Schlumberger Technology Corporation

Other

Massachusetts Institute of Technology

Sepand Ossia

Julian J Pop

Kentaro Indo

Alexis Petit

Tullio Moscato

Maxim Nikolayevich Yushko

Tudor Ioan Palaghita

Zeynep Alpman

Kai Hsu

Steven G Villareal

Nader Salman

Agathe Robisson

Srinand Sreedharan Karuppoor

Shitong Sherry Zhu

Ke Ken Li

Tianxiang Su

Meng Qu

Adame Kante

Alex G Arzoumanidis

Larry Bernard

Vianney Bruned

Xiaoran Hu

Vivek Agarwal

Choon Sooi Tan

Sebastien Mannai

Guillaume Le Moing

Vahagn Hakopian

Ji Qi

An active learning framework is provided that employs a plurality of machine learning components that operate over iterations of a training phase followed by an active learning phase. In each iteration of the training phase, the machine learning components are trained from a pool of labeled observations. In the active learning phase, the machine learning components are configured to generate metrics used to control sampling of unlabeled observations for labeling such that newly labeled observations are added to a pool of labeled observations for the next iteration of the training phase. The machine learning components can include an inspection (or primary) learning component that generates a predicted label and uncertainty score for an unlabeled observation, and at least one additional component that generates a quality metric related to the unlabeled observation or the predicted label. The uncertainty score and quality metric(s) can be combined for efficient sampling of observations for labeling.

Active learning framework for machine-assisted tasks

Providing diagnostics or monitoring operation of a rod pressure includes using waves in production fluid produced by the rod pump may be used to determine one or more operating states of the rod pump. The one or more operating states of the rod pump may be used by a user to diagnose or monitor the operation of the rod pump.

Rod pump system diagnostics and analysis

Methods may include introducing a polymerizable composition containing a polycyclic monomer and a catalyst into a subterranean formation; and polymerizing the polymerizable composition in the presence of the catalyst in situ to form a polymer. Methods may also include lowering a wellbore tool into the subterranean formation, wherein the tool contains a first partition containing a polymerizable composition, and a second partition containing a catalyst; releasing the polymerizable composition from the first partition; releasing the catalyst from the second partition; contacting the polymerizable composition and the catalyst in a mixing region; and reacting the polymerizable composition and the catalyst in situ to form a polymer.

Methods for in situ formation of high glass transition temperature polymers

A method for sampling a downhole formation fluid includes pumping formation fluid into the flowline of a downhole sampling tool While pumping, a saturation pressure of the formation fluid is measured. The pumping rate is adjusted such that the fluid pressure in the flowline remains above a threshold saturation pressure.

Flowline saturation pressure measurements

A method for sampling a downhole formation fluid includes pumping formation fluid into the flowline of a downhole sampling tool, measuring a saturation pressure of the formation fluid in the flowline while pumping, and adjusting the pumping rate such that the fluid pressure in the flowline remains within a predetermined threshold above the measured saturation pressure.

Flowline saturation pressure measurement

A method includes pumping fluid from outside of a downhole tool through a flowline of the downhole tool with a pump. The method further includes taking a first plurality of measurements over time using at least one sensor and estimating a future saturation pressure of the fluid within the flowline at constant time increments via a processor based at least in part on the first plurality of measurements and a saturation pressure model. The method further includes adjusting the flowline pressure to maintain the pressure of the flowline above the estimated future saturation pressure.

Method to estimate saturation pressure of flow-line fluid with its associated uncertainty during sampling operations downhole and application thereof

A method for sampling a downhole formation fluid includes pumping formation fluid into the flowline of a downhole sampling tool. The method can also include measuring a saturation pressure of the formation fluid in the flowline while pumping. The method can also include adjusting the pumping rate such that the fluid pressure in the flowline remains within a predetermined threshold above the measured saturation pressure.

A method includes positioning a downhole acquisition tool in a well-logging device in a wellbore in a geological formation, where the wellbore or the geological formation, or both contain a reservoir fluid. The method includes performing downhole fluid analysis using a downhole acquisition tool in the wellbore to determine a plurality of fluid properties associated with the reservoir fluid. The method includes generating a nonlinear predictive control model representative of the plurality of fluid properties based at least in part on the downhole fluid analysis. The method includes adjusting the nonlinear predictive control model based at least in part on an output representative of a pump flow control sequence at a first time interval and the plurality of fluid properties.

Systems and methods for pump control based on non-linear model predictive controls

A method for sampling a downhole formation fluid that includes pumping formation fluid into the flowline of a downhole sampling tool. The method also includes measuring a saturation pressure of the formation fluid in the flowline while pumping, and adjusting the pumping rate such that the fluid pressure in the flowline remains within a predetermined threshold above the measured saturation pressure.

A downhole fluid testing system includes a downhole acquisition tool housing configured to be moved into a wellbore, where the wellbore contains fluid that comprises a native reservoir fluid of a geological formation and a contaminant. The system includes a pump to pump fluid through the downhole acquisition tool, a sensor configured to analyze portions of the fluid and obtain a fluid property the fluid from an optical spectrometer, including an optical density, and a controller coupled to the housing to receive a first plurality of measurements over time from the sensor, estimate a future saturation pressure of the fluid at specific time increments via a processor based in part on the first plurality of measurements and a saturation pressure model, and control a flow rate of the pump that causes the flow line pressure to remain above the estimated future saturation pressure plus a value of the associated uncertainty.

Systems and methods for pump control based on estimated saturation pressure of flow-line fluid with its associated uncertainty during sampling operations and application thereof

A method for analyzing the condition of a spectrometer is provided. In one embodiment, the method includes acquiring optical data from a spectrometer of a downhole tool during flushing of a flowline and selecting a data set from the acquired optical data. The method can also include estimating light scattering and optical drift for the spectrometer based on the selected data set and determining impacts of the estimated light scattering and optical drift for the spectrometer on measurement accuracy of a characteristic of a downhole fluid determinable through analysis of the downhole fluid using the spectrometer. Additional methods, systems, and devices are also disclosed.

Method for diagnosing optical spectrometers of downhole tools

A system and a method analyze fatigue damage of a bottom hole assembly ('BHA'), and more specifically, use a multi-scale approach for fatigue analysis of a BHA. Three length scales may be used in modeling of a BHA, namely the BHA scale, the component scale and the feature scale. Loading conditions for each collar/tool of the BHA may be determined, such as by use of a beam model, and may be applied to the finite element models for the collar/tool to determine the fatigue damage of each fatigue susceptible feature of each collar/tool. A cumulative fatigue damage of each critical feature may be determined, and the weakest component of the BHA may be identified. Prognostic and diagnostic implementation with well survey and drilling data may monitor fatigue damage of critical components of the BHA.

System and method for fatigue analysis of a bottom hole assembly

A method and apparatus for controlling fluidic torque in a downhole tool is provided. One or more rotatable components of the downhole tool comprise a deformable material, such as rubber or SMA, selectively deformable in response to the flow of fluid through the downhole tool. The rotatable components may include a rotor and/or a turbine of a generator in the downhole tool. Non-rotatable components, such as the stator of the generator, may also be deformable. The rotor, the stator, and/or turbine may comprise a deformable material capable of selectively deforming in response to the flow of drilling mud through the generator. The desired deformation and/or the desired torque may be controlled by adjusting the parameters of the components.

Growing community of inventors

Houston, TX, United States of America

Sepand Ossia