中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

21 records (took 0.026 seconds)

    Method for Diagnosing Optical Spectrometers of Downhole Tools
    3.
    发明申请
    Method for Diagnosing Optical Spectrometers of Downhole Tools 有权
    诊断井下工具光谱仪的方法

    公开(公告)号：US20160178435A1

    公开(公告)日：2016-06-23

    申请号：US14577573

    申请日：2014-12-19

    Applicant: Schlumberger Technology Corporation

    Inventor： Kentaro Indo ,  Alexis Petit ,  Vivek Agarwal ,  Sepand Ossia ,  Julian J. Pop ,  Kai Hsu

    IPC: G01J3/02 ,  G01V8/02 ,  E21B47/01 ,  E21B49/08

    CPC classification number: G01J3/0297 ,  E21B47/01 ,  E21B49/087 ,  E21B49/10 ,  G01V8/02

    Abstract: 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.

    Abstract translation: 提供了一种分析光谱仪条件的方法。 在一个实施例中，该方法包括在冲洗流线期间从井下工具的光谱仪获取光学数据，并从所获取的光学数据中选择数据组。 该方法还可以包括基于所选择的数据集估计光谱仪的光散射和光漂移，并确定光谱仪的估计光散射和光漂移对通过井下分析可确定的井下流体特性的测量精度的影响 流体使用光谱仪。 还公开了附加的方法，系统和装置。

    Systems and Methods for Pump Control Based on Non-Linear Model Predictive Controls
    5.
    发明申请
    Systems and Methods for Pump Control Based on Non-Linear Model Predictive Controls 审中-公开

    公开(公告)号：US20170284198A1

    公开(公告)日：2017-10-05

    申请号：US15465733

    申请日：2017-03-22

    Applicant: Schlumberger Technology Corporation

    Inventor： Julian Pop ,  Vianney Bruned ,  Kentaro Indo ,  Sepand Ossia ,  Steven G. Villareal

    IPC: E21B49/10 ,  E21B47/06

    Abstract: 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.

    Active learning framework for machine-assisted tasks
    6.
    发明授权
    Active learning framework for machine-assisted tasks 有权

    公开(公告)号：US11960984B2

    公开(公告)日：2024-04-16

    申请号：US17279431

    申请日：2019-09-24

    Applicant: SCHLUMBERGER TECHNOLOGY CORPORATION

    Inventor： Nader Salman ,  Guillaume Le Moing ,  Sepand Ossia ,  Vahagn Hakopian

    IPC: G06N3/04 ,  G06N3/045 ,  G06N3/047 ,  G06N3/08 ,  G06N20/20

    CPC classification number: G06N3/047 ,  G06N3/045 ,  G06N3/08 ,  G06N20/20

    Abstract: 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.

Patent Agency Ranking