scholarly journals Deep learning based solder joint defect detection on industrial printed circuit board X-ray images

2022 ◽  
Author(s):  
Qianru Zhang ◽  
Meng Zhang ◽  
Chinthaka Gamanayake ◽  
Chau Yuen ◽  
Zehao Geng ◽  
...  
Keyword(s):  
Quality Control ◽  
Deep Learning ◽  
Defect Detection ◽  
Printed Circuit Board ◽  
Circuit Board ◽  
Image Size ◽  
X Ray ◽  
Component Size ◽  
Image Dimension ◽  
X Ray Imaging

AbstractWith the improvement of electronic circuit production methods, such as reduction of component size and the increase of component density, the risk of defects is increasing in the production line. Many techniques have been incorporated to check for failed solder joints, such as X-ray imaging, optical imaging and thermal imaging, among which X-ray imaging can inspect external and internal defects. However, some advanced algorithms are not accurate enough to meet the requirements of quality control. A lot of manual inspection is required that increases the specialist workload. In addition, automatic X-ray inspection could produce incorrect region of interests that deteriorates the defect detection. The high-dimensionality of X-ray images and changes in image size also pose challenges to detection algorithms. Recently, the latest advances in deep learning provide inspiration for image-based tasks and are competitive with human level. In this work, deep learning is introduced in the inspection for quality control. Four joint defect detection models based on artificial intelligence are proposed and compared. The noisy ROI and the change of image dimension problems are addressed. The effectiveness of the proposed models is verified by experiments on real-world 3D X-ray dataset, which saves the specialist inspection workload greatly.

Printed Circuit Board Propagating Faults

2004 ◽  
Author(s):  
Daren T. Slee
Keyword(s):  
Printed Circuit Boards ◽  
Printed Circuit Board ◽  
Fault Tree Analysis ◽  
Circuit Board ◽  
Circuit Boards ◽  
Visual Examination ◽  
X Ray ◽  
Printed Circuit ◽  
Root Cause ◽  
X Ray Imaging

Abstract This paper is a review of propagating faults in printed circuit boards (PCBs) from the perspective of using the resulting burn and melted copper patterns to identify likely locations of fault initiation. Visual examination and x-ray imaging are the main techniques for examining PCB propagating faults. Once the likely fault initiation location has been identified, fault tree analysis can be used to determine the root cause for fault initiation. The paper discusses the mechanisms by which PCB propagating faults occur. The method of determining the likely area of initiation of the fault using visual examination of the PCB burn pattern, x-ray imaging, and the layout artwork for the PCB is discussed. The paper then goes on to discuss possible root-causes for the initiation of PCB propagating faults and some of their considerations.

scholarly journals Automatic Quality Control in Lung X-Ray Imaging with Deep Learning

2021 ◽  
Author(s):  
A. A. Dovganich ◽  
A. V. Khvostikov ◽  
A. S. Krylov ◽  
L. E. Parolina
Keyword(s):  
Quality Control ◽  
Deep Learning ◽  
X Ray ◽  
X Ray Imaging ◽  
Automatic Quality Control

Thermal Model of Printed Circuit Board Plated-Through Hole under One-Sided Heating Conditions

2021 ◽  
Vol 26 (5) ◽  
pp. 426-431
Author(s):  
V.A. Sergeev ◽  
◽  
A.M. Khodakov ◽  
M.Yu. Salnikov ◽  
◽  
...  
Keyword(s):  
Quality Control ◽  
Thermal Resistance ◽  
Thermal Model ◽  
Printed Circuit Board ◽  
Circuit Board ◽  
Thermal Models ◽  
Printed Circuit ◽  
Plated Through Hole ◽  
Through Hole

Thermal methods of quality control of the plated-through hole (PTH) of printed circuit board (PCB) are based on thermal models. However, known thermal models of PTH take no account of heat transfer to PCB material thus not allowing for PTH heat characteristic tying up with adhesion quality. In this work, an axisymmetric thermal model of a single-layer PCB PTH under one-sided heating conditions is considered. It was shown that the ratio of the temperature increments of the upper (heated) and lower end of the PTH in the considered range of heating power does not depend on the power level. A linear thermal equivalent scheme of the PTH has been proposed, which includes the longitudinal thermal resistance of the PTH metallization, de-termined by the parameters and quality of the metallization layer, the thermal resistance, which determines the convection heat exchange between the ends of the PTH with the adjacent PCB surface and the environment, and the thermal resistance of the area of the PCB material adjacent to the PTH, depending on the quality of the metallization adhesion and the PCB dielectric. Thermal equivalent circuit parameters determined by the ratio of the temperature increment of the upper and lower ends of the PTH and their difference can serve as the basis for the development of a nondestructive inspection procedure for PTH quality control by way of its unilateral heating, for example, by a laser beam.

scholarly journals Artificial Intelligence Framework for Efficient Detection and Classification of Pneumonia Using Chest Radiography Images

2021 ◽  
Author(s):  
Ali Mohammad Alqudah ◽  
Shoroq Qazan ◽  
Ihssan S. Masad
Keyword(s):  
Artificial Intelligence ◽  
Input Image ◽  
Image Size ◽  
X Ray ◽  
Softmax Classifier ◽  
Non Invasive ◽  
Efficient Detection ◽  
X Ray Imaging ◽  
Chest X Ray

Abstract BackgroundChest diseases are serious health problems that threaten the lives of people. The early and accurate diagnosis of such diseases is very crucial in the success of their treatment and cure. Pneumonia is one of the most widely occurred chest diseases responsible for a high percentage of deaths especially among children. So, detection and classification of pneumonia using the non-invasive chest x-ray imaging would have a great advantage of reducing the mortality rates.ResultsThe results showed that the best input image size in this framework was 64 64 based on comparison between different sizes. Using CNN as a deep features extractor and utilizing the 10-fold methodology the propose artificial intelligence framework achieved an accuracy of 94% for SVM and 93.9% for KNN, a sensitivity of 93.33% for SVM and 93.19% for KNN and a specificity of 96.68% for SVM and 96.60% for KNN.ConclusionsIn this study, an artificial intelligence framework has been proposed for the detection and classification of pneumonia based on chest x-ray imaging with different sizes of input images. The proposed methodology used CNN for features extraction that were fed to two different types of classifiers, namely, SVM and KNN; in addition to the SoftMax classifier which is the default CNN classifier. The proposed CNN has been trained, validated, and tested using a large dataset of chest x-ray images contains in total 5852 images.

scholarly journals Deep Learning-Based Decision-Tree Classifier for COVID-19 Diagnosis From Chest X-ray Imaging

2020 ◽  
Vol 7 ◽  
Author(s):  
Seung Hoon Yoo ◽  
Hui Geng ◽  
Tin Lok Chiu ◽  
Siu Ki Yu ◽  
Dae Chul Cho ◽  
...  
Keyword(s):  
Deep Learning ◽  
Decision Tree ◽  
Decision Tree Classifier ◽  
X Ray ◽  
X Ray Imaging ◽  
Tree Classifier ◽  
Chest X Ray

scholarly journals Quality management systems in radiology

2013 ◽  
Vol 17 (3) ◽  
pp. 84-88
Author(s):  
Geoffrey K. Korir ◽  
Jeska S. Wambani ◽  
Ian K. Korir ◽  
Mark Tries ◽  
Beatrice M. Mulama
Keyword(s):  
Quality Control ◽  
Quality Management ◽  
Management Systems ◽  
Reference Level ◽  
Quality Management Systems ◽  
X Ray ◽  
Dose Monitoring ◽  
X Ray Imaging ◽  
National Quality ◽  
Medical Facilities

Background: The use of X-ray imaging is ever increasing in proportion to the need for radiological services and technological capabilities. Quality management that includes patient radiation dose monitoring is fundamental to safety and quality improvement of radiological services.Objective: To assess the level of quality management systems in X-ray medical facilities in Kenya.Methods: Quality management inspection, quality control performance tests and patient radiation exposure were assessed in 54 representative X-ray medical facilities. Additionally, a survey of X-ray examination frequency was conducted in 140 hospitals across the country.Results: The overall findings placed the country’s X-ray imaging quality management systems at 61±3% out of a possible 100%. The most and the least quality assurance performance indicators were general radiography X-ray equipment quality control tests at 88±4%, and the interventional cardiology adult examinations below diagnostic reference level at 25±1%, respectively.Conclusions: The study used a systematic evidence-based approach for the assessment of national quality management systems in radiological practice in clinical application, technical conduct of the procedure, image quality criteria, and patient characteristics as part of the quality management programme.

Sign in / Sign up

Export Citation Format

Share Document