Use of neural networks library for material defect detection diagnosis

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F11%3A86080851" target="_blank" >RIV/61989100:27240/11:86080851 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-3-642-21762-3_58" target="_blank" >http://dx.doi.org/10.1007/978-3-642-21762-3_58</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-642-21762-3_58" target="_blank" >10.1007/978-3-642-21762-3_58</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Use of neural networks library for material defect detection diagnosis

Popis výsledku v původním jazyce

Aim of this project is to prepare support for design and realization of application, which is developed in object orientated programming language C#. This application classifies data that are obtained within industrial processes. Data used in this project was received during measurement of material diagnostics and its structural defects. Core of developed application is based on neural networks design, which is capable to classify whether the material has defect or not. Before classification itself it is necessary to set structural parameters of the neural network to obtain a good quality results. Afterwards application outputs are compared with outputs from Statistica programme, which is also used for classification purposes.

Název v anglickém jazyce

Use of neural networks library for material defect detection diagnosis

Popis výsledku anglicky

Aim of this project is to prepare support for design and realization of application, which is developed in object orientated programming language C#. This application classifies data that are obtained within industrial processes. Data used in this project was received during measurement of material diagnostics and its structural defects. Core of developed application is based on neural networks design, which is capable to classify whether the material has defect or not. Before classification itself it is necessary to set structural parameters of the neural network to obtain a good quality results. Afterwards application outputs are compared with outputs from Statistica programme, which is also used for classification purposes.

Druh

J_x - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

<a href="/cs/project/1M0567" target="_blank" >1M0567: Centrum aplikované kybernetiky</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2011

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Lecture Notes in Electrical Engineering

ISSN

1876-1100

e-ISSN

—

Svazek periodika

100 LNEE

Číslo periodika v rámci svazku

4

Stát vydavatele periodika

DE - Spolková republika Německo

Počet stran výsledku

8

Strana od-do

447-454

Kód UT WoS článku

—

EID výsledku v databázi Scopus

—