Electronic component detection based on image sample generation

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Hao Wu ◽  
Quanquan Lv ◽  
Jiankang Yang ◽  
Xiaodong Yan ◽  
Xiangrong Xu
Keyword(s):  
Deep Learning ◽  
Printed Circuit Board ◽  
Training Model ◽  
Circuit Board ◽  
Electronic Components ◽  
Generative Adversarial Network ◽  
Content Type ◽  
Real Samples ◽  
Adversarial Network ◽  
Defect Recognition

Purpose This paper aims to propose a deep learning model that can be used to expand the number of samples. In the process of manufacturing and assembling electronic components on the printed circuit board in the surface mount technology production line, it is relatively easy to collect non-defective samples, but it is difficult to collect defective samples within a certain period of time. Therefore, the number of non-defective components is much greater than the number of defective components. In the process of training the defect detection method of electronic components based on deep learning, a large number of defective and non-defective samples need to be input at the same time. Design/methodology/approach To obtain enough electronic components samples required for training, a method based on the generative adversarial network (GAN) to generate training samples is proposed, and then the generated samples and real samples are used to train the convolutional neural networks (CNN) together to obtain the best detection results. Findings The experimental results show that the defect recognition method using GAN and CNN can not only expand the sample images of the electronic components required for the training model but also accurately classify the defect types. Originality/value To solve the problem of unbalanced sample types in component inspection, a GAN-based method is proposed to generate different types of training component samples and then the generated samples and real samples are used to train the CNN together to obtain the best detection results.

Realistic warpage evaluation of printed board assembly during reflow process

2015 ◽  
Vol 27 (4) ◽  
pp. 137-145 ◽  
Author(s):  
Soonwan Chung ◽  
Jae B. Kwak
Keyword(s):  
Numerical Simulation ◽  
Boundary Conditions ◽  
Printed Circuit Board ◽  
Circuit Board ◽  
Contact Boundary ◽  
Electronic Components ◽  
Reflow Process ◽  
Common Component ◽  
Content Type ◽  
Printed Circuit

Purpose – This paper aims to develop an estimation tool for warpage behavior of slim printed circuit board (PCB) array while soldering with electronic components by using finite element method. One of the essential requirements for handheld devices, such as smart phone, digital camera, and Note-PC, is the slim design to satisfy the customers’ desires. Accordingly, the printed circuit board (PCB) should be also thinner for a slim appearance, which would result in decreasing the PCB’s bending stiffness. This means that PCB deforms severely during the reflow (soldering) process where the peak temperature goes up to 250°C. Therefore, it is important to estimate PCB deformation at a high temperature for thermo-mechanical quality/reliability after reflow process. Design/methodology/approach – A numerical simulation technique was devised and customized to accurately estimate the behavior of a thin printed board assembly (PBA) during reflow by considering all components, including PCB, microelectronic packages and solder interconnects. Findings – By applying appropriate constraints and boundary conditions, it was found that PBA’s warpage can be accurately predicted during the reflow process. The results were also validated by warpage measurement, which showed a fairly good agreement with one and another. Research limitations/implications – For research limitations, there are many assumptions regarding numerical modeling. That is, the viscoplastic material property of solder ball is ignored, the reflow profile is simplified and the accurate heat capacity is not considered. Furthermore, the residual stress within the PCB, generated at PCB manufacturing process, is not included in this paper. Practical implications – This paper shows how to calculate PBA warpage during the reflow process as accurately as possible. This methodology helps a PCB designer and surface-mount technology (SMT) process manager to predict a PBA warpage issue and modify PCB design before PCB real fabrication. Practically, this modeling and simulation process can be easily performed by using a graphical user interface (GUI) module, so that the engineer can handle an issue by inputting some numbers and clicking some buttons. Social implications – In a common sense manner, a numerical simulation method can decrease time and cost in manufacturing real samples. This PCB warpage method can also decrease product development duration and produce a new product earlier. Furthermore, PCB is a common component in all the electronic devices. So, this PCB warpage method can have various applications. Originality/value – Because of an economic advantage, the development of a numerical simulation tool for estimating the thin PBA warpage behaviour during reflow process was attempted. The developed tool contains the features of detailed modeling for electronic components and contact boundary conditions of the supporting rails in the reflow oven.

scholarly journals Transfer Learning for Toxoplasma gondii Recognition

mSystems ◽  
2020 ◽  
Vol 5 (1) ◽  
Author(s):  
Sen Li ◽  
Aijia Li ◽  
Diego Alejandro Molina Lara ◽  
Jorge Enrique Gómez Marín ◽  
Mario Juhas ◽  
...  
Keyword(s):  
Deep Learning ◽  
Toxoplasma Gondii ◽  
Transfer Learning ◽  
Cluster Algorithm ◽  
High Accuracy ◽  
Generative Adversarial Network ◽  
Content Type ◽  
Microscopic Images ◽  
Adversarial Network ◽  
Content Identification

ABSTRACT Toxoplasma gondii, one of the world’s most common parasites, can infect all types of warm-blooded animals, including one-third of the world’s human population. Most current routine diagnostic methods are costly, time-consuming, and labor-intensive. Although T. gondii can be directly observed under the microscope in tissue or spinal fluid samples, this form of identification is difficult and requires well-trained professionals. Nevertheless, the traditional identification of parasites under the microscope is still performed by a large number of laboratories. Novel, efficient, and reliable methods of T. gondii identification are therefore needed, particularly in developing countries. To this end, we developed a novel transfer learning-based microscopic image recognition method for T. gondii identification. This approach employs the fuzzy cycle generative adversarial network (FCGAN) with transfer learning utilizing knowledge gained by parasitologists that Toxoplasma is banana or crescent shaped. Our approach aims to build connections between microscopic and macroscopic associated objects by embedding the fuzzy C-means cluster algorithm into the cycle generative adversarial network (Cycle GAN). Our approach achieves 93.1% and 94.0% detection accuracy for ×400 and ×1,000 Toxoplasma microscopic images, respectively. We showed the high accuracy and effectiveness of our approach in newly collected unlabeled Toxoplasma microscopic images, compared to other currently available deep learning methods. This novel method for Toxoplasma microscopic image recognition will open a new window for developing cost-effective and scalable deep learning-based diagnostic solutions, potentially enabling broader clinical access in developing countries. IMPORTANCE Toxoplasma gondii, one of the world’s most common parasites, can infect all types of warm-blooded animals, including one-third of the world’s human population. Artificial intelligence (AI) could provide accurate and rapid diagnosis in fighting Toxoplasma. So far, none of the previously reported deep learning methods have attempted to explore the advantages of transfer learning for Toxoplasma detection. The knowledge from parasitologists is that the Toxoplasma parasite is generally banana or crescent shaped. Based on this, we built connections between microscopic and macroscopic associated objects by embedding the fuzzy C-means cluster algorithm into the cycle generative adversarial network (Cycle GAN). Our approach achieves high accuracy and effectiveness in ×400 and ×1,000 Toxoplasma microscopic images.

scholarly journals An Imbalanced Image Classification Method for the Cell Cycle Phase

Information ◽  
2021 ◽  
Vol 12 (6) ◽  
pp. 249
Author(s):  
Xin Jin ◽  
Yuanwen Zou ◽  
Zhongbing Huang
Keyword(s):  
Cell Cycle ◽  
Deep Learning ◽  
Image Classification ◽  
Classification Accuracy ◽  
Data Augmentation ◽  
Cycle Phase ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Cellular Life

The cell cycle is an important process in cellular life. In recent years, some image processing methods have been developed to determine the cell cycle stages of individual cells. However, in most of these methods, cells have to be segmented, and their features need to be extracted. During feature extraction, some important information may be lost, resulting in lower classification accuracy. Thus, we used a deep learning method to retain all cell features. In order to solve the problems surrounding insufficient numbers of original images and the imbalanced distribution of original images, we used the Wasserstein generative adversarial network-gradient penalty (WGAN-GP) for data augmentation. At the same time, a residual network (ResNet) was used for image classification. ResNet is one of the most used deep learning classification networks. The classification accuracy of cell cycle images was achieved more effectively with our method, reaching 83.88%. Compared with an accuracy of 79.40% in previous experiments, our accuracy increased by 4.48%. Another dataset was used to verify the effect of our model and, compared with the accuracy from previous results, our accuracy increased by 12.52%. The results showed that our new cell cycle image classification system based on WGAN-GP and ResNet is useful for the classification of imbalanced images. Moreover, our method could potentially solve the low classification accuracy in biomedical images caused by insufficient numbers of original images and the imbalanced distribution of original images.

Evaluation of new technologies and materials for printed circuit boards with improved heat dissipation properties

Circuit World ◽  
2016 ◽  
Vol 42 (1) ◽  
pp. 32-36 ◽  
Author(s):  
Michal Baszynski ◽  
Edward Ramotowski ◽  
Dariusz Ostaszewski ◽  
Tomasz Klej ◽  
Mariusz Wojcik ◽  
...  
Keyword(s):  
Thermal Properties ◽  
Printed Circuit Boards ◽  
Heat Dissipation ◽  
Printed Circuit Board ◽  
New Technologies ◽  
Electronic Device ◽  
Circuit Board ◽  
New Materials ◽  
Content Type ◽  
Printed Circuit

Purpose – The purpose of this paper is to evaluate thermal properties of printed circuit board (PCB) made with use of new materials and technologies. Design/methodology/approach – Four PCBs with the same layout but made with use of different materials and technologies have been investigated using thermal camera to compare their thermal properties. Findings – The results show how important the thermal properties of PCBs are for providing effective heat dissipation, and how a simple alteration to the design can help to improve the thermal performance of electronic device. Proper layout, new materials and technologies of PCB manufacturing can significantly reduce the temperature of electronic components resulting in higher reliability of electronic and power electronic devices. Originality/value – This paper shows the advantages of new technologies and materials in PCB thermal management.

A high-power PCCM LED driver based on GaN eHEMT with hybrid dimming modes

Circuit World ◽  
2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Xixian Lin ◽  
Yuming Zhang ◽  
Yimeng Zhang ◽  
Guangjian Rong
Keyword(s):  
Printed Circuit Board ◽  
Pulse Width Modulation ◽  
Circuit Board ◽  
Switching Frequency ◽  
Led Driver ◽  
Power Circuit ◽  
Content Type ◽  
Wide Range ◽  
Circuit Function ◽  
Pwm Dimming

Purpose The purpose of this study is to design a more flexible and larger range of the dimming circuit that achieves the independence of multiple LED strings drive and can time-multiplex the power circuit. Design/methodology/approach The state-space method is used to model the BUCK circuit working in Pseudo continuous conduction mode, analyze the frequency characteristics of the system transfer function and design the compensation network. Build a simulation platform on the Orcad PSPICE platform and verify the function of the designed circuit through the simulation results. Use Altium Designer 16 to draw the printed circuit board, complete the welding of various components and use the oscilloscope, direct current (DC) power supply and a signal generator to verify the circuit function. Findings A prototype of the proposed LED driver is fabricated and tested. The measurement results show that the switching frequency can be increased to 1 MHz, Power inductance is 2.2 µH, which is smaller than current research. The dimming ratio can be set from 10% to 100%. The proposed LED driver can output more than 48 W and achieve a peak conversion efficiency of 91%. Originality/value The proposed LED driver adopts pulse width modulation (PWM) dimming at a lower dimming ratio and adopts DC dimming at a larger dimming ratio to realize switching PWM dimming to analog dimming. The control strategy can be more precise and have a wide range of dimming.

Robotic system design and development for automated dismantling of PCB waste

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Ioan Doroftei ◽  
Daniel Chirita ◽  
Ciprian Stamate ◽  
Stelian Cazan ◽  
Carlos Pascal ◽  
...  
Keyword(s):  
Design Methodology ◽  
Printed Circuit Board ◽  
Vision System ◽  
Electronic Waste ◽  
Robotic System ◽  
Circuit Board ◽  
Short Introduction ◽  
Content Type ◽  
Printed Circuit ◽  
System A

Purpose The mass electronics sector is one of the most critical sources of waste, in terms of volume and content with dangerous effects on the environment. The purpose of this study is to provide an automated and accurate dismantling system that can improve the outcome of recycling. Design/methodology/approach Following a short introduction, the paper details the implementation layout and highlights the advantages of using a custom architecture for the automated dismantling of printed circuit board waste. Findings Currently, the amount of electronic waste is impressive while manual dismantling is a very common and non-efficient approach. Designing an automatic procedure that can be replicated, is one of the tasks for efficient electronic waste recovery. This paper proposes an automated dismantling system for the advanced recovery of particular waste materials from computer and telecommunications equipment. The automated dismantling architecture is built using a robotic system, a custom device and an eye-to-hand configuration for a stereo vision system. Originality/value The proposed approach is innovative because of its custom device design. The custom device is built using a programmable screwdriver combined with an innovative rotary dismantling tool. The dismantling torque can be tuned empirically.

AN AI-BASED APPROACH TO ENHANCED FRACTURE RESOLUTION IN IMAGE LOGS

2021 ◽  
Author(s):  
James Howard ◽  
◽  
Joe Tracey ◽  
Mike Shen ◽  
Shawn Zhang ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Nearest Neighbor ◽  
Rock Fracture ◽  
Short Interval ◽  
Acoustic Properties ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Deep Learning Neural Network ◽  
Borehole Image

Borehole image logs are used to identify the presence and orientation of fractures, both natural and induced, found in reservoir intervals. The contrast in electrical or acoustic properties of the rock matrix and fluid-filled fractures is sufficiently large enough that sub-resolution features can be detected by these image logging tools. The resolution of these image logs is based on the design and operation of the tools, and generally is in the millimeter per pixel range. Hence the quantitative measurement of actual width remains problematic. An artificial intelligence (AI) -based workflow combines the statistical information obtained from a Machine-Learning (ML) segmentation process with a multiple-layer neural network that defines a Deep Learning process that enhances fractures in a borehole image. These new images allow for a more robust analysis of fracture widths, especially those that are sub-resolution. The images from a BHTV log were first segmented into rock and fluid-filled fractures using a ML-segmentation tool that applied multiple image processing filters that captured information to describe patterns in fracture-rock distribution based on nearest-neighbor behavior. The robust ML analysis was trained by users to identify these two components over a short interval in the well, and then the regression model-based coefficients applied to the remaining log. Based on the training, each pixel was assigned a probability value between 1.0 (being a fracture) and 0.0 (pure rock), with most of the pixels assigned one of these two values. Intermediate probabilities represented pixels on the edge of rock-fracture interface or the presence of one or more sub-resolution fractures within the rock. The probability matrix produced a map or image of the distribution of probabilities that determined whether a given pixel in the image was a fracture or partially filled with a fracture. The Deep Learning neural network was based on a Conditional Generative Adversarial Network (cGAN) approach where the probability map was first encoded and combined with a noise vector that acted as a seed for diverse feature generation. This combination was used to generate new images that represented the BHTV response. The second layer of the neural network, the adversarial or discriminator portion, determined whether the generated images were representative of the actual BHTV by comparing the generated images with actual images from the log and producing an output probability of whether it was real or fake. This probability was then used to train the generator and discriminator models that were then applied to the entire log. Several scenarios were run with different probability maps. The enhanced BHTV images brought out fractures observed in the core photos that were less obvious in the original BTHV log through enhanced continuity and improved resolution on fracture widths.

scholarly journals Generative Adversarial Networks-Based Semi-Supervised Automatic Modulation Recognition for Cognitive Radio Networks

Sensors ◽  
2018 ◽  
Vol 18 (11) ◽  
pp. 3913 ◽  
Author(s):  
Mingxuan Li ◽  
Ou Li ◽  
Guangyi Liu ◽  
Ce Zhang
Keyword(s):  
Deep Learning ◽  
Cognitive Radio ◽  
Supervised Learning ◽  
Rapid Development ◽  
Generative Adversarial Networks ◽  
Modulation Recognition ◽  
Learning Methods ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Automatic Modulation Recognition

With the recently explosive growth of deep learning, automatic modulation recognition has undergone rapid development. Most of the newly proposed methods are dependent on large numbers of labeled samples. We are committed to using fewer labeled samples to perform automatic modulation recognition in the cognitive radio domain. Here, a semi-supervised learning method based on adversarial training is proposed which is called signal classifier generative adversarial network. Most of the prior methods based on this technology involve computer vision applications. However, we improve the existing network structure of a generative adversarial network by adding the encoder network and a signal spatial transform module, allowing our framework to address radio signal processing tasks more efficiently. These two technical improvements effectively avoid nonconvergence and mode collapse problems caused by the complexity of the radio signals. The results of simulations show that compared with well-known deep learning methods, our method improves the classification accuracy on a synthetic radio frequency dataset by 0.1% to 12%. In addition, we verify the advantages of our method in a semi-supervised scenario and obtain a significant increase in accuracy compared with traditional semi-supervised learning methods.

scholarly journals INFRASTRUCTURE DEGRADATION AND POST-DISASTER DAMAGE DETECTION USING ANOMALY DETECTING GENERATIVE ADVERSARIAL NETWORKS

2020 ◽  
Vol V-2-2020 ◽  
pp. 573-582 ◽  
Author(s):  
S. M. Tilon ◽  
F. Nex ◽  
D. Duarte ◽  
N. Kerle ◽  
G. Vosselman
Keyword(s):  
Deep Learning ◽  
Damage Detection ◽  
Training Data ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Essential Information ◽  
Urban Scenes ◽  
Adversarial Network ◽  
Collapsed Buildings ◽  
Post Disaster

Abstract. Degradation and damage detection provides essential information to maintenance workers in routine monitoring and to first responders in post-disaster scenarios. Despite advance in Earth Observation (EO), image analysis and deep learning techniques, the quality and quantity of training data for deep learning is still limited. As a result, no robust method has been found yet that can transfer and generalize well over a variety of geographic locations and typologies of damages. Since damages can be seen as anomalies, occurring sparingly over time and space, we propose to use an anomaly detecting Generative Adversarial Network (GAN) to detect damages. The main advantages of using GANs are that only healthy unannotated images are needed, and that a variety of damages, including the never before seen damage, can be detected. In this study we aimed to investigate 1) the ability of anomaly detecting GANs to detect degradation (potholes and cracks) in asphalt road infrastructures using Mobile Mapper imagery and building damage (collapsed buildings, rubble piles) using post-disaster aerial imagery, and 2) the sensitivity of this method against various types of pre-processing. Our results show that we can detect damages in urban scenes at satisfying levels but not on asphalt roads. Future work will investigate how to further classify the found damages and how to improve damage detection for asphalt roads.

Analysis of surface insulation resistance related failures in electronics by circuit simulation

Circuit World ◽  
2017 ◽  
Vol 43 (2) ◽  
pp. 45-55 ◽  
Author(s):  
Vadimas Verdingovas ◽  
Salil Joshy ◽  
Morten Stendahl Jellesen ◽  
Rajan Ambat
Keyword(s):  
Printed Circuit Board ◽  
Electronic Device ◽  
Early Stage ◽  
Circuit Simulation ◽  
Circuit Board ◽  
Insulation Resistance ◽  
Electronic Circuits ◽  
Content Type ◽  
Printed Circuit ◽  
Surface Insulation Resistance

Purpose The purpose of this study is to show that the humidity levels for surface insulation resistance (SIR)-related failures are dependent on the type of activators used in no-clean flux systems and to demonstrate the possibility of simulating the effects of humidity and contamination on printed circuit board components and sensitive parts if typical SIR data connected to a particular climatic condition are available. This is shown on representative components and typical circuits. Design/methodology/approach A range of SIR values obtained on SIR patterns with 1,476 squares was used as input data for the circuit analysis. The SIR data were compared to the surface resistance values observable on a real device printed circuit board assembly. SIR issues at the component and circuit levels were analysed on the basis of parasitic circuit effects owing to the formation of a water layer as an electrical conduction medium. Findings This paper provides a summary of the effects of contamination with various weak organic acids representing the active components in no-clean solder flux residue, and demonstrates the effect of humidity and contamination on the possible malfunctions and errors in electronic circuits. The effect of contamination and humidity is expressed as drift from the nominal resistance values of the resistors, self-discharge of the capacitors and the errors in the circuits due to parasitic leakage currents (reduction of SIR). Practical/implications The methodology of the analysis of the circuits using a range of empirical leakage resistance values combined with the knowledge of the humidity and contamination profile of the electronics can be used for the robust design of a device, which is also important for electronic products relying on low current consumption for long battery lifetime. Originality/value Examples provide a basic link between the combined effect of humidity and contamination and the performance of electronic circuits. The methodology shown provides the possibility of addressing the climatic reliability of an electronic device at the early stage of device design by using typical SIR data representing the possible climate exposure.

Sign in / Sign up

Export Citation Format

Share Document