RUS  ENG
Full version
JOURNALS // News of the Kabardino-Balkarian Scientific Center of the Russian Academy of Sciences // Archive

News of the Kabardin-Balkar scientific center of RAS, 2011 Issue 1, Pages 118–121 (Mi izkab597)

COMPUTER SCIENCE. CALCULATION EQUIPMENT. MANAGEMENT

Choice of parameters for neuronetwork model of argon-arc welding management process

P. V. Evdokimov

“Electrocentromontazh” Open Stock Co, Russia, 121059, Moscow, 20-a, Berezhkovsky quay

Abstract: The possibility of Kohonen’s Self Organizing Maps (SOM) implementation for construction of dynamics objects predictive models for technological process monitoring is considered. The short review of fractal dimensionality determination methods is observed. Method of fractal dimensionality determination is used for finding optimal parameters of SOM. Problem of determination of butt joint’s quality in the argon-arc welding technological process has been analyzed by neuro-regressional model.

Keywords: dynamic objects, predictive models, time series fractal dimensionality, Kohonen Self Organizing Maps, training algorithm.

UDC: 681.5; 004.021

Received: 22.02.2011



Bibliographic databases:


© Steklov Math. Inst. of RAS, 2024