Proceedings of International Conference on Applied Innovation in IT 2018/03/13, Volume 6, Issue 1, pp.1-10 Detection of Changes in Oil Well Power Consumption Profile on the Basis of Dynamic Time Warping AlgorithmIvan Luzyanin, Anton PetrochenkovAbstract: At present oil companies are forced to continually decrease electric power inputs. However, energy efficiency of oil well equipment decreases in time. Well re-equipment enables to stop energy efficiency loss but it requires large additional inputs. The possible solution of this problem is development of the energy efficiency growth strategy that does not include equipment replacement. To do this the oil well model that is able to precisely estimate energy efficiency of every element in electric power system needs to be constructed. Oil well technological and mechanical parameters, determining production efficiency, are strongly connected to the electric parameters of equipment. Therefore, they need to be included in the model. Models used in oil companies for energy efficiency estimation reflect dependencies between described parameters but they do not consider instant changes of electric parameters caused by changing of electric power system regime. Mathematical models of electric power systems that consider instant changes of electrical parameters are based on differential equations which have complicated solutions. The paper considers a method for instant changes analysis in power consumption profiles of oil well equipment that is based on dynamic time warping algorithm. It is demonstrated that instant changes of electrical parameters at the short time period caused only by electric power system regime changes and are independent from well production conditions. Based on this thesis it is proposed to study instant changes of electrical parameters in wells with similar production conditions. The comparison of two modifications of dynamic time warping algorithm is presented. Investigation of the properties of given modifications when applying to power consumption profiles exposes limitations of using the method. However, the study of other algorithm modifications allows to find possible ways of overcoming the restrictions. Keywords: Oil Field, Electric Power System, Statistical Model, Dynamic Time Warping, Distance Measurement, Signal Processing DOI: 10.13142/kt10006.11 Download: PDF References:
|
|
DOI: http://dx.doi.org/10.25673/115729
Proceedings of the International Conference on Applied Innovations in IT by Anhalt University of Applied Sciences is licensed under CC BY-SA 4.0
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License
ISSN 2199-8876
Publisher: Edition Hochschule Anhalt
Location: Anhalt University of Applied Sciences
Email: leiterin.hsb@hs-anhalt.de
Phone: +49 (0) 3496 67 5611
Address: Building 01 - Red Building, Top floor, Room 425, Bernburger Str. 55, D-06366 Köthen, Germany
Except where otherwise noted, all works and proceedings on this site is licensed under Creative Commons Attribution-ShareAlike 4.0 International License.