Maximizing Oil Recovery in a Naturally Fractured Carbonate Reservoir using Computational Intelligence Based on Particle Swarm Optimization

Abstract

A major challenge in carbonate reservoirs is the highly-fractured nature of the rock. The flow rate may be high or low depending on the targeted fracture clusters. In addition, it is possible that flow rates vary from one region of the reservoir to another. Smart wells furnished with smart completion strategy presents great prospects to produce such reservoirs intelligently, thereby, helping to deal with heterogeneities rather smartly. It is established that early water break-through occurs when multi-lateral wells are completed with constant choke settings, and therefore one way to mitigate this problem is using smart completions that manage the unexpected production through fractures, thereby increasing ultimate recovery. The early water breakthrough is obvious because if a lateral section intersects a clusters of fracture zone, there is a possibility that these fractures may connect with the water zone that may trigger the breakthrough. This can be managed by preferentially regulating production from manifold laterals. The evident communication among the various laterals of the mother bore raises difficulty in optimizing the production from the variable productivity intervals. In theory, the optimization scheme of smart completion involves different constraints, nevertheless, the settings of the smart inflow control valve (ICV) is the single most important parameter that may prove to be the differentiating factor between a high producing well to a poorly producing one. This study engrosses its effort on the reservoir engineering characteristics of finding the optimum choke setting that would lead to maximum recovery. Computational Intelligence through Particle Swarm Optimization (PSO) is utilized as the integral algorithm to determine the optimal ICV configuration for a fishbone well in a naturally fractured carbonate reservoir. A commercial black oil simulator was used to determine the objective function; whose role here is to evaluate the fitness of a configuration of the choke; this was carried out under a workflow programmed in the MATLAB programming language that coupled the optimization algorithm with the numerical simulator. A single fishbone well, having 15 laterals was studied in order tot see the effect of the fracture network on the water breakthrough and consequent impact on recovery. Three different scenarios are developed to see the impact of optimization; a base case employing only multilateral well technology without the smart well completion, a smart well completion scheme with no optimization and finally the optimized smart well completion. The results very sequentially clarify the need for not only optimization but also highlights the role of intelligent completions for wells in the reservoir being studied. It is evident that without using smart wells, the water breakthrough is relatively earlier and produces less hydrocarbons, but as the use of smart wells is incorporated, the results start improving and for complete optimization scheme of the ICVs, it is observed that the recovery has increased by almost 80% from 21% to 38%. Moreover, the time to water breakthrough and eventually the cumulative water cut has also been managed quiet significantly.

A Machine Learning Based Accelerated Approach to Infer the Breakdown Pressure of the Tight Rocks

“…Machine learning and artificial intelligence is making great progress in the oil and gas industry, with various researchers investigating advance applications pertaining to complex/heterogenous systems (Konoshonkin et al, 2020;Ma et al, 2018;Mohaghegh et al, 1994;wu zy and liu, 2018;Zhang et al, 2005Zhang et al, , 2012 (Elkatatny et al, 2016;Tariq, 2018;Tariq et al, 2021Tariq et al, , 2020cTariq et al, , 2020dTariq et al, , 2019aTariq et al, , 2019bTariq and Mahmoud, 2019). A wide range of ML algorithms have been employed to develop models/correlations for estimating various parameters related to hydrocarbons development (Ahmadi et al, 2014;Anifowose et al, 2015;da Silva et al, 2005;Janjua et al, 2016;Khan et al, 2019aKhan et al, , 2019bKhan et al, , 2018bKhan et al, , 2018aKhan et al, , 2018cLi et al, 2020;Tariq et al, 2018Tariq et al, , 2016Tohidi-Hosseini et al, 2016). Lithology determination from well logs utilizing neural networks has been the subject for various publications (Amir et al, 2020;Rogers et al, 1992).…”

An Effective Method of Estimating Nuclear Magnetic Resonance Based Porosity Using Deep Learning Approach

“…Machine learning is making great progress in the oil and gas industry, with various researchers investigating advance applications pertaining to complex/heterogenous systems (Konoshonkin et al, 2020;Ma et al, 2018;Mohaghegh et al, 1994;wu zy and liu, 2018;Zhang et al, 2005Zhang et al, , 2012 (Elkatatny et al, 2016;Tariq, 2018;Tariq et al, 2021Tariq et al, , 2019aTariq et al, , 2019bZeeshan Tariq et al, 2020b, 2020cTariq and Mahmoud, 2019). A wide range of AI algorithms have been employed to develop models/correlations for estimating various parameters related to hydrocarbons development (Ahmadi et al, 2014;Anifowose et al, 2015;da Silva et al, 2005;Janjua et al, 2016;Khan et al, 2019aKhan et al, , 2019bKhan et al, , 2018bKhan et al, , 2018aKhan et al, , 2018cLi et al, 2020;Tariq et al, 2018Tariq et al, , 2016Tohidi-Hosseini et al, 2016). Lithology determination from well logs utilizing neural networks has been the subject for various publications (Amir et al, 2020;Rogers et al, 1992).…”