Saudi Arabian Oil Company

Obiomalotaoso Leonard Isichei

Hassan A Hussain

Soloman M Almadi

James Ohioma Arukhe

Jawad Zahur

Al-Waleed Abdullah Al-Gouhi

Mohammed Khalid Mugharbil

Ayedh Al-Shehri

Said S Malki

Ayman Alkhalaf

Najmul Hasan Ansari

Ahmad T Shammari

Bayan A Momtan

Said Almalki

Mohammad Fahad Al-Qasimi

Faisal Khelaiwi

Muhammad Daanyal

Abdulmonam Al-Maghlouth

Razan M Alzamanan

Systems and methods include a computer-implemented method for well models. Historical well data for past operations of a well is received. An expanded minimum/maximum range of values for the historical well data is generated for parameters used in a well model. Object-oriented object instances are generated using the historical well data and the expanded range. Each object instance is an object that includes a specific combination of parameters within the expanded range. The well model is executed using the instances, generating result objects, each representing a result of the well model. A hybrid well model variant of the well model is generated using the object instances and result objects to model combinations of the object instances and the result objects. A data object encapsulating the object instances and result objects is passed by an object-oriented application to a machine learning model in an absence of database tables.

Generating well model flow tables for artificial intelligent models

A system and method for controlling an electrical submersible pump (ESP) of a well, including a processor and a non-transitory computer-readable medium storing instructions that when executed by the processor cause the processor to perform operations. The operations include obtaining a well model corresponding to the well, obtaining a target well rate for the well, then receiving, from one or more data sources associated with one or more components of the well, operational data associated with the ESP operating at the target well rate within the well, determining a target efficiency of the ESP at the target well rate based on the well model, and then modifying, based on the operational data and the target efficiency an operating characteristic of the ESP.

Optimizing the performance of electrical submersible pumps (ESP) in real time

Provided are techniques that include determining a first set of operating parameters for a hydrocarbon well for a first period; determining, based on the first set of operating parameters, a skin factor (S); determining, based on the skin factor (S), a well model for the well; determining, a second set of operating parameters for the well for a second period; determining, based on the second set of operating parameters, well performance characteristics for the second period that include: a well pressure and a production flowrate for the second period of time; determining that the well performance characteristics for the second period are not consistent with the well model and, in response: determining, based on the second set of operating parameters, an updated skin factor; and determining, based on the updated skin factor (S), an updated well model for the well.

Dynamic hydrocarbon well skin modeling and operation

Provided are techniques for operating a hydrocarbon well having inflow control valves (ICVs) and an electrical submersible pump (ESP) disposed in a wellbore of the well. Baseline production data is acquired for a relatively small subset of the possible operating configurations of ICVs in the well, the baseline data is assessed to model fluid pressure gradients in the wellbore, and the modeled fluid pressure gradients are used to estimate an ESP intake pressure for one or more configurations of the ICVs, and the ICVs are controlled to operate in accordance with an ICV configuration associated with an estimated ESP intake pressure that is within an operating intake pressure range for the ESP.

Systems and methods for operating downhole inflow control valves to provide sufficient pump intake pressure

Sensor data is received from a plurality of sensors contained in an electrical submersible pump (ESP) deployed in a well hole. An early indication of an ESP failure that is imminent is determined in real time using a pattern recognition methodology based on the sensor data and a pattern detection model that correlates historical ESP failures with historical sensor readings. A notification of the imminence of the ESP failure is provided.

Predicting failures in electrical submersible pumps using pattern recognition

Embodiments provide a system and method for designing automated inflow control devices used in the extraction of hydrocarbons from subterranean formations. The system includes real-time data processing module configured to gather and process well data, the well data comprising logging while drilling data and user inputted data, and an intelligent field restriction module configured to generate one or more optimized inflow control device designs based on the well data gathered and processed by the real-time data processing module. The system further includes an inflow control design module configured to couple the one or more optimized inflow control device designs from the intelligent field restriction module with one or more scenarios to create a set of ranked optimized inflow control device designs, from which a user selects a preferred optimized inflow control device design based on well optimization goals defined in the user inputted data.

System and method for automated-inflow control device design

A method of automated preventive and predictive maintenance for downhole valves in a well system includes receiving, at a plurality of first times, first diagnostics data of the plurality of downhole valves, where each downhole valve is at a respective first valve position at a respective first time, and the diagnostics data represents a valve condition of each downhole valve at a respective valve position and at a respective time. The method also includes receiving, at a plurality of second times, second diagnostics data of the plurality of downhole valves, where each downhole valve has been moved from the respective first valve position at the respective first time to a respective second valve position at a respective second time. The first diagnostics data and the second diagnostics data are compared. Based on results of comparing, a valve maintenance operation is selected for each downhole valve.

Automated preventive and predictive maintenance of downhole valves

A process for determining the productivity index of a multilateral completion using data from individual laterals and data from commingled well tests is disclosed. The process includes 1) determining the productivity index for each single lateral by iteratively altering the productivity index until the individual lateral flowrate based on a known reservoir pressure is matched and 2) further determining the productivity index by iteratively altering the productivity index until the commingled flowrate is matched. The productivity index may be used to set wellhead pressures and inline control valve (ICV) settings for production.

Growing community of inventors

Al-Rakkah, Saudi Arabia

Obiomalotaoso Leonard Isichei