A novel convolutional neural network for electronic component classification with diverse backgrounds

2021 ◽  
Author(s):  
Longfei Zhou ◽  
Lin Zhang
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Convolutional Neural Network ◽  
Printed Circuit Board ◽  
Manufacturing Industries ◽  
Circuit Board ◽  
Electronics Manufacturing ◽  
Electronic Components ◽  
Printed Circuit ◽  
Single Category

The rapid development of computer vision techniques has brought new opportunities for manufacturing industries, accelerating the intelligence of manufacturing systems in terms of product quality assurance, automatic assembly, and industrial robot control. In the electronics manufacturing industry, intensive variability in component shapes and colors, background brightness, and visual contrast between components and background results in difficulties in printed circuit board image classification. In this paper, we apply computer vision techniques to detect diverse electronic components from their background images, which is a challenging problem in electronics manufacturing industries because there are multiple types of components mounted on the same printed circuit board. Specifically, a 13-layer convolutional neural network (ECON) is proposed to detect electronic components either of a single category or of diverse categories. The proposed network consists of five Convolution-MaxPooling blocks, followed by a flattened layer and two fully connected layers. An electronic component image dataset from a real manufacturing company is applied to compare the performance between ECON, Xception, VGG16, and VGG19. In this dataset, there are 11 categories of components as well as their background images. Results show that ECON has higher accuracy in both single-category and diverse component classification than the other networks.

scholarly journals SMT Assembly Inspection Using Dual-Stream Convolutional Networks and Two Solder Regions

2020 ◽  
Vol 10 (13) ◽  
pp. 4598
Author(s):  
Young-Gyu Kim ◽  
Tae-Hyoung Park
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Classification Accuracy ◽  
Printed Circuit Board ◽  
Circuit Board ◽  
Printed Circuit ◽  
Convolutional Networks ◽  
Single Stream ◽  
Automated Optical Inspection ◽  
Network Weight

The automated optical inspection of a surface mount technology line inspects a printed circuit board for quality assurance, and subsequently classifies the chip assembly defects. However, it is difficult to improve the accuracy of previous defect classification methods using full chip component images with single-stream convolutional neural networks due to interference elements such as silk lines included in a printed circuit board image. This paper proposes a late-merge dual-stream convolutional neural network to increase the classification accuracy. Two solder regions are extracted from a printed circuit board image and are input to a convolutional neural network with a merge stage. A new convolutional neural network structure is then proposed that is able to classify for defects. Since defect features are concentrated in solder regions, the classification accuracy is increased. In addition, the network weight is reduced due to a reduction of the input data. Experimental results for the proposed method show a 5.3% higher performance in F1-score than a single-stream convolutional neural network based on full chip component images.

A Virtual Prototyping Framework for Electronics Manufacturing

Manufacturing ◽  
2002 ◽  
Author(s):  
J. Cecil ◽  
A. Kanchanapiboon
Keyword(s):  
Life Cycle ◽  
Printed Circuit Board ◽  
Virtual Prototyping ◽  
Circuit Board ◽  
Electronics Manufacturing ◽  
Functional Evaluation ◽  
Surface Mount Technology ◽  
Team Members ◽  
Printed Circuit ◽  
Pcb Assembly

This paper presents a framework for supporting virtual prototyping related activities in the domain of printed circuit board (PCB) assembly. The focus of discussion is restricted to Surface Mount Technology (SMT) based processes only. In general, Virtual Prototyping enables the conceptualization, evaluation and validation of proposed ideas, plans and solutions. Using a virtual prototyping framework, cross functional evaluation and analysis can be facilitated where designers, manufacturing engineers, testing and other life-cycle team members can communicate effectively as well as identify and eliminate problems, which may arise later in the downstream manufacturing and testing activities.

scholarly journals Universal synthesis of conductive liquid network in polymers enabling elastic printed circuit board technology

2021 ◽  
Author(s):  
Jiheong Kang ◽  
Wonbeom Lee ◽  
Hyunjun Kim ◽  
Inho Kang ◽  
Hongjun Park ◽  
...  
Keyword(s):  
Liquid Metal ◽  
Acoustic Field ◽  
Printed Circuit Board ◽  
Circuit Board ◽  
System Level ◽  
Large Strains ◽  
Stretchable Electronics ◽  
Electronic Components ◽  
Conductive Liquid ◽  
Printed Circuit

Abstract Stretchable electronics are considered next-generation electronic devices in a broad range of emerging fields, including soft robotics1,2, biomedical devices3,4, human-machine interfaces5,6, and virtual or augmented reality devices7,8. A stretchable printed circuit board (S-PCB) is a basic conductive framework for the facile assembly of system-level stretchable electronics with various electronic components. Since an S-PCB is responsible for electrical communications between numerous electronic components, the conductive lines in S-PCB should strictly satisfy the following features: (i) metallic conductivity, (ii) constant electrical resistance during dynamic stretching, and (iii) tough interface bonding with various components9. Despite recent significant advances in intrinsically stretchable conductors10,11,12, they cannot simultaneously satisfy the above stringent requirements. Here, we present a new concept of conductive liquid network-based elastic conductors. These conductors are based on unprecedented liquid metal particles assembled network (LMPNet) and an elastomer. The unique assembled network structure and reconfigurable nature of the LMPNet conductor enabled high conductivity, high stretchability, tough adhesion, and imperceptible resistance changes under large strains, which enabled the first elastic-PCB (E-PCB) technology. We synthesized LMPNet through an acoustic field-driven cavitation event in the solid state. When an acoustic field is applied, liquid metal nanoparticles (LMPnano) are remarkably generated from original LMPs and assemble into a highly conductive particle network (LMPNet). Finally, we demonstrated a multi-layered E-PCB, in which various electronic components were integrated with tough adhesion to form a highly stretchable health monitoring system. Since our synthesis of LMPNet is universal, we could synthesize LMPNet in various polymers, including hydrogel, self-healing elastomer and photoresist and add new functions to LMPNet.

scholarly journals Thermal and Electrical Analysis of Solid Aluminium Capacitors

1987 ◽  
Vol 12 (3) ◽  
pp. 167-186 ◽  
Author(s):  
E. H.L.J. Dekker ◽  
C. J.M. Lasance
Keyword(s):  
Thermal Properties ◽  
Printed Circuit Board ◽  
Circuit Board ◽  
Electronic Components ◽  
Reverse Voltage ◽  
Printed Circuit ◽  
Electrolytic Capacitors ◽  
Extensive Analysis ◽  
Current Specification ◽  
Electrical Analysis

The thermal properties of electronic components partly determine the reliability of electronic equipment. For electrolytic capacitors, they also set the limits for the ripple current and voltage values.This article first discusses the voltage limits under various conditions of temperature, frequency and polarity. Then the connection of ripple current to these parameters and to the capacitor's resistance is treated.An extensive analysis is made of the influence of heat conduction in the capacitor and the printed-circuit board, for metal-cased as well as for epoxy-coated pearl types. The study pays particular attention to solid aluminium capacitors containing a manganese dioxide semiconductor. They have some extraordinary properties: a temperature range of at least – 80 to + 175℃, and an appreciable reverse voltage potential.These can be fully employed to improve the ripple-current specification.

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.

Sign in / Sign up

Export Citation Format

Share Document