Crude oil viscosity is an important parameter which is considered in both porous media and in pipeline channels. Estimating oil viscosity at various operating conditions of pressure and temperature is of great value to petroleum engineers.

In petroleum and reservoir engineering, we are often faced with the analysis of processes which involve petroleum fluid properties, but in many cases no experimental data is available. At such cases, empirical correlations are used to estimate the oil viscosity but these correlations are either too simple or too complex and very few of these correlations are generic. Oil viscosity correlations have been barely generated for the Niger Delta region because of inappropriate coefficients obtained for the correlations. Hence, Artificial Neural Network (ANN) has been applied as the technique for re-calibrating these coefficients.

Feed-forward back propagation networks were used with a training algorithm of Levenberg-Maquardt to develop the ANN model for re-calibrating oil viscosity correlation coefficients.

A total of 350 data points were used in the development of the ANN model for oil viscosity above bubble point pressure with inputs of T, Pb, P, µob. The newly developed ANN model shows good results when compared to the existing oil viscosity correlations. The average absolute relative error for the ANN model was obtained as 5.46094 and the regression coefficient, R, was obtained as 0.9999. The input weights and biases from the ANN model serve as the re-calibrated coefficients and constants which can be used in the existing correlations to enhance applicability

TABLE OF CONTENTS

CERTIFICATIONii

DEDICATIONiii

ACKNOWLEDGEMENTiv

ABSTRACTv

LIST OF FIGURESvi

LIST OF TABLESvii

LIST OF SYMBOLSviii

TABLE OF CONTENTSx

CHAPTER ONE1

INTRODUCTION1

1.1 Background of Study1

1.2 Petroleum Reservoir Classifications2

1.3 Reservoir Fluid Properties (PVT properties)5

1.3.1 Solution Gas-Oil-Ratio (Solution GOR)5

1.3.2 Oil Formation Volume Factor (FVF)5

1.3.3 Bubble Point Pressure6

1.3.4 Coefficient of Isothermal Compressibility of oil8

1.3.5 Oil Viscosity9

1.3.6 Gas Formation Volume Factor (FVF)11

1.3.7 Critical Point12

1.4 Laboratory Experiments13

1.5 Equation of State (EoS)14

1.6 Empirical Correlations14

1.7 Aim and Objectives15

1.8 Problem Statement15

1.9 Significance of Study16

1.10 Artificial Neural Networks (ANN)16

1.10.1 Neurons18

1.10.2 Weights and Biases19

1.10.3 Transfer Functions19

1.10.4 Layers20

CHAPTER 221

LITERATURE REVIEW21

2.1 Oil Viscosity21

2.2 Under-saturated oil viscosity correlations applicable worldwide22

2.2.1 Khan et al Correlations22

2.2.2 Chew and Connally Correlation23

2.2.3 Vasquez and Beggs Correlation23

2.2.4 Beal’s Correlation24

2.2.5 Ishenuwa et al Correlation24

2.2.6 Kartoatmodjo and Schmidt Correlation25

2.3 Review of past works relative to ANN models25

CHAPTER THREE27

METHODOLOGY27

3.1 PROCEDURES27

3.2 Performance Evaluation of Developed Network33

CHAPTER FOUR34

RESULTS AND DISCUSSION34

4.1 ANN Model Development and Testing34

4.2 Analysis of Results from ANN tool in MATLAB35

4.3 Statistical Analysis of the ANN model43

CHAPTER FIVE45

CONCLUSION AND RECOMMENDATIONS45

5.1 Conclusion45

5.2 Recommendations46

REFERENCES47