2014
DOI: 10.4028/www.scientific.net/amr.909.252
|View full text |Cite
|
Sign up to set email alerts
|

Hybrid Method of Dynamograms Wavelet Analysis for Oil-Production Equipment State Identification

Abstract: In the paper we considered a hybrid method of dynamograms wavelet analysis, applied for oil-production equipment work mode identification. Neural network architecture for sucker-rod deep-well pump units malfunctions detection is proposed. The architecture of intellectual data recognition system applied for pump installation control is presented.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2

Citation Types

0
8
0

Year Published

2015
2015
2022
2022

Publication Types

Select...
3
3

Relationship

1
5

Authors

Journals

citations
Cited by 8 publications
(9 citation statements)
references
References 67 publications
(145 reference statements)
0
8
0
Order By: Relevance
“…This method consists of two stages. At the first stage the search for point features in the images [16]. At the second stage search pairs of point correspondences.…”
Section: Algorithm Of Image Superpositionmentioning
confidence: 99%
See 3 more Smart Citations
“…This method consists of two stages. At the first stage the search for point features in the images [16]. At the second stage search pairs of point correspondences.…”
Section: Algorithm Of Image Superpositionmentioning
confidence: 99%
“…At the second stage search pairs of point correspondences. The main drawback of this method is the complexity of the search point correspondences between pairs of images [15], [16].…”
Section: Algorithm Of Image Superpositionmentioning
confidence: 99%
See 2 more Smart Citations
“…Methods represent operations, modeling evolutionary processes on the basis of genetic inheritance and selection mechanisms[6] Complexity of initial model creation4 Neural network approachNon-formalizable or fuzzy tasks with modeling of difficult nonlinear dependences between factors and target indicators, identification of tendencies in the input generalizing dependences, receiving substantial results -are solved at rather small volume of initial information, the subsequent specification of models (retraining) is possible. Allow to solve problems of clustering, classification and image recognition, functions approximation, prediction/forecast, optimization[2][3][4][5] Doesn't demand big computing resources. Possesses a high speed of data processing.…”
mentioning
confidence: 99%