---

Journal of Applied Nonlinear Dynamics 3(4) (2014) 299--306 | DOI:10.5890/JAND.2014.12.001

Yuliya Lind$^{1}$, Jan Awrejcewicz$^{2}$ , Aigul Kabirova$^{3}$, Azamat Murzagalin$^{4}$, Anna Khashper$^{4}$

$^{1}$ BashNIPIneft LLC, Ufa, Russia

$^{2}$ Department of Automation, Biomechanics and Mechatronics, Technical University of Lodz, Lodz, Poland

$^{3}$ Laboratory of Mathematical Chemistry, Institute of Petrochemistry and Catalysis of RAS, Ufa, Russia

$^{4}$ Department of Mathematics and Information Technologies, Bashkir State University, Ufa, Russia

Download Full Text PDF

 

Abstract

The general approach to engineering of systems in oil and gas industry from the aspect of their automation and use of information technologies including design and experiment result analysis on the base of mathematical models requires involving newest technologies of artificial intelligence to obtain the most effective results. In this paper application of artificial intelligence methods such as neural networks for optimization of drilling process and automation of log curves digitization has been proposed. A hybrid neural network on the base of radial basis network learning by k-means algorithm has demonstrated the highest efficiency for solution of these problems regarding classification and pattern recognition.

Acknowledgments

The paper has been presented during 12th Conference on Dynamical Systems—Theory and Applications.

References

1. [1]	George, F. Luger (2005), Artificial Intelligence: Structures and Strategies for Complex Problem Solving, Williams, Moscow.

2. [2]	Egorov, A.A., The part of intelligence systems in oil and gas industry: conditions and prospects. Automation and IT in oil and gas industry, http://www.avite.ru/ngk/stati/rol-intellektualnyih-sistem-v-neftegazovoyotrasli- predposyilki-i-perspektivyi.html (in Russian).

3. [3]	Glova, V.I., Anikin, I.V. and Shagiakhmetov, M.R. (2001), Systems of fuzzy modeling for problems of increasing oil production solving, Bulletin of KSTU (named after A.N. Tupolev), 3, 59–61.

4. [4]	Haykin S. (2005), Neural Networks: A Comprehensive Foundation, Pearson Education.

5. [5]	Yasov V.G. and Myslyuk M.A., (1982) Prediction of Loss During Fractured Reservoirs Drilling, VNIIOENG, Moscow.

6. [6]	Gorban A.N. (1998), The generalized approximating theorem and computational power of neural networks, Siberian Journal of Computing Mathematics, 1 (1), 12–24.

7. [7]	Lind, Yu.B., Mulyukov, R.A., Kabirova, A.R., and Murzagalin, A.R. (2013), Online prediction of troubles in drilling process, Oil Industry 2, 55–57 (in Russian).

8. [8]	Lind, Yu.B. (2013), Issues of artificial intelligence methods use in solving problems of oil producing industry, Oil and Gas Business 3(11), 107–111 (in Russian).

9. [9]	Merkov, A.B., Basic methods of images recognition in paper, http://www.recognition.mccme.ru/pub/Recognition-Lab.html/methods.html (in Russian).