Javad Ghiasi-Freez; Amir Hatampour; Payam Parvasi

Application of Optimized Neural Network Models for Prediction of Nuclear Magnetic Resonance Parameters in Carbonate Reservoir Rocks

Full Text (PDF, 764KB), PP.21-32

Views: 0 Downloads: 0

Author(s)

Javad Ghiasi-Freez ^1,* Amir Hatampour ² Payam Parvasi ³

1. Iranian Central Oil Fields Company, National Iranian Oil Company (NIOC), Tehran, Iran

2. Pars Oil and Gas Company (POGC), Tehran, Iran

3. Islamic Azad University of Dashtestan, Borazjan, Iran

* Corresponding author.

DOI: https://doi.org/10.5815/ijisa.2015.06.02

Received: 6 Jul. 2014 / Revised: 20 Nov. 2014 / Accepted: 17 Jan. 2015 / Published: 8 May 2015

Index Terms

Nuclear Magnetic Resonance (NMR) Log, Conventional Porosity Log, Neural Network Model, Genetic Algorithm, Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO)

Abstract

Neural network models are powerful tools for extracting the underlying dependency of a set of input/output data. However, the mentioned tools are in danger of sticking in local minima. The present study went to step forward by optimizing neural network models using three intelligent optimization algorithms, including genetic algorithm (GA), particle swarm optimization (PSO), and ant colony (AC), to eliminate the risk of being exposed to local minima. This strategy was capable of significantly improving the accuracy of a neural network by optimizing network parameters such as weights and biases. Nuclear magnetic resonance (NMR) log measures some of the most useful characteristics of reservoir rock; the capabilities of the optimized models were used for prediction of nuclear magnetic resonance (NMR) log parameters in a carbonate reservoir rock of Iran. Conventional porosity logs, which are the easily accessible tools compared to NMR log’s parameters, were introduced to the models as inputs while free fluid porosity and permeability, which were measured by NMR log, are desire outputs. The performance of three optimized models was verified by some unseen test data. The results show that PSO-based network and ACO-based network is the best and poorest method, respectively, in terms of accuracy; however, the convergence time of GA-based model is considerably smaller than PSO-based and GA-based models.

Cite This Paper

Javad Ghiasi-Freez, Amir Hatampour, Payam Parvasi, "Application of Optimized Neural Network Models for Prediction of Nuclear Magnetic Resonance Parameters in Carbonate Reservoir Rocks", International Journal of Intelligent Systems and Applications(IJISA), vol.7, no.6, pp.21-32, 2015. DOI:10.5815/ijisa.2015.06.02

Reference

[1]S. D. Mohaghegh, “Virtual-intelligence applications in petroleum engineering: part 1-Artificial Neural Network” Journal of Petroleum Technology, Vol. 52, pp. 64-73, 2000.

[2]S. R. Ogilvie, S. Cuddy, C. Lindsay, A. Hurst, “Novel methods of permeability prediction from NMR tool data. Dialog” magazine of the London Petrophysical Society, pp. 15-22, 2002.

[3]C. H. Chen, Z. S. Lin, “A Committee Machine with Empirical Formulas for Permeability Prediction” Computers and Geosciences, Vol. 32, pp. 485–496, 2006.

[4]J. Ghiasi-Freez, A. Hatampour, “A Fuzzy Logic Model for Predicting Dipole Shear Sonic Imager Parameters From Conventional Well Logs” Petroleum Science and Technology, Vol. 31, pp. 2557–2568, 2013.

[5]M. H. Afshari, “Application of Ant Colony Algorithm to Pipe Network optimization” Iranian Journal of Science & Technology, Transaction B, Engineering, Vol. 31, pp 487-500, 2007.

[6]O. Velez-Langs, “Genetic algorithms in oil industry: An overview” Petroleum Science and Engineering, Vol. 47, pp. 15– 22, 2005.

[7]G. R. Coates, M. Miller, M. Gillen, C. Henderson, “The MRIL In Conoco 33-1 An Investigation Of A New Magnetic Resonance Imaging Log, 32nd Annual SPWLA Logging Symposium Transactions, p. 24. 1991.

[8]S. K. Nanda, D. P. Tripathy, S. K. Nayak, S. Mohapatra, “Prediction of Rainfall in India using Artificial Neural Network (ANN) Models” I.J. Intelligent Systems and Applications,Vol. 12, pp. 1-22, 2013.

[9]M. H. Afshari, “Application of Ant Colony Algorithm to Pipe Network optimization” Iranian Journal of Science & Technology, Transaction B, Engineering, Vol. 31, pp 487-500, 2007.

[10]A. Gupta, P. R. Sharma, “Application of GA for Optimal Location of FACTS Devices for Steady State Voltage Stability Enhancement of Power System” I.J. Intelligent Systems and Applications, Vol. 03, pp. 69-75, 2014.

[11]M. B. Gueye, A. Niang, S. Arnault, S. Thiria, M. Crépon, “Neural approach to inverting complex system: Application to ocean salinity profile estimation from surface parameters” Computers and Geosciences, Vol. 72, pp. 201-209, 2014.

[12]S. Mirzaei, A. Nikpey, P. Zarbakhsh, “ Recognition of Control Chart Patterns Using Imperialist Competitive Algorithm and Fuzzy Rules Approach” I.J. Intelligent Systems and Applications, Vol. 10, pp. 67-76, 2014.

[13]S. Haykin, Neural networks: A comprehensive foundation. Englewood Cliffs, NJ: Prentice-Hall. 1991.

[14]M. Saemi, M. Ahmadi, A. Y., Varjani, “Design of neural networks using genetic algorithm for the permeability estimation the reservoir” Petroleum Science and Engineering. Vol. 59, pp. 97–105, 2007.

[15]J. Kennedy, r. C. Eberhart, “Particle swarm optimization” Proc. IEEE Intel. Conf. on Neural Network, IV, pp. 1942-1948, Piscataway NJ: IEEE Service center, 1995.

[16]M. Dorigo, G. Di Caro, The Ant Colony Optimization meta-heuristic, in New Ideas in Optimization, McGraw Hill, London, UK, pp. 11–32, 1999.

International Journal of Intelligent Systems and Applications (IJISA)