Abstract
The article deals with the issues of preliminary data processing of time series of production systems characterized by data breaks. On the example of analyzing the structure of the construction of oil and gas wells shows the presence in the time series of two characteristic classes of data breaks, the first of which is associated with randomly occurring sections of unproductive time, the second class is characteristic of technologically deterministic fastening wells. The article shows that the value of the monitored indicators is influenced by the asymmetry of the elements of the time series associated with the deviation of the discretization step from a fixed value, depending on the characteristics of individual production systems. In order to eliminate nonlinearities and non-stationary effects from time series, a multi-stage method of preliminary data processing of the initial time series was proposed, which solved the problem of removing random and non-random data breaks, and also ensured that the asymmetry of the discretization step was eliminated by transforming the original time series to drilling penetration rate. The results of the work can find practical application for planning the production activities of enterprises, including for predicting the speed of drilling oil and gas wells.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Vestnik komp'iuternykh i informatsionnykh tekhnologii
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
