Key words: data mining, diagnostics, forecasting, oilfield equipment, neural networks, genetic algorithms.
The article describes an evolutionary approach to artificial neural network (NN) training, which is used to determine the state of oil-production equipment. A new artificial NN weight coefficient coding method using multi-chromosomes is proposed. The genetic operators of crossingover and mutation applied to multi-chromosomes are examined. A genetic algorithm structure of artificial NN training is proposed based on the developed genetic operators. A comparison of the proposed approach to NN training with existing ones has been carried out.
References
1. Korovin Ya.S, Tkachenko M.G., Kononov S.V., Neftyanoe khozyaystvo
– Oil Industry, 2012, no. 9, pp. 116-118.
2. Korovin Ya.S., Tkachenko M.G., Izvestiya Yuzhnogo federal'nogo universiteta.
Tekhnicheskie nauki - Izvestiya SFedU. Engineering Sciences,
2010, no. 12, pp. 172-178.
3. Viharos Zs.J., Monostori L., Vincze T., Training and application of artificial
neural networks with incomplete data, Lecture Notes in Computer
Science, Springer-Verlag Gmb., 2002, T. 2358, pp. 649.
4. Aksenov S.V., Novosel'tsev V.B., Organizatsiya i ispol'zovanie neyronnykh
setey: Metody i tekhnologii (The organization and the use of neural
networks: methods and technologies), Tomsk: Publ. of scientific and
technical literature, 2006, 128 р.
5. Feraud R., Clerot F., Simon J.L., et al., Kalman and neural network approaches
for the control of a vp bandwidth in an atm network, Lecture
Notes in Computer Science, Springer-Verlag Gmb., 2000, T. 1815,
pp. 655.
6. Perez-Ortiz Ju.A., Schmidhuber Ju., Gers F.A., Eck D., Improving longterm
online prediction with decoupled extended kalman filters, Lecture
Notes in Computer Science, Springer-Verlag Gmb., 2002, T. 2415,
pp. 1055.
7. Dorado Ju., Pazos A., Rivero D., Rules and generalization capacity
extraction from ann with gp Ju.R. Rabunal, Lecture Notes in Computer
Science, Springer-Verlag Gmb., 2003, 2686, pp. 606-613.
8. Mishchenko V.A., Korobkin A.A., Sovremennye problemy nauki i
obrazovaniya, 2011, no. 6, pp. 116-119.
9. Tenenev V.A., Intellektual'nye sistemy v proizvodstve, 2006, no. 2,
pp. 103-109.
10. Maor-Shoshani A., Reuven N.B., Tomer G., Livneh Z., Highly mutagenic
replication by DNA polymerase V (UmuC) provides a mechanistic
basis for SOS untargeted mutagenesis, Proc. Nat. Acad. Sci. USA,
2000, no. 97, pp. 565-570.
11. Rutkovskiy L., Metody i tekhnologii iskusstvennogo intellekta (Methods
and techniques of artificial intelligence), Moscow: Goryachaya
liniya-Telekom Publ., 2010, pp. 520.
12. UCI Machine Learning Repository, URL: http://archive.ics.uci.edu/ml/.
13. Cantu-Paz E., Pruning neural networks with distribution estimation
algorithms, Lecture Notes in Computer Science, Springer-Verlag Gmb.,
2003, T. 2723, pp. 790-800.
14. Schuessler O., Loyola D., Parallel training of artificial neural networks
using multithreaded and multicore CPUs, Lecture Notes in Computer
Science, Springer-Verlag Gmb., 2011, T. 6593 LNCS, no. PART 1, pp. 70-79.
To buy the complete text of article (Russian version a format - PDF) or to read the material which is in open access
.
