Open AccessResearch of methods for pumping technological equipment condition predictive monitoring
Author(s) -
V. V. Bukhtoyarov,
V. S. Tynchenko,
К. А. Башмур,
Eduard Petrovskiy,
В. В. Кукарцев,
N. A. Bukhtoyarova
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1399/5/055082
Subject(s) - exponential smoothing , artificial neural network , singular spectrum analysis , computer science , smoothing , series (stratigraphy) , spectral analysis , exponential function , algorithm , mathematics , artificial intelligence , singular value decomposition , mathematical analysis , physics , paleontology , quantum mechanics , spectroscopy , computer vision , biology
The article discusses the need to develop a diagnostic prognostic unit for certain types of technological equipment. Several well-known methods for predicting time series are considered: a method based on artificial neural couples, a method for analyzing a singular spectrum, an exponential smoothing method. A brief description of the methods under consideration is given. The parameters of the numerical study of the methods are described. The results of a numerical study are presented, the advantage of the neural network approach and the method of singular spectral analysis are shown.