scholarly journals Real-Time Deep Learning at the Edge for Scalable Reliability Modeling of Si-MOSFET Power Electronics Converters

2019 ◽  
Vol 6 (5) ◽  
pp. 7375-7385 ◽  
Author(s):  
Mohammadreza Baharani ◽  
Mehrdad Biglarbegian ◽  
Babak Parkhideh ◽  
Hamed Tabkhi
Energies ◽  
2020 ◽  
Vol 13 (2) ◽  
pp. 373 ◽  
Author(s):  
Leonel Estrada ◽  
Nimrod Vázquez ◽  
Joaquín Vaquero ◽  
Ángel de Castro ◽  
Jaime Arau

Nowadays, the use of the hardware in the loop (HIL) simulation has gained popularity among researchers all over the world. One of its main applications is the simulation of power electronics converters. However, the equipment designed for this purpose is difficult to acquire for some universities or research centers, so ad-hoc solutions for the implementation of HIL simulation in low-cost hardware for power electronics converters is a novel research topic. However, the information regarding implementation is written at a high technical level and in a specific language that is not easy for non-expert users to understand. In this paper, a systematic methodology using LabVIEW software (LabVIEW 2018) for HIL simulation is shown. A fast and easy implementation of power converter topologies is obtained by means of the differential equations that define each state of the power converter. Five simple steps are considered: designing the converter, modeling the converter, solving the model using a numerical method, programming an off-line simulation of the model using fixed-point representation, and implementing the solution of the model in a Field-Programmable Gate Array (FPGA). This methodology is intended for people with no experience in the use of languages as Very High-Speed Integrated Circuit Hardware Description Language (VHDL) for Real-Time Simulation (RTS) and HIL simulation. In order to prove the methodology’s effectiveness and easiness, two converters were simulated—a buck converter and a three-phase Voltage Source Inverter (VSI)—and compared with the simulation of commercial software (PSIM® v9.0) and a real power converter.


Energies ◽  
2019 ◽  
Vol 12 (6) ◽  
pp. 969 ◽  
Author(s):  
Jaka Marguč ◽  
Mitja Truntič ◽  
Miran Rodič ◽  
Miro Milanovič

This paper deals with an emulation system for Power Electronics Converters (PEC). The emulation of PECs is performed on a Field-Programmable Gate Array (FPGA) capable of hard real-time operation. To obtain such a system, the converter operation is described using a differential equations-based model designed with the graph theory. Differential equation coefficients are changed according to the type of converter and pulse-width modulation (PWM) signals. The tie-set and incidence matrix approach for the converter modelling is performed to describe the converter operation in a general way. Such approach enables that any type of PECs can be described appropriately. The emulator was verified experimentally by synchronous operation with a real DC-AC converter built for this purposes.


2020 ◽  
Vol 39 (4) ◽  
pp. 5699-5711
Author(s):  
Shirong Long ◽  
Xuekong Zhao

The smart teaching mode overcomes the shortcomings of traditional teaching online and offline, but there are certain deficiencies in the real-time feature extraction of teachers and students. In view of this, this study uses the particle swarm image recognition and deep learning technology to process the intelligent classroom video teaching image and extracts the classroom task features in real time and sends them to the teacher. In order to overcome the shortcomings of the premature convergence of the standard particle swarm optimization algorithm, an improved strategy for multiple particle swarm optimization algorithms is proposed. In order to improve the premature problem in the search performance algorithm of PSO algorithm, this paper combines the algorithm with the useful attributes of other algorithms to improve the particle diversity in the algorithm, enhance the global search ability of the particle, and achieve effective feature extraction. The research indicates that the method proposed in this paper has certain practical effects and can provide theoretical reference for subsequent related research.


2020 ◽  
Vol 9 (3) ◽  
pp. 25-30
Author(s):  
So Yeon Jeon ◽  
Jong Hwa Park ◽  
Sang Byung Youn ◽  
Young Soo Kim ◽  
Yong Sung Lee ◽  
...  

Face recognition plays a vital role in security purpose. In recent years, the researchers have focused on the pose illumination, face recognition, etc,. The traditional methods of face recognition focus on Open CV’s fisher faces which results in analyzing the face expressions and attributes. Deep learning method used in this proposed system is Convolutional Neural Network (CNN). Proposed work includes the following modules: [1] Face Detection [2] Gender Recognition [3] Age Prediction. Thus the results obtained from this work prove that real time age and gender detection using CNN provides better accuracy results compared to other existing approaches.


Sign in / Sign up

Export Citation Format

Share Document