Valdir Estevam

DEVELOPMENT OF A NEURAL NETWORK FOR THE IDENTIFICATION OF MULTIPHASE FLOW PATTERNS

This work is concerned with the development of an artificial neural network (ANN), capable of classifying two-phase flow patterns, such as discrete bubbles, stratified, slug-flow, intermittent and annular regimes. Experimental operating data from the literature and the physical properties of the fluids were used to define and calculate dimensionless numbers. These numbers constitute the inputs of the neural model. They successfully describe the flow because they account for the competing forces occurring within the multiphase fluid. The training procedure was performed using a Levenberg-Marquardt algorithm. The methodology used to find the best network architecture is described in detail. All the flow regimes were accurately classified presenting only a small deviation. The final goal is to develop an automatic classification tool for multiphase flow patterns aimed at laboratories and field applications.

Influence of the Produced Fluids Properties and Flow Behavior on the Separation Efficiency of a Subsea Gas-Liquid Separator: A Sensitivity Analysis

The development of deep and ultra deep water fields, especially in marginal areas, always presents challenges related to profitability or associated flow assurance issues for subsea equipment.Currently, Petrobras has a great number of production wells operating in deepwater, mainly in its mature fields (brown fields), therefore we are constantly motivated to improve production capacity and reduce operational costs (OPEX) in these scenarios.In order to overcome this challenge (reduce OPEX and CAPEX) and keep focus in scenarios with high GOR, Petrobras has applied efforts in developing a high efficiency subsea gas-liquid separation system, particularly through PROCAP Technology Program - Future Vision [1]. The development of this technology is important to confirm whether is sound and reliable for use in large scale applications to increase oil production and, as well, improve both the flow assurance performance and recovery factor.In the subsea gas-liquid separation technology one of the main challenges is related to variation in the design parameters and in the flowrate range expected during the life cycle of the project. The subsea separator has to be able to handle large flowrate variations since it can work with more than one production well connected.The objective of this paper is to present the main results of the analysis carried out regarding the influence of the produced fluids properties and the flow behavior on the separation efficiency of a vertical annular subsea separator system (VASPS) [2]. The paper will present the subsea separator design and its performance when subjected to variations of fluid viscosity, fluid density, liquid and gas flowrates, bubble cut off diameter and water cut.Copyright