The fifty-two sandy and multilayer reservoir from depth 500 – 1750 m in Mamburungan field became more challenging when electric submersible pumps (ESP) were used. The average 2 – 7 m range net pay height in each layer contrasts with sand production for screen implementation in reducing productivity index. Multilayer reservoirs result requires various types of ESP design based on depth. As a result, a reliable method is needed to produce the well effectively and economically. The production method was divided into two basic concerns. Firstly, determining reservoir analysis with loose sand reservoir at 500 – 1000 m depth, and consolidated sand reservoir at 1000 -1750 m depth, Secondly, designing ESP which could accommodate all layers, which are divided into two main zones, i.e. the optimum design zone at 1200 – 1750 m depth and the overdesigned zone at 500 – 1200 m depth. In an overdesigned zone attention must be paid to choke installation to limit production rate, the safety factor for motor temperature specifications based on reservoir temperature, and also the safety factor for power specifications in variable speed drive (VSD) and transformer. Currently, all ESP wells in Mamburungan field are producing without failure and the ESP operation is running smoothly by implementing the aforementioned production method. In the optimum design zone, no ESP performance issues have been raised. Meanwhile in the overdesigned zone, potential performance issues might not be arise by adhering to certain rules: application of choke to control the production rate within up thrust and down thrust area; implementation of additional 40 percent safety factor in motor temperature specification refer to the deepest layer temperature; design of VSD and transformer to provide sufficient power consumption based on motor requirement at the deepest layer. Applying the overdesigned method delivers an optimum trade-off between lifetime, cumulative production, economic value with ESP system efficiency to produce the well in Mamburungan field.
Having characteristic deltaic sandstone with 72 multilayer reservoirs with 252 perforation history became more challenging when determining potential zone. It is challenging because most of all have already produced. Regarding low oil price, high success rate on evaluating potential zones are needed. Developing an artificial intelligent (AI) to evaluate performance of potential zone based on perforation history and log evaluation could increase its success rate. Since log evaluation is used to determine potential zone, basic log evaluation parameter is used as input. There are also several zone characterizations to made AI more accurate such as; water zone, tight zone, and coal zone. Production history was used as an output and converted as 0–1. The output of this AI expected to predict cumulative production in one year in 0–1 index by iterated using Bournazel – Jeanson water breakthrough model to predict performance. Artificial Intelligent has been implemented while determining workover program. There are eight workover programs that have been executed. All of them give an expected result based on artificial intelligent prediction. Three programs has been executed and produced more than a year. The production performance created by artificial intelligence are quite match within actual performance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.