scholarly journals Prediction of Static Characteristic Parameters of an Insulated Gate Bipolar Transistor Using Artificial Neural Network

Micromachines ◽  
2021 ◽  
Vol 13 (1) ◽  
pp. 4
Author(s):  
Qing Yao ◽  
Yufeng Guo ◽  
Bo Zhang ◽  
Jing Chen ◽  
Jun Zhang ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Computer Aided Design ◽  
Structural Parameters ◽  
Characteristic Parameter ◽  
Static Characteristic ◽  
Characteristic Parameters ◽  
Tcad Simulation ◽  
Artificial Neural ◽  
Latch Up

Breakdown voltage (BV), on-state voltage (Von), static latch-up voltage (Vlu), static latch-up current density (Jlu), and threshold voltage (Vth), etc., are critical static characteristic parameters of an IGBT for researchers. Von and Vth can characterize the conduction capability of the device, while BV, Vlu, and Jlu can help designers analyze the safe operating area (SOA) of the device and its reliability. In this paper, we propose a multi-layer artificial neural network (ANN) framework to predict these characteristic parameters. The proposed scheme can accurately fit the relationship between structural parameters and static characteristic parameters. Given the structural parameters of the device, characteristic parameters can be generated accurately and efficiently. Compared with technology computer-aided design (TCAD) simulation, the average errors of our scheme for each characteristic parameter are within 8%, especially for BV and Vth, while the errors are controlled within 1%, and the evaluation speed is improved more than 107 times. In addition, since the prediction process is mathematically a matrix operation process, there is no convergence problem, which there is in a TCAD simulation.

Offline Signature Verification and Forgery Detection Based on Computer Vision and Fuzzy Logic

2014 ◽  
Vol 3 (4) ◽  
pp. 156
Author(s):  
Gautam S. Prakash ◽  
Shanu Sharma
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Fuzzy Logic ◽  
Detection System ◽  
Structural Parameters ◽  
Signature Verification ◽  
Width Ratio ◽  
Forgery Detection ◽  
Offline Signature Verification ◽  
Artificial Neural

<p>Automated signature verification and forgery detection has many applications in the field of Bank-cheque processing,document  authentication, ATM access etc. Handwritten signatures have proved to be important in authenticating a person's identity, who is signing the document. In this paper a Fuzzy Logic and Artificial Neural Network Based Off-line Signature Verification and Forgery Detection System is presented. As there are unique and important variations in the feature elements of each signature, so in order to match a particular signature with the database, the structural parameters of the signatures along with the local variations in the signature characteristics are used. These characteristics have been used to train the artificial neural network. The system uses the features extracted from the signatures such as centroid, height – width ratio, total area, I<sup>st</sup> and II<sup>nd</sup> order derivatives, quadrant areas etc. After the verification of the signature the angle features are used in fuzzy logic based system for forgery detection.</p>

Parametric Analysis of the Cathode Catalyst Layer of Proton Exchange Membrane Fuel Cells Using Artificial Neural Network

2011 ◽  
Author(s):  
N. Khajeh-Hosseini-Dalasm ◽  
S. Ahadian ◽  
K. Fushinobu ◽  
K. Okazaki
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Proton Exchange Membrane ◽  
Structural Parameters ◽  
Catalyst Layer ◽  
Proton Exchange ◽  
Cathode Catalyst ◽  
Cathode Catalyst Layer ◽  
Artificial Neural ◽  
Exchange Membrane

A mathematical model was developed to study the cathode catalyst layer (CL) performance of a proton exchange membrane fuel cell (PEMFC). A number of CL parameters affecting its performance are implemented into the CL agglomerate model. These parameters are: saturation and eight structural parameters, i.e., ionomer film thickness covering the agglomerate, agglomerate radius, platinum and carbon loading, membrane content, gas diffusion layer penetration content and CL thickness. An artificial neural network (ANN) approach along with statistical methods was used for modeling, prediction, and analysis of the CL performance, which is determined by activation over-potential. The ANN was constructed to develop a relationship between the named (input) parameters and activation overpotential. An statistical analysis, namely, analysis of means (ANOM) was performed on the data obtained by the trained ANN and resulted in the main effect of each input parameter, sensitivity factors of structural parameters and their mutual combination.

Simulation of Performance Deterioration of a Microturbine and Application of Neural Network to Its Performance Diagnosis

2008 ◽  
Author(s):  
Jae Eun Yoon ◽  
Jong Joon Lee ◽  
Tong Seop Kim ◽  
Jeong Lak Sohn
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Test Data ◽  
Input Data ◽  
Data Sets ◽  
Characteristic Parameters ◽  
Performance Diagnosis ◽  
The Neural Network ◽  
Performance Deterioration ◽  
Artificial Neural

This study aims to simulate performance deterioration of a microturbine and apply artificial neural network to its performance diagnosis. As it is hard to obtain test data with degraded component performance, the degraded engine data have been acquired through simulation. Artificial neural network is adopted as the diagnosis tool. First, the microturbine has been tested to get reference operation data, assumed to be degradation free. Then, a simulation program was set up to regenerate the performance test data. Deterioration of each component (compressor, turbine and recuperator) was modeled by changes in the component characteristic parameters such as compressor and turbine efficiency, their flow capacities and recuperator effectiveness and pressure drop. Single and double faults (deterioration of single and two components) were simulated to generate fault data. The neural network was trained with majority of the data sets. Then, the remaining data sets were used to check the predictability of the neural network. Given measurable performance parameters (power, temperatures, pressures) as inputs to the neural network, characteristic parameters of each component were predicted as outputs and compared with original data. The neural network produced sufficiently accurate prediction. Reducing the number of input data decreased prediction accuracy. However, excluding up to a couple of input data still produced acceptable accuracy.

scholarly journals Online learning method based on artificial neural network to optimize magnetic shielding characteristic parameters

2019 ◽  
Vol 68 (13) ◽  
pp. 130701
Author(s):  
Xiang-Kai Peng ◽  
Jing-Wei Ji ◽  
Lin Li ◽  
Wei Ren ◽  
Jing-Feng Xiang ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Online Learning ◽  
Magnetic Shielding ◽  
Learning Method ◽  
Characteristic Parameters ◽  
Artificial Neural

Intelligent Choice of Characteristic Parameters of Oilstone in Honing of Titanium Alloy Cylinder Based on Artificial Neural Network

2010 ◽  
Vol 426-427 ◽  
pp. 35-39 ◽  
Author(s):  
Yi Fang Wen ◽  
Yan Nian Rui ◽  
Jian Dong Cao
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Titanium Alloy ◽  
High Reliability ◽  
Experimental Studies ◽  
Surface Hardness ◽  
Characteristic Parameters ◽  
Workpiece Material ◽  
Organizational Stability ◽  
Artificial Neural

Titanium alloys have good mechanical properties and organizational stability. However, due to the larger viscousity of titanium, a reasonable choice of the characteristic parameters of oilstone will directly affect the quality and efficiency of honing processing. This article solved multi-objective problem using artificial neural network with fast convergence and high precision. Based on a comprehensive analysis of the relationship between the workpiece material, materials status, surface hardness, the required surface quality and various parameters of oilstone, the improved artificial neural network algorithm-GCAQBP was adopted, through coding optimization of input and output parameters, model of intelligent choice of oilstone’s parameters was constructed about titanium alloy cylinder honing processing. Through experimental studies, it is shown that the intelligent model can choose quickly with high reliability compared with the traditional experience.

Sign in / Sign up

Export Citation Format

Share Document