Loading...
| Friend's email | |
| Your name | |
| Your email | |
| enter code | |
This page was sent successfuly
- Type of Document: M.Sc. Thesis
- Language: English
- Document No: 50180 (55)
- University: Sharif University of Technology, International Campus, Kish Island
- Department: Science and Engineering
- Advisor(s): Hajsadeghi, Khosro
- Abstract:
- Determining the porosity, water saturation and permeability values in the reservoir rock, are major steps in the petroleum engineering and formation evaluation. Today in the oil industry, these parameters are obtained using Helium gas injection technique on core (Plug) samples. However, the coring operation is difficult and costly. In addition, there isn't the possibility of coring in some of wells, such as horizontal wells. In fact, the present research is the modelling of artificial neural networks to estimate permeability in one of the Iranian oil field reservoirs by using oil well logging data. In this research, MLP neural network has been used and for network training, the evolutionary optimization algorithm method such as Genetic Algorithm (GA) and Particles Swarm Optimization (PSO) algorithm has been applied. Data input includes the conductivity of reservoir rock and Gamma-Ray, Neutron, Density, and Photoelectric Effect and Sonic logs. After network training which was conducted using 80% of well data and testing this network by remaining 20% of data, the value of mean square error (MSE) in Genetic Algorithm method was calculated as 0.0125, and in the algorithm of PSO, it was calculated as 0.0039, too. Based on this result, it is concluded that the accuracy of both models is acceptable. However, in case of using PSO algorithm, the value of MSE is more acceptable than that of Genetic Algorithm. Accordingly, the use of PSO method is recommended in this research
- Keywords:
- Porosity ; Water Saturation ; Permeability ; Genetic Algorithm ; Particles Swarm Optimization (PSO) ; Multi-Layer Perceptron (MLP)
Digital Object List-
محتواي کتاب - view
Bookmark