|
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.
Received: 22.02.2011
Citation:
P. V. Evdokimov, “Choice of parameters for neuronetwork model
of argon-arc welding management process”, News of the Kabardin-Balkar scientific center of RAS, 2011, no. 1, 118–121
Linking options:
https://www.mathnet.ru/eng/izkab597 https://www.mathnet.ru/eng/izkab/y2011/i1/p118
|
Statistics & downloads: |
Abstract page: | 29 | Full-text PDF : | 7 | References: | 13 |
|