Neural network identification technology for manufacturing operations of drilling rig
/ 2
- Details
- Category: Information technologies, systems analysis and administration
- Last Updated on 24 July 2017
- Published on 24 July 2017
- Hits: 4509
Authors:
M.I.Horbiichuk, Dr. Sc. (Tech.), Prof., Ivano-Frankivsk National Technical University of Oil and Gas, Ivano-Frankivsk, Ukraine, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
T.V.Humeniuk, Cand. Sc. (Tech.), Ivano-Frankivsk National Technical University of Oil and Gas, Ivano-Frankivsk, Ukraine, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
Abstract:
Purpose. The development of methods and algorithms of identifying rig manufacturing operations to ensure the optimal control algorithm of the process of deepening the well automatically.
Methodology. The problem of identifying the technical operations of a drilling rig is formulated as the problem of pattern recognition. The Hamming neural network method was used to solve this problem.
Findings. An analysis of the basic technological operations of a rig was conducted and the methods and algorithms for solving the problem of recognition rig manufacturing operations were developed. This will provide monitoring the sequence of technological operations of mechanical drilling, held by an operator, and automatic determining of the length of round-lifting operations for the current voyage, which in its turn will enable the implementation of the algorithm of the optimal control of the process of deepening the well automatically. A new approach for determining the start and duration of technological operations of the rig during the deepening hole was suggested on the basis of artificial neural networks. Analysis of artificial neural networks showed that for the problem of recognition of rig manufacturing operations the Hamming network should be used. The architecture and the algorithm of the performance of such artificial neural network were developed.
Originality. The method for recognition operations of rig using Hamming network has been suggested for the first time, allowing us to determine the duration of the round-lifting operations for the performance in real time automatically and to develop an efficient algorithm for optimal control of the process of deepening wells.
Practical value. Algorithms and software were developed to solve the problem of recognition of rig manufacturing operations, which provide the monitoring process of the sequence of manufacturing operations to deepen the well, which is held by an operator, and automatically determine the duration of launching gear operations for the current haul cycle in order to implement the algorithm of optimal control process of deepening the well automatically. Software, developed on the basis of the suggested method and algorithm, was integrated into complex SKUB-M2. This complex was a part of the rig during drilling of the well number 5 of Vasyshchivskyi gas condensate field, which made it possible to determine the efficiency and effectiveness of the developed methods and algorithms. The suggested method and algorithm of identification the process operation of the drilling rig can also be integrated into other control systems and automatic process control to deepen the well.
References
1. Sementsov, G.N. and Sabat, N.V., 2014. Signal identification of rock drillability while deepening oil wells. Odessa: Kupriyenko S.V.
2. Horbiichuk, M.I. and Humeniuk, T.V., 2016. Determination of the drilling rig condition. GISAP. Technical sciences, construction and architecture, 10, pp. 35‒38.
3. Kropyvnytska, V.B., 2008. Computer system for optimal control of drilling oil and gas wells. Scientific Bulletin Ivano-Frankivsk National Technical University of Oil and Gas, 1, pp. 105‒109.
4. Wong, R., Liu, Q., Ringer, M., Dunlop, J., Luppens, C. and Yu, H., 2013. Advances in Real-Time Event Detection While Drilling. In: SPE/IADC Drilling Conference. Society of Petroleum Engineers, pp. 26–33.
5. Voitenko, V.S., Vitryk, V.G., Yaremiichuk, R.S. and Yaremiichuk, Y. S., 2012. Technology and engineering drilling, generalized reference book. Kyiv: Lions; Kyiv: Center of Europe.
6. Kropyvnytska, V.B., Humeniuk, T.V. and Tkachivskyi, D.A., 2010. Methods for identifying drilling rig. Herald of Khmelnytskyi National University, 1(144), pp. 94‒97.
7. Krulikovskyi, B.B., Sydor, A.I., Zastavnyi, A.N. and Nykolaichuk, Y.M., 2016. Theoretical Foundations of Recognition of multidimensional images in Hemming space. Scientific Herald of NLTU of Ukraine, 3, pp. 361‒367.
8. Suzuki, K., 2013. Artificial Neural Networks: Architectures and Applications. Winchester, Hampshire: InTech.
9. Bianchini, M., 2013. Handbook on Neural Information Processing (Intelligent Systems Reference Library). Springer.
 03_2017_Horbiichuk
|
|
 2017-07-23  431.5 KB  878 |
|
Archive