Halliburton Energy Services, Inc.

Benjamin Simon Schaeffer

Mikko K Jaaskelainen

Julian Drew

Richard Gibson

Jeffrey Bridges

In some embodiments, a system for producing fluid from a well can include an electrical submersible pump (ESP) disposed in a wellbore of the well and configured to pump the fluid. The system may further include a distributed acoustic sensing (DAS) system, for example having an interrogator unit and a fiber optic cable extending downhole in the wellbore. An end of the fiber optic cable can be disposed downhole relative to the ESP. In embodiments, the system may further include a controller configured to receive data from the DAS system, process the data to detect a slug, determine a parameter of the detected slug, and alter operation of the ESP in response to determining that the parameter exceeds a threshold.

Producing fluid from a well using distributed acoustic sensing and an electrical submersible pump

Some implementations relate to a computer-implemented method for creating digital acoustic sensing (DAS) related training data for a learning machine. The method may include moving a first optimal microseismic event location to a first perturbed microseismic event location in each of a plurality of first images. The method also may include modifying first shear waves and first compressional waves in each of the first images based on one or more signal travel times between the first perturbed microseismic event location and a fiber optic cable to form a plurality of training images configured to train a learning machine.

Machine learning guided subsurface formation microseismic imaging

A method for configuring a learning machine to predict a flow rate of at least one phase of a fluid. The method comprises determining a feature set for the learning machine, the feature set including information derived from a signal generated by a flow of the fluid interacting with a fluidic oscillator in a wellbore. The method comprises configuring the learning machine with the feature set including information derived from the signal.

Machine learning-based wellbore fluid flow rate prediction

A method for determining flow information of a well producing fluid from a subsurface formation comprising. The method comprises obtaining at least one first production measurement from the well. The method comprises obtaining, with a sensor, a first measurement generated by the fluid flowing through a device. The method comprises inputting the first measurement and the at least one first production measurement into a virtual flow meter. The method comprises determining, via the virtual flow meter, a multi-phase flow rate of the fluid based on the first measurement and the at least one first production measurement.

Virtual flow metering using acoustics for a well

Aspects of the subject technology relate to systems, methods, and computer-readable media for machine learning analysis of low-frequency signal data in fracturing operations. The present technology can receive strain data associated with a monitoring well that is proximate to a treatment well. The strain data can comprise information representing a fracturing operation associated with the treatment well. Further, the present technology can convert the strain data into image data where a color scale corresponds to a degree of strain observed by a fiber optic cable deployed in the monitoring well. As follows, the present technology can provide the image data to a machine-learning model, which is configured to identify one or more features in the image data.

Machine learning analysis of low-frequency signal data in fracturing operations

An asymmetric fluidic oscillator can generate acoustic signals in a wellbore. The asymmetric fluidic oscillator can include an inlet housing defining an inlet channel, a feedback system, and an outlet housing defining an outlet channel. The inlet channel can be sized to receive fluid from the wellbore. The feedback system can be coupled to the inlet channel to oscillate the fluid from the wellbore. The outlet channel can be coupled to the feedback system and can be sized to receive the oscillated fluid from the feedback system. The outlet channel can include an asymmetric feature to generate acoustic signals detectable in the wellbore.

Growing community of inventors

Denver, CO, United States of America

Benjamin Simon Schaeffer