Abstract

This paper presents a study in which injector performance is evaluated during water flooding operations in a North-Sea Field. It is well known that water quality and well conditions strongly affect injection performance. Poor water quality leads to plugging and bacterial growth which results in a loss of permeability and injectivity decline. The effect of poor water quality can be mitigated through the treatment and removal of harmful solids, dissolved oxygen (DO) and bisulfites (BI). Long-term remideation can be achieved through various stimulation techniques. However, technology limits and frequent treatment plant upsets can negate the effects of these mitigations and frequent stimulations would result in significant costs.

Optimization of injection operations depends on the selection of the proper strategy and answering questions such as “Which water contaminants have the biggest impact?” and “How much would stimulation improve injectivity?” Surprisingly, reliable answers are difficult to obtain because interactions among injection variables are obscured by highly-complex, process dynamics (time-dependencies). In this study, data mining techniques were applied in order to understand factors that affect field injection performance. The study used 11 years of injection and water quality data from 14 wells in two different blocks. Dynamic models of well behavior were synthesized using a combination of “artificial neural networks” (ANN), a machine learning technique from the field of Artificial Intelligence and “multivariate state space reconstruction” from the Chaos Theory.

Sensitivity analysis performed using the ANNs revealed the relative impacts of each variable on injector performance. Despite different histories for each well, the models were relatively uniform in quantifying the relationships between the variables. Findings included - a different response to acidizing in each block; delayed cumulative formation damage from each variable of 1-3 months; the impact of DO was more than twice that of particulate matter (PM)  and BI; and clorides (CL) had only a small affect on suppressing bioactivity. The uniformity and clarity of these results reduce uncertainties and provide operators with detailed knowledge to help optimize their injection designs.

Introduction

Water injection generally aims to both increase recovery and provide an economical waste disposal method. Operators strive to maximize the performance of their injectors while minimizing their operating costs. Performance is driven by a wide range of variables whose interactions can be difficult to quantify. A key driver is the injected water itself, which hereafter is referred to as water quality. Poor water quality leads to flaking, rust, scale and accelerated biological activity increasing total suspended solids (TSS) in the injected water. These factors reduce the formation’s effective permeability over time and ultimately the well’s injectivity. Injectivity is defined as the injected volumetric flow rate divided by the sand face injection pressure minus the average reservoir pressure. Water treatment plants are designed to remove harmful particulate matter (PM) and compounds such as dissolved oxygen (DO) and bisulphites (BI), but technology limits and frequent operational upsets take their toll over time. Stimulation can partially restore injectivity in some scenarios but at significant cost. It is necessary when mitigating the effects of formation damage to select the correct stimulation, intervention or management technique. In order to make such a selection, the primary damage mechanism must be identified; this proves to be a challenging endeavour.

Background

Today’s abundance of real-time data has created new opportunities for understanding, monitoring, and controlling dynamic processes with greater clarity and precision. Data mining is an emerging science that converts massive databases into valuable knowledge [1]. “Real-time data mining” is an advanced form used to model dynamical processes that evolve in time. It employs signal processing, statistics, machine learning, Chaos Theory, and multivariate visualization. The goal of data mining is to produce knowledge and tools for correcting and avoiding recurring problems, optimizing processes, and forecasting.