Experimental modeling of radio information systems for solving the problem of failures forecasting

We report a simulation model of technical condition data of radio information systems at solving the problem of failures forecasting. Time cost analysis on sampling for high-accuracy forecasting of radio information systems failures showed that the performance of samples accumulation by testing the...

Full description

Saved in:
Bibliographic Details
Published in:Journal of physics. Conference series 2020-03, Vol.1499 (1), p.12034
Main Authors: Perlov, A, Zyuzin, A, Kokuev, A, Kochkarov, A, L'vov, K, Tymoshenko, A
Format: Article
Language:English
Subjects:
Cost analysis
Data transmission
Failure analysis
Forecasting
Information systems
Mathematical models
Physical properties
Physics
Prediction models
Radio
Sensors
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We report a simulation model of technical condition data of radio information systems at solving the problem of failures forecasting. Time cost analysis on sampling for high-accuracy forecasting of radio information systems failures showed that the performance of samples accumulation by testing the equipment at the stands does not allows us to create radio information systems with automated operation management system on time. The existing level of product unification allows the use of both data from previous generation stations and current data from of the built-in control of new generation radar stations, due to their correlation connections. These features create the conditions for operative formation of a large amount of data on the technical states of the stations due to the development of a simulation data model of the built-in control. A feature of such a model concludes in its versatility, i.e. the formation of the data stream on both binary sensors (operational or not) and sensors of physical parameters. An analysis of the temperature recorded during the development process of the components was carried out to determine the minimum sample size required. The temperature prediction model described above was trained on samples of various volumes for determination of the influence of the training sample volume on forecast accuracy. The developed methodological apparatus for formation of data from the station's built-in control provides a solution of the problem of high-precision failure prediction.
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/1499/1/012034