Evaluation of the Pressure Drop due to Multi Phase Flow in Horizontal Pipes Using Fuzzy Logic and Neural Networks

Abstract

One of the most important parameters affecting flow rate in oil producing wells is the pressure drop across the surface flow-lines. The pressure drop calculation in multiphase flow is very complicated due to the empirical nature of the correlations used and the high variation in gas and liquid hold up especially in hilly terrain and rough environment that will complicate the flow regime and make negative impact on well productivity. Scientists came up with two main approaches: empirical/experimental flow correlations and mechanistic models to overcome this difficulty. These two approaches are applicable within certain conditions where their accuracy in pressure drop prediction degrades outside their design boundary ranges. The raising popularity of Artificial Intelligence (AI) techniques during the past two decades proved that AI can be an alternative solution to many of the problems where physics and classic statistics fail to provide satisfactory solutions. This paper describes the utilization of Fuzzy Logic and Neural Networks, which is one of the industry AI techniques in predicting the multiphase flow pressure drop in surface pipeline for oil fields using real testing data collected from oil fields. More than 240 published real well testing data were used in constructing the model. After filtering the data and building the model, the newly developed AI model was the best method to predict the multiphase flow pressure drop. Prosper software was used to confirm the validity of the AI methods over the other existing correlations. The final results confirmed that Adaptive Neuro-Fuzzy Inference System (ANFIS) is more accurate than all the used correlations and Neural Networks. The ANFIS model resulted in .4% absolute average error compared to a range of 17.5% – 64.57 % for the compared correlations.

Pressure Drop Due to Multiphase Flow Using Four Artificial Intelligence Methods

“…Accurate pressure drop calculation is essential for proper design of surface facilities such as pipelines and GOSP'S (Attia et al 2013). The flow of the fluid inside the tubing or the surface pipes are affected essentially by two forces: the gravity force and the friction force.…”

An Integrated Application of Cluster Analysis and Artificial Neural Networks for SAGD Recovery Performance Prediction in Heterogeneous Reservoirs

“…Applications of these hybrid systems can be found in petroleum engineering (Mohaghegh 2000), particularly in the areas of reservoir lithology identification and property prediction (Zhou et al 1993;Lim 2005;Aminzadeh & Brouwer 2006), reservoir management (Nikravesh et al 1998;Alimonti & Falcone 2004;Popa & Cassidy 2012), and optimization of well operations design (Mohaghegh & Reeves 2000;Murillo et al 2009;Attia et al 2013).…”