Article

Article title APPLICATION OF ARTIFICIAL NEURAL NETWORKS OPTIMIZED BY GENETIC ALGORITHM FOR EQUIPMENT STATE ANALYSIS IN OIL AND GAS INDUSTRY
Authors M.G. Tkachenko
Section SECTION VI. COMPUTER COMPLEXES OF NEW GENERATION AND NEUROCOMPUTERS
Month, Year 07, 2014 @en
Index UDC 004.891.3
DOI
Abstract One of actual problems of oil and gas extraction enterprises is increase of equipment overall performance due to introduction of innovative technologies of the operational analysis and diagnostics. The systems constructed with application of approaches of Data mining and soft computing in the field have the greatest efficiency. The paper is devoted to model based on back-propagation artificial neural network, which is optimized by genetic algorithm. Application of genetic algorithm allows optimize network parameters calculation, decrease learning time and improve the results of the analysis process. The simulation results of the offered method in the operational analysis of technological objects condition in oil and gas extraction branch show that the proposed method can solve such problems of neural network approaches as lack of accuracy, network parameters choice difficulties, and training time. Practical application of genetic algorithm to artificial neural network has significantly improved the accuracy of predictive assessments of submersible equipment for oil industry.

Download PDF

Keywords Neural network; genetic algorithms; soft computing.
References 1. Ulyanov S., Litvintseva L., Dobrynin V, Mishin A. Intellektualnoe robastnoe upravlenie: tekhnologii myagkikh vychisleniy [Intellectual robust control: technology of soft computing]. – 1st ed. Moscow: Pronetlabs, 2011, 406 p.
2. Manzhula V.G., Fedyashov D.S. Neyronnye seti kokhonena i nechetkie neyronnye seti v intellektualnom analize dannykh [Neural network Kohonen and fuzzy neural networks in data mining] Fundamentalnye issledovaniya [Fundamental Research, 2011, No. 4, pp. 108-114.
3. Hoskins J.C., Himmelblau D.M. Process control via artificial neural networks and reinforcement learning Computers & Chemical Engineering, 1992, No. 16, pp. 241-251.
4. Rutkovskiyj L. Metody i tekhnologii iskusstvennogo intellekta [Methods and technologies of artificial intelligence]. Moscow: Goryachaya liniya-telekom, 2010, 520 p.
5. Tkachenko M.G., Korovin Ya.S., Kononov S.V. Operativnaya diagnostika sostoyaniya neftepromyslovogo oborudovaniya na osnove tekhnologiy intellektualnoy obrabotki dannykh [Operational diagnostics of oil-field equipment-based data mining technologies], Neftyanoe khozyayjstvo [Oil industry], 2012, No. 9, pp. 116-118.
6. Korovin Ya.S., Tkachenko M.G. Primenenie neyrosetevogo analiza dannykh v neftegazodobihvayushchey promyshlennosti [The use of neural network data analysis in the oil and gas industry], Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences]. 2010. No. 12, pp. 172-178.
7. Korovin Ya.S., Khisamutdinov M.G., Tkachenko M.G. Prognozirovanie sostoyaniy neftepromyslovykh obhektov s primeneniem tekhnologiy evolyutsionnykh algoritmov i iskusstvennykh neyronnykh setey [Forecasting of conditions of oil-field objects with application of technologies of evolutionary algorithms and artificial neural networks], Neftyanoe khozyaystvo [Oil industry], 2013, No. 10, pp. 128-132.
8. Ji B.Y. Overview of Oilfield Development Indicators Forecasting Methods, Petroleum Geology and Oilfield. Development in Daqing, 1999, Vol. 18, No. 2, pp. 19-22.
9. Yang B. Applied Neural Network in Oil Well Logging Petroleum Industry Press. 2005, pp. 36-39.
10. Floudas C.A., Pardalos P.M. Encyclopedia of Optimization Springer. 2008. Vol. 1, pp. 727-748.
11. Mithenko V.A., Korobkin A.A. Ispolzovanie geneticheskikh algoritmov v obuchenii neyronnykh setey [The use of genetic algorithms in training of neural networks], Sovremennye problemy nauki i obrazovaniya [Modern Problems of Science and Education], 2011, No. 6, pp. 116-119.
12. Tenenev V.A. Reshenie zadachi mnogokriterialnoy optimizacii geneticheskimi algoritmami [The solution of multicriteria optimization, genetic algorithms], Intellektualnye sistemy v proizvodstve [Intelligent Systems in Production], 2006, No. 2, pp. 03-109.
13. UCI Machine learning repository. Available at: http://archive.ics.uci.edu/ml/.
14. Kallan R. Osnovnye kontseptsii neyronnykh setey [Basic concepts of neural networks]: Per. s angl. Moscow: ID «Viljyams», 2001, 291 p.

Comments are closed.