scholarly journals Alternative negative weight for simpler hardware implementation of synapse device based neuromorphic system

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Geonhui Han ◽  
Chuljun Lee ◽  
Jae-Eun Lee ◽  
Jongseon Seo ◽  
Myungjun Kim ◽  
...  
Keyword(s):  
Hardware Implementation ◽  
Printed Circuit Board ◽  
Synaptic Weight ◽  
Circuit Complexity ◽  
Activation Function ◽  
Circuit Board ◽  
Negative Weight ◽  
Von Neumann ◽  
Higher Power ◽  
Data Consumption

AbstractLately, there has been a rapid increase in the use of software-based deep learning neural networks (S-DNN) for the analysis of unstructured data consumption. For implementation of the S-DNN, synapse-device-based hardware DNN (H-DNN) has been proposed as an alternative to typical Von-Neumann structural computing systems. In the H-DNN, various numerical values such as the synaptic weight, activation function, and etc., have to be realized through electrical device or circuit. Among them, the synaptic weight that should have both positive and negative numerical values needs to be implemented in a simpler way. Because the synaptic weight has been expressed by conductance value of the synapse device, it always has a positive value. Therefore, typically, a pair of synapse devices is required to realize the negative weight values, which leads to additional hardware resources such as more devices, higher power consumption, larger area, and increased circuit complexity. Herein, we propose an alternative simpler method to realize the negative weight (named weight shifter) and its hardware implementation. To demonstrate the weight shifter, we investigated its theoretical, numerical, and circuit-related aspects, following which the H-DNN circuit was successfully implemented on a printed circuit board.

scholarly journals Design Analysis of a Mobile-Based Gait Analyzer

2019 ◽  
Vol 3 (3) ◽  
Author(s):  
Adedotun Oluwakanyinsola Owojori ◽  
Ibukunoluwa A. Adebanjo ◽  
Samson A. Oyetunji
Keyword(s):  
Hardware Implementation ◽  
Printed Circuit Board ◽  
Dielectric Material ◽  
Circuit Board ◽  
Printed Circuit ◽  
Uniform Distance ◽  
Pressure Mapping ◽  
Short Period ◽  
Mapping Technology ◽  
Processing Circuit

Considering a system capable of identifying abnormalities in people's walking conditions in real-time, simply by studying his/her walking profile over a short period of time is a phenomenal breakthrough in the field of biotechnology. Such abnormalities could be as a result of injury, old age, or disease termed gait which could be analyzed using the pressure mapping technology. Pressure points in the feet of an injured person as he/she walks is analyzed by sets of sensors (capacitive sensors) carefully design with a rectangular 5.1cm by 2cm parallel aluminium plate and placed on developed footwear with a uniform distance of 1cm across the dielectric material. The output of the pre-processing stage gives varying values which are calibrated and sent to the microcontroller. All placed on a portable sized Printed Circuit Board (PCB) making it moveable from one place to another (that is, mobile), is the pre-processing circuit that converts measured or evaluated result to the transmittable signal through a Mobile Communication System which can be received on a Personal Computer (PC) in form of a periodic chat and/ or report. The result of the analysis is shown both in simulation and hardware implementation of the system

Coexisting Infinitely Many Nonchaotic Attractors in a Memristive Weight-Based Tabu Learning Neuron

2021 ◽  
Vol 31 (12) ◽  
pp. 2150189
Author(s):  
Liping Hou ◽  
Han Bao ◽  
Quan Xu ◽  
Mo Chen ◽  
Bocheng Bao
Keyword(s):  
Equilibrium State ◽  
Printed Circuit Board ◽  
Synaptic Weight ◽  
Circuit Board ◽  
Initial State ◽  
Printed Circuit ◽  
Extreme Multistability ◽  
Physical Processing ◽  
The Stability ◽  
Line Equilibrium

Memristive synaptic weight is a changeable connection synaptic weight. It reflects the self-adaption physical processing in biological neurons. To study its dynamical effect, this paper presents a memristive synaptic weight-based tabu learning neuron model. It is constructed by replacing the resistive self-connection synaptic weight in the tabu learning neuron with a memristive self-connection synaptic weight. The equilibrium point of the memristive tabu learning model is time-varying and switches between no equilibrium state and line equilibrium state with the change of the external current. Particularly, the stability of the line equilibrium state closely relies on the initial state of the memristor, resulting in the emergence of coexisting infinitely many nonchaotic attractors. By employing the bifurcation plots, Lyapunov exponents, and phase plots, this paper numerically reveals the initial state-switched coexisting bifurcation behaviors and initial state-relied extreme multistability, and thereby discloses the coexisting infinitely many nonchaotic attractors composed of mono-periodic, multiperiodic, and quasi-periodic orbits. In addition, PSIM circuit simulations and printed-circuit board-based experiments are executed and the coexisting infinitely many nonchaotic attractors are realized physically. The results well verify the numerical simulations.

scholarly journals YOLOv4-MN3 for PCB Surface Defect Detection

2021 ◽  
Vol 11 (24) ◽  
pp. 11701
Author(s):  
Xinting Liao ◽  
Shengping Lv ◽  
Denghui Li ◽  
Yong Luo ◽  
Zichun Zhu ◽  
...  
Keyword(s):  
Defect Detection ◽  
High Performance ◽  
Surface Defect ◽  
Printed Circuit Board ◽  
Surface Defects ◽  
Activation Function ◽  
Production Quality ◽  
Circuit Board ◽  
Detection Accuracy ◽  
Surface Defect Detection

Surface defect detection for printed circuit board (PCB) is indispensable for managing PCB production quality. However, automatic detection of PCB surface defects is still a challenging task because, even within the same category of surface defect, defects present great differences in morphology and pattern. Although many computer vision-based detectors have been established to handle these problems, current detectors struggle to achieve high detection accuracy, fast detection speed and low memory consumption simultaneously. To address those issues, we propose a cost-effective deep learning (DL)-based detector based on the cutting-edge YOLOv4 to detect PCB surface defect quickly and efficiently. The YOLOv4 is improved upon with respect to its backbone network and the activation function in its neck/prediction network. The improved YOLOv4 is evaluated with a customized dataset, collected from a PCB factory. The experimental results show that the improved detector achieved a high performance, scoring 98.64% on mean average precision (mAP) at 56.98 frames per second (FPS), outperforming the other compared SOTA detectors. Furthermore, the improved YOLOv4 reduced the parameter space of YOLOv4 from 63.96 M to 39.59 M and the number of multiply-accumulate operations (Madds) from 59.75 G to 26.15 G.

Print Copper on Ceramic for High Reliability Electronics

2015 ◽  
Vol 2015 (1) ◽  
pp. 000330-000335
Author(s):  
Ryan Persons ◽  
Paul Gundel
Keyword(s):  
Screen Printing ◽  
Printed Circuit Board ◽  
High Reliability ◽  
Dielectric Materials ◽  
Circuit Board ◽  
Printed Circuit ◽  
Design Flexibility ◽  
Higher Power ◽  
Power Densities ◽  
Primary Substrate

In the power electronics world, Direct Bonded Copper (DBC) is the primary substrate technology. In this paper, we will discuss an alternative technology utilizing screen printable copper pastes (Thick Printed Copper - TPC) on a variety of substrate technologies including Alumina (Al2O3) and Aluminum Nitride (AlN). These materials when processed, look and perform similar to DBC, but exhibit superior reliability and excellent design flexibility. DBC has drawbacks when it comes to thermal mechanical reliability and lacks the flexibility to have multiple copper thicknesses for power and signal circuits within the same design, which is easily achieved via screen printing. The benefits of this TPC system will be demonstrated through data generated on passive thermal shock tests in comparison to high end DBC. Furthermore, this Thick Print Copper technology has the excellent potential for replacing high end Metal Core Printed Circuit Board (MCPCB) technology due to utilization of higher thermal conductive dielectric materials like Al2O3 and AlN. This will allow for designers to drive their LED's harder and effectively producing LED modules with higher power densities.

scholarly journals Design and Hardware Implementation of an IGBT-Based Half-Bridge Cell for Modular Voltage Source Inverters

Electronics ◽  
2021 ◽  
Vol 10 (20) ◽  
pp. 2549
Author(s):  
Roberto Morales-Caporal ◽  
José F. Pérez-Cuapio ◽  
Haydee P. Martínez-Hernández ◽  
Raúl Cortes-Maldonado
Keyword(s):  
Hardware Implementation ◽  
Printed Circuit Board ◽  
High Efficiency ◽  
International Standards ◽  
Circuit Board ◽  
Voltage Source ◽  
Voltage Source Inverters ◽  
Power Cell ◽  
Three Phase ◽  
Grid Interconnection

This article presents the design and hardware implementation of an IGBT-based half-bridge voltage source inverter (VSI) to be used as a basic cell to assemble VSIs of different topologies in modular ways. Herein, we have presented the design methodology and utilized techniques for reducing stray inductances and EMI radiation on the printed circuit board, as well as the way to calculate and select the main electronic components. For the design of the circuit board, local regulations for grid interconnection and international standards were considered in order to obtain a safe and reliable electronic power cell. The developed hardware was subjected to different tests using AC electric motors as loads to validate its design. Two VSIs topologies were evaluated: a single-phase two-level full-bridge inverter and a three-phase two-level inverter. The experimental results validated the theory and demonstrated the excellent performance, reliability, and high efficiency of the developed half-bridge power cell for modular VSIs.

Thermal Management of QFN 48 Package Attached to Different Multi-Layers of Printed Circuit Board Designs

2003 ◽  
Author(s):  
John Chia ◽  
Charles Yang
Keyword(s):  
Thermal Efficiency ◽  
Printed Circuit Board ◽  
Circuit Board ◽  
Thermal Dissipation ◽  
Substrate Type ◽  
Printed Circuit ◽  
Higher Power ◽  
Body Sizes ◽  
Reliability Issue ◽  
Ic Package

A near CSP plastic encapsulated package with a quad flat non-leaded (QFN) structure has been drawn much attention due to it small size and lightweight applications. Thermal efficiency is the major concern for adopting such type of package in place of TSSOP package. The thermal dissipation for electronics with the higher power consumption is current developing to it uppermost limitation as a wire bonded, lead-frame substrate type of QFN with various pine counts and body sizes. It is therefore an object of the present study to investigate thermal performance of QFN package optimum design attached on different layers and thickness of laminated printed circuit board (PCB), which is further related to reliability issue of this type of IC package. Numerical simulation illustrates how the thermal efficiency of the QFN package can be reached with different PCB designs and airflow conditions.

Characteristics of Radiated Emission from a Printed Circuit Board with a Slit

2012 ◽  
Vol 132 (6) ◽  
pp. 404-410 ◽  
Author(s):  
Kenichi Nakayama ◽  
Kenichi Kagoshima ◽  
Shigeki Takeda
Keyword(s):  
Printed Circuit Board ◽  
Circuit Board ◽  
Printed Circuit ◽  
Radiated Emission

Confirming the Signal Integrity in Transmission of Digital Signals on Microstrip Straight Circuits via the Eye Diagrams

2014 ◽  
Vol 5 (1) ◽  
pp. 737-741
Author(s):  
Alejandro Dueñas Jiménez ◽  
Francisco Jiménez Hernández
Keyword(s):  
Integrated Circuits ◽  
Printed Circuit Board ◽  
Signal Integrity ◽  
High Volume ◽  
Information Storage ◽  
Circuit Board ◽  
Electromagnetic Simulation ◽  
Electronic Systems ◽  
Digital Signals ◽  
Printed Circuit

Because of the high volume of processing, transmission, and information storage, electronic systems presently requires faster clock speeds tosynchronizethe integrated circuits. Presently the “speeds” on the connections of a printed circuit board (PCB) are in the order of the GHz. At these frequencies the behavior of the interconnects are more like that of a transmission line, and hence distortion, delay, and phase shift- effects caused by phenomena like cross talk, ringing and over shot are present and may be undesirable for the performance of a circuit or system.Some of these phrases were extracted from the chapter eight of book “2-D Electromagnetic Simulation of Passive Microstrip Circuits” from the corresponding author of this paper.

DIDACTIC MODEL OF LIFT

2018 ◽  
pp. 219-224
Author(s):  
Lubica Miková
Keyword(s):  
Printed Circuit Board ◽  
Base Plate ◽  
Educational Process ◽  
Circuit Board ◽  
Basic Knowledge ◽  
Practical Training ◽  
Target Setting ◽  
Lower Base ◽  
Complex Design ◽  
Starting Point

Urgency of the research. Mechatronics products become more sophisticated and complicated. Mechatronic engineers should be prepared for this complex design process. Practical experimental model helps improve educational process as preparing for practice. Target setting. Miniaturized model of the lift suitable for practical training on subjects focused to microcontrollers, sen-sors, actuators etc. Students have possibility to make practice on laboratory exercises, where they can verify theoretical knowledge obtained on lectures. The arrangement of the model has modular character, because of possibility to rearrange or adding of new function into model. The aim was to create minimized model of real lift with all functions and systems. Actual scientific researches and issues analysis. Many universities are oriented only to finished robotic kits and do not support creativity of students. Open access and open structure model missing in this field. There is a need for fast prototyping model, which allows the creation of new design of product. Uninvestigated parts of general matters defining. The question of the design of printed circuit board are uninvestigated, because they need more time than allows normal exercises. The research objective. The main aim of educational process is to educate engineers with basic knowledge, skills and handicraft. Practical models help as support devices for fulfil of this aim. All mechatronic students can practice a training on these practical models. They become as more skilled and well-oriented engineers.. The statement of basic materials. Construction consist of upper and lower base plate connected with four pillars used as linear guide for moving of lift cage. Lower base plate includes base microcontrollers boards, resistor network, power transis-tor array board, power supply terminals, relay modules, PWM module and signals terminals. Upper base plate consist of DC motor with gearing and screw mechanism for moving the lift cage. Conclusions. The model enables supports the creativity of the students. The starting point of the using of the model can be without any wired connections. Students should connect every part and try functionality of every function. The students receive the defined several problems and they have to analyze it and make any proposal for solution of defined problems.

Sign in / Sign up

Export Citation Format

Share Document