Summary Production data are essential for designing and operating electrical submersible pump (ESP) systems. This study aims to develop artificial neural network (ANN) models to predict flow rates of ESP artificially lifted wells. The ANN models were developed using 31,652 data points randomly split into 80% (25,744 data points) for training and 20% (5,625 data points) for testing. Each data set included measurements for wellhead parameters, fluid properties, ESP downhole sensor measurements, and variable speed drive (VSD) sensors parameters. The models consisted of four separate neural networks to predict oil, water, gas, and liquid flow rates. Sensitivity analyses were performed to determine the optimum number of input parameters that can be used in the model. The best performance was achieved with ANN models of 16 input parameters that are readily available in ESP wells. The results of the best ANN configuration indicate that the mean absolute percent error (MAPE) between the predicted flow rates and the actual measurements for the testing data points of the oil, water, gas, and liquid networks is 3.7, 5.2, 6.4, and 4.1%, respectively. In addition, the correlation coefficients (R2) are 0.991, 0.992, 0.983, and 0.979 for the estimated oil, water, gas, and liquid flow rates for the testing data points, respectively. The performance of the ANN models was compared against performance of published physics-based models and the results were comparable. Unlike the physics-based methods, the ANN models have the advantage that they do not require periodic calibration. The ANN models were used to predict the flow rate curves of an oilwell in the Western Desert of Egypt. The results were compared to the actual separator test data. It was clear that the model results matched the actual test data. The ANN model is useful for predicting individual well production rates within wide variety of pumping conditions and completion configurations. This should allow for continuous monitoring, optimization, and performance analysis of ESP wells as well as quicker response to operational issues. In comparison to traditional separators and multiphase flowmeters (MPFMs), the use of the developed ANN models is simple, quick, and inexpensive.

Permanent Downhole Gauges (PDG) can play great roles in production optimization as well as reservoir continuous monitoring and management. Data obtained from these gauges or sensors can give useful information to applications, including but not limited to monitoring artificial lift performance, pressure monitoring, transient well testing, and evaluation of well performance. Reservoir continuous monitoring, production losses mitigation, pump optimization and benefits from detection or prevention to early failure have been considered overcoming short-term concerns about cost containment during economic downturn. This paper presents case studies based on a pilot project deployed by Agiba Petroleum Company and Schlumberger in Aghar-4 field, Western Desert, Egypt. This field consists of three producers that are equipped with permanent downhole gauge and integrated real time system connecting bottom hole sensor technology to some essential surface measurement capability. Aghar-4 is a promising heavy oil field with a total of 13 wells drilled and being produced by sucker rod pumping to the date of the study. Aghar 4-1 was commissioned in January 2009 and is the first well in the Middle East operating with the intelligent downhole monitoring system application. This success story in Aghar 4-1 implied the installation of two more systems in Aghar 4-4 and Aghar 4-12. Later in October 2009, Aghar 4-12 made its history as the first world sucker rod well integrating downhole sensor, surface controller, and real time PC web-based satellite transmitted interface monitoring system. Artificial lift downhole equipment failures often occur within a relatively short period causing reduced or deferred production. Continuous real time monitoring of the environment in and around pumps will significantly improve production through a proactive surveillance and optimization of artificial lift operations.

Mature fields have the potential to contribute significantly to future reserves provided that the recovery can be optimized. The main objective of this paper is to discuss the application of some techniques and technologies to optimize the production in Ashrafi Field offshore, Gulf of Suez (GOS), Egypt. Ashrafi Field, located in south-western part of the Gulf of Suez was discovered in 1987 and put in production in 1992 from its Main Area. In 1997, the South-West Area, discovered one year before, started contributing significantly to the overall field production. The field consists of sedimentary reservoir units partially overlying a tilted block of fractured Basement reservoir. The field reached its peak production of 25,800 BOPD in June 2000 from 12 naturally flowing wells and then the production declined drastically. The only artificial lift type that was suitable for the field was the gas lift system and it was implemented starting 2004 in 80% of the wells. The strategy to unlock the unexploited potential in the field was to search for the bypassed oil through cutting edge technologies, using special techniques for stimulation of fracture Basement reservoir, combating scale and paraffin depositions in an efficient and economical manner. The final result for the use of such techniques and technologies was the increase of the oil production to more than 225 % of its levels before the intervention campaign, the increase of the gas production needed for gas lift system feeding and the decrease of the amount of produced water.

Conventionally, the transition from completion to production often requires the well to be killed immediately after perforation is completed, thus exposing the formation to potentially damaging killing fluid. To obtain a perforation tunnel with maximum productivity, this transition requires an optimal clean-up and removal of the perforation damages. Underbalance perforation through Tubing Conveyed Perforating (TCP) system is one of the best practices to ensure less damage to the perforation tunnels (perforating skin) leading to increased well productivity. However, it is very challenging in cases of completions with Electrical Submersible Pump's (ESP) to maintain productivity with undamaged reservoir by preventing any contact between reservoir and completion fluid and achieve the above simultaneously with safe well control during ESP deployment. Otherwise, the alternative solution is to run TCP string in single run then kill the well after perforation in order to install the ESP completion. As a result of the increasing emphasis on reducing operating costs, maximizing well productivity, and minimizing wellbore clean-up time, an integrated solution was designed and successfully implemented for perforating artificially lifted wells in static underbalanced condition and installing ESP completion in single run without killing the well. It combines the use of TCP system equipped with automatic release gun hanger. TCP gun string has been set by Electric Line against the required intervals, then the ESP has been separately installed and the guns has been activated through an electronic firing head for a shoot-and-drop operation. The static underbalance condition has been created by the ESP thanks to the programmed delayed firing time. After this operation, the well has been directly lined up to production flowline with minimal wellbore clean-up time. The combination of static underbalanced perforation with deep penetration charges which is able to bypass invasion zone, can create a clean perforation tunnel, and significantly reduce the post-perforating damage by killing fluid, and finally maximize the well productivity. Despite the challenging reservoir conditions (Depth= 16,500 FT, Pressure=6250 Psi, Temperature= 285 deg. F, Porosity = 8%), the Productivity Index (PI) of the wells were three times compared to the offset wells. Five jobs have been performed by Agiba Petroleum Company, one of the main operators in Western Desert of Egypt, employing this combined TCP-ESP technique which has resulted in significant savings in rig time and increased operating efficiency. This paper summarizes the practical experiences gained during the development and deployment of this integrated technique, in addition to an evaluation of the impact compared to the conventional perforation techniques through ESP downhole sensor data and well modelling.