Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Cherepovets State Un...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Повышение быстродействия в обучении нейронной сети многопараметрическому контролю процессов в металлургии на базе вычислителей низкой конфигурации

Повышение быстродействия в обучении нейронной сети многопараметрическому контролю процессов в металлургии на базе вычислителей низкой конфигурации

Abstract

The paper considers a possibility of applying the ANN theory for the tasks of the linked multi-parameter control in metallurgy. The neural net is trained by a computer and functions in a highly reliable microcontroller of the PIC18xx family. The scheme is sug-gested reducing the number of measurements to generate a learning sample due to multivariate interpolation application; an optimum method of interpolation is chosen. The factors influencing the efficiency of neural net approximation are analyzed. The training algo-rithm providing the best convergence is determined and optimum neural net configuration is computed for the case of typical non-analytical functions of three parameters.

Рассматривается возможность применения теории искусственных нейронных сетей в задачах связанного многопарамет-рического контроля в металлургии, когда сеть обучается на ЭВМ, а функционирует на высоконадежном микроконтроллере семейства PIC18xx. Предлагается схема, позволяющая сократить число измерений для формирования обучающей выборки за счет многомерной интерполяции, производится выбор оптимального метода интерполяции. Анализируются факторы, влияющие на эффективность нейросетевой аппроксимации. На примере типовых неаналитических функций трех парамет-ров определяется алгоритм обучения, обеспечивающий наилучшую сходимость, рассчитывается оптимальная конфигурация сети.

Keywords

МНОГОПАРАМЕТРИЧЕСКИЙ КОНТРОЛЬ, ВЫЧИСЛИТЕЛЬ НИЗКОЙ КОНФИГУРАЦИИ, ПОГРЕШНОСТЬ МНОГОМЕРНОЙ ИНТЕРПОЛЯЦИИ, ИСКУС-СТВЕННАЯ НЕЙРОННАЯ СЕТЬ, НЕЙРОСЕТЕВАЯ АППРОКСИМАЦИЯ, ОБРАТНОЕ РАСПРОСТРАНЕНИЕ ОШИБКИ, ПРОИЗВОДИТЕЛЬНОСТЬ СЕТИ, АЛГО-РИТМ ЛЕВЕНБЕРГА МАРКВАРДТА

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
bronze