Halliburton Energy Services, Inc.

Summit Esp, LLC

Luke Golden Janger

David Christopher Beck

Wesley John Nowitzki

Ryan Bridwell Ashbaugh

David Linn Self

Donn Jason Brown

Carl Albert Palmgren, Iii

Travis Chet Johnson

German Hoffman

Fernando Suzacq

Carl Albert Palmgren

A method comprises operating an electric submersible pump (ESP) motor downhole in a well. The ESP motor is electrically connected to a variable speed drive (VSD) proximate to the well. The operating comprises measuring a revolution rate and a motor current of the ESP motor for a first period of time and performing a first adjustment of a voltage output of the VSD. The method comprises measuring, after the first adjustment, the revolution rate and the motor current of the ESP motor for a second period of time determining a difference between the motor current measured for the first period of time and the motor current measured for the second period of time; and performing a second adjustment of the voltage output of the VSD based on a change in the revolution rate and the motor current between the first period of time and the second period of time.

Dynamic power optimization system and method for electric submersible motors

A system comprises an electric submersible pump (ESP) motor electrically coupled to a variable speed drive (VSD) that outputs voltage to the ESP motor. The system comprises a magnet on a shaft of the ESP motor and a downhole sensor coupled to the magnet, wherein the downhole sensor is to measure a magnetic flux of the magnet. The system comprises a VSD controller to control the VSD, wherein the VSD controller comprises a processor and a non-transitory memory storage having instructions stored thereon that are executable by the processor to perform operations comprising: obtaining a measurement of at least one pump performance variable and a motor current for a first period of time to establish a first data set and making a first adjustment to a voltage output from the VSD to the ESP motor, the first adjustment having a first adjustment type.

A motor of an electric submersible pump (ESP) is positioned in a wellbore. Measured data is received from one or more sensors. A first deep learning model running on a motor controller of the ESP determines first operating parameters or first operating conditions for the ESP based on the measured data. The motor controller sends the first operating parameters or first operating conditions to a centralized computer system. A second deep learning model running on the centralized computer system determines second operating parameters or second operating conditions associated with the ESP based on the first operating parameters or first operating conditions. The centralized computer system sends the second operating parameters or second operating conditions to the motor controller. The motor controller adjusts operation of the motor of the ESP based on the second operating parameters or second operating conditions.

Distributed machine learning control of electric submersible pumps

A dynamic power optimization system and method for electric submersible motors. A system to optimize operation of an electric submersible motor electrically coupled to a variable speed drive controlled by a computer performing dynamically in a loop the steps of obtaining measurement of a pump performance variable and motor current to establish a first data set, making a motor voltage adjustment of a first type including either an increase or a decrease, establishing a second data set after the adjustment, differencing the first data set with the second data set, and making a second adjustment to the motor voltage of the first adjustment type if the current drops and the pump performance variable is maintained within thresholds, or opposite the first adjustment type if the current rises and the pump performance variable is maintained, or if the current drops and the pump performance variable deviates outside the thresholds.

A system, method and apparatus for autonomous data collection from variable frequency drives (VFD) is described. The system includes at least two embedded control systems, each built on a commercial platform, with customized components in transportable cases. A computer program with multiple instantiations operates on the at least two embedded control systems to provide a client-server implementation of data collection and recording units. The units communicate by Wi-Fi autonomously when the client comes within range of the server. Units do not require any direct intervention by technicians to gather and store VFD system data. The client is a mobile unit is installed in a field truck operated by a driver without the training to operate a VFD. When the mobile unit obtains a communications link to a central receiving server, the unit uploads its data for processing in a processing system.

Growing community of inventors

Tulsa, OK, United States of America

Luke Golden Janger