Estimate Permeability from Nuclear Magnetic Resonance Measurements Using Improved Artificial Neural Network Based on Genetic Algorithm

Abstract:

Knowledge of the permeability distribution is critical to a successful reservoir model. Nuclear Magnetic Resonance (NMR) measurements can be used for permeability prediction because the T₂ relaxation time is proportional to pore size. Due to the conventional estimators have difficult and complex problems in simulating the relationship between permeability and NMR measurements, an intelligent technique using artificial neural network and genetic algorithm to estimate permeability from NMR measurements is developed. Neural network is used as a nonlinear regression method to develop transformation between the permeability and NMR measurements. Genetic algorithm is used for selecting the best parameters and initial value for the neural network, which solved two major problems of the network: local minima and parameter selection depend on experience. Information gain principle is introduced to select the neural network's input parameters automatically from data. The technique is demonstrated with an application to the well data in Northeast China. The results show that the refined technique make more accurate and reliable reservoir permeability estimation compared with conventional methods. This intelligent technique can be utilized a powerful tool for estimate permeability from NMR logs in oil and gas industry.

• Periodical: Applied Mechanics and Materials (Volumes 110-116)
• Pages: 5072-5077
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.110-116.5072
• Online since: October 2011
• Authors: Yu Zhou, Guo Qi Wei, He Kun Guo
• Keywords: Genetic Algorithm (GA), Information Gain, Neural Network (NN), Nuclear Magnetic Resonance, Permeability

References

[1] D. Tiab and E.C. Donaldson, Petrophysics, 2nd ed., Elsevier, 2004, pp.65-67.

[2] J. Kozeny, Uber Die Kapillare Leitung des Wassers im Boden, Situngsber Akad. Wiss, Wein, Math – Naturwiss, KL, vol. 136(Ila), 1927, pp.271-306.

[3] W.E. Kenyon, J.J. Howard, A. Sezginer, C. Straley, A. Matteson, K. Horkowita, and R. Ehrlich, Pore-size distribution and NMR in microporous cherty sandstones, SPWLA 30th Anual Loggong Symposium, Paper LL, (1989).

[4] W.E. Kenyon, Nuclear magnetic resonance as a petrophysical measurement, Nuclear Geophysics, 6(2), 1992, pp.153-171.

[5] W.E. Kenyon, Petrophysical principles of applications of NMR logging, The Log Analyst, vol. 38, 1997, pp.21-43.

[6] Straley, D. Rossini, H.J. Vinegar, P.N. Tutunjian and C.E. Morriss, Core analysis by low-field NMR, The Log Analyst, vol. 38, 1997, pp.84-94.

[7] J.D. Loren and J.D. Robinson, Relations between pore size, ffuid and matrix properties, and NML mea- surements, Soc, Petrol. Eng. J, vol. 10, 1970, pp.268-278.

DOI: 10.2118/2529-pa

[8] W.E. Kenyon, P.I. Day, C. Straley and J.F. Willemsen, A three-part study of NMR longitudinal relaxation properties of water-saturated sandstones, SPE For mation Evaluation, vol. 3, 1998, pp.622-636.

DOI: 10.2118/15643-pa

[9] J.R. Banavar and L.M. Schwartz, Magnetic Resonance as a Probe of Permeability in Porous Media, Phys. Rev. Lett., vol. 58, 1987, pp.1411-1414.

DOI: 10.1103/physrevlett.58.1411

[10] G.R. Coates, and J.L. Dumanoir, A New Approach to Improved Log-Derived Permeability, The Log Analyst, vol. 15, 1974, pp.17-31.

[11] Timur, An investigation of permeability, porosity, and residual water saturation relationships, The Log Analyst, vol. 9, 1968, pp.8-17.

[12] C.I. guru, U.O. Onyeagoro, J. Lin, J. Okkerman and I.O. Sikiru, Permeability prediction using genetic unit averages of flow zone indicators (FZIs) and Neural Network, SPE98828, (2005).

DOI: 10.2118/98828-ms

[13] C.E. Shannon. A mathematical theory of communication, The bell system technical journal, vol. 27, 1948, pp.379-423, 623-656.

DOI: 10.1002/j.1538-7305.1948.tb00917.x

[14] T. Yang, Computational Verb Decision Trees,. International Journal of Computational Cognition, vol. 4 (4), 2006, p.34–46.

[15] S.D. Mohaghegh, Virtual Intelligence Applications in Petroleum Enginerring: Patr 1-Artificial Neural Networks, SPE 58046, JPT Sep. 2000, pp.64-70.

[16] S.D. Mohaghegh, Virtual Intelligence Applications in Petroleum Enginerring: Patr 2-Evolutionary Computing, paper SPE 61925, JPT Oct. 2000, pp.40-46.

[17] Berson, S. Smith, K. Thearling, Building Data Mining Applications for CRM, McGraw-Hill, (1999).

[18] H.N. Robert, Kolmogorov's mapping neural network existence theorem, Proc IEEE 1st Inter Conf on Neural Networks, 1987), Volume: 3, Publisher: IEEE Press, pp.11-13.

[19] D.S. Huang, The Local Minima-Free Condition of Feedforward Neural Networks for Outer-Supervised Learning, IEEE Transactons on systems, man, and cybernetics - Part B: Cybernetics, vol. 28, No. 3, 1998, pp.477-480.

DOI: 10.1109/3477.678658

[20] Y. Chauvin, D.E. Rumelhart, Backpropagation: theory, architectures, and applications, Lawrence Erlbaum Associates, Inc, (1995).