thereby, the AOI is a vision-based system deriving user defined physical measurements from a camera image. Based on these pre-defined measurements associated with static specification limits, the AOI labels each inspected soldering spot on a PCB as non-defect or defect. However, a large majority of PCBs are wrongly labelled defect, so-called false calls, causing a major manual labour effort at the MIS.This dataset contains a 132-days recording of PCBs going through the MIS labelled as true defect or false call with the physical measurement by the AOI. Furthermore, the dataset may contain various distribution drifts of unknown type that can be explained by the high sensitivity of electronic production to small external factors that may change unrecognized and additionally the dataset has an unknown percentage of label error due the human labelling process.

Printed circuit board (PCB) defect detection is essential for ensuring the reliability of electronic manufacturing. Traditional automated optical inspection (AOI) methods rely on handcrafted features and rule-based heuristics, which often fail under complex defect patterns. Recent progress in deep learning, particularly the YOLO family of object detectors, has significantly improved industrial inspection. This paper presents a systematic benchmark of the YOLOv12 series, including five model scales (n, s, m, l, x), for PCB defect detection. All variants are trained and evaluated under unified protocols on a standard PCB dataset. Results show that YOLOv12l and YOLOv12x achieve the highest accuracy (mAP@0.5 ≈ 0.88 – 0.89), while YOLOv12n and YOLOv12s provide superior inference speed ( inference-only >300 FPS, end-to-end 6–8 FPS) at the expense of precision. YOLOv12m emerges as the most balanced variant, offering ~0.92 mAP@0.5 with real-time throughput. Error analysis using precision – recall curves and confusion matrices highlights challenges in fine-grained categories such as spur and mouse_bite. These findings provide practical guidelines for selecting YOLOv12 variants in PCB inspection, balancing accuracy and efficiency for diverse deployment scenarios.

This paper presents the development of an automated component detection system for quality control in Printed Circuit Boards (PCBs) by integrating the YOLO object detection algorithm with Internet of Things (IoT) real-time streaming on a Raspberry Pi platform. The proposed system aims to address the challenges associated with traditional manual inspection methods, including time inefficiency, human error, and limited accuracy in detecting faulty components. The YOLO model, renowned for its high-speed and accurate object detection capabilities, was trained to identify various PCB components and deployed on a Raspberry Pi due to its affordability, portability, and low power consumption. To enable real-time remote monitoring and analysis, IoT capabilities were incorporated using the MQTT protocol, allowing seamless data transmission to remote servers or devices. The experimental results demonstrated the effectiveness of the proposed system, achiev-ing an average detection accuracy of 95%, making it a reliable solution for real-time quality assurance in PCB manufacturing. The novelty of this study lies in the innovative integration of the YOLO algorithm with IoT technology on a cost-efficient platform, providing a scalable and practical solution for automating PCB inspection processes. This approach not only enhances inspection efficiency but also reduces operational costs, offering significant value to the electronics manufacturing industry. Future work will focus on scaling thesystem for broader applications and improving the detection capabilities for more complex PCB designs.

The conventional PCB (Printed Circuit Board) DIP (Dual Inline Package) process solder defect detection was done by labor inspection, which is not only time-intensive but also labor-intensive. This paper proposes a deep ensemble method to inspect the PCB solder defects to replace the labor inspection. To achieve a high detection rate and a low false alarm rate, two distinct detection models, a hybrid YOLOv2 (YOLOv2 as a foreground detector and ResNet-101 as a classifier) and Faster RCNN with ResNet-101 and FPN are separately trained to obtain a high detection rate result. The final ensemble model aggregates the result from the two detection models. That achieves a 96.73% detection rate and a 19.73% false alarm rate in real tests. The detection time is less than 15 seconds for inferencing a PCB image with a resolution of 7296*6000. The proposed method has been proven efficient in terms of guiding operators to identify and fix PCB solder defects [1] and thus is able to reduce 33% of labor demand for each PCB production line at our real test site. [1].

Ultrasonic recovery of copper and iron through the simultaneous utilization of Printed Circuit Boards (PCB) spent acid etching solution and PCB waste sludge

With the advancement of Industry 4.0, the need to integrate intelligent technologies into production processes has grown, aiming for greater automation, efficiency, and quality control. Aligned with this context, this project developed a supervisory system for solder quality inspection on printed circuit boards (PCBs) in the surface-mount technology (SMT) process, using artificial intelligence (AI). Currently, inspections performed by AOI (Automated Optical Inspection) machines generate data in multiple formats (HTML, TXT, and PDF), but their collection and analysis are manual. This makes the process slow, error-prone, and poorly integrated, hindering real-time decision-making. To overcome these limitations, an automated system was developed, including a RESTful API for module integration, a relational database for efficient data storage, a graphical interface with dashboards, and AI models for predictive analysis. The AI, based on Convolutional Neural Networks using Keras and TensorFlow, enables precise detection of solder defects, reducing the need for human intervention. The project followed a hybrid methodology, combining Scrum for agile software development and the Waterfall model for the sequential stages of hardware and research. The team was divided into hardware and software groups, with defined tasks for each phase of the schedule. The main phases included planning, SMT process mapping, system module development and integration, functional and performance testing, and user validation. The system was delivered validated, with formal acceptance from the client. The result is an intelligent solution that automates inspection in the SMT process, increases reliability, reduces failures, and promotes digital transformation in line with the principles of Industry 4.0.

Automatic Optical Inspection (AOI) is any method of detecting defects during a Printed Circuit Board (PCB) manufacturing process. Early AOI methods were based on classic image processing algorithms using a reference PCB. The traditional methods require very complex and inflexible preprocessing stages. With recent advances in the field of deep learning, especially Convolutional Neural Networks (CNN), automating various computer vision tasks has been established. Limited research has been carried out in the past on using CNN for AOI. The present systems are inflexible and require a lot of preprocessing steps or a complex illumination system to improve the accuracy. This paper studies the effectiveness of using CNN to detect soldering bridge faults in a PCB assembly. The paper presents a method for designing an optimized CNN architecture to detect soldering faults in a PCBA. The proposed CNN architecture is compared with the state-of-the-art object detection architecture, namely YOLO, with respect to detection accuracy, processing time, and memory requirement. The results of our experiments show that the proposed CNN architecture has a 3.0% better average precision, has 50% less number of parameters and infers in half the time as YOLO. The experimental results prove the effectiveness of using CNN in AOI by using images of a PCB assembly without any reference image, any complex preprocessing stage, or a complex illumination system. Doi: 10.28991/HIJ-2022-03-01-01 Full Text: PDF