中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

21 records (took 0.015 seconds)

    MACHINE-LEARNING BASED FRACTURE-HIT DETECTION USING LOW-FREQUENCY DAS SIGNAL
    11.
    发明申请
    MACHINE-LEARNING BASED FRACTURE-HIT DETECTION USING LOW-FREQUENCY DAS SIGNAL 审中-公开

    公开(公告)号：US20200309982A1

    公开(公告)日：2020-10-01

    申请号：US16815378

    申请日：2020-03-11

    Applicant: ConocoPhillips Company

    Inventor： Ge Jin ,  Kevin Mendoza ,  Baishali Roy ,  Darryl G. Buswell

    IPC: G01V1/50 ,  E21B47/14 ,  G06N3/08 ,  G06N20/00 ,  G06F17/18 ,  G02B6/44

    Abstract: Various aspects described herein relate to a machine learning based detecting of fracture hits in offset monitoring wells when designing hydraulic fracturing processes for a particular well. In one example, a computer-implemented method includes receiving a set of features for a first well proximate to a second well, the second well undergoing a hydraulic fracturing process for extraction of natural resources from underground formations; inputting the set of features into a trained neural network; and providing, as output of the trained neural network, a probability of a fracture hit at a location associated with the set of features in the first well during a given completion stage of the hydraulic fracturing process in the second well.

    Low frequency distributed acoustic sensing hydraulic fracture geometry
    12.
    发明授权
    Low frequency distributed acoustic sensing hydraulic fracture geometry 有权

    公开(公告)号：US12173603B2

    公开(公告)日：2024-12-24

    申请号：US17741197

    申请日：2022-05-10

    Applicant: CONOCOPHILLIPS COMPANY

    Inventor： Ge Jin ,  Baishali Roy

    IPC: E21B49/00 ,  E21B43/26 ,  E21B47/113 ,  G01V1/20 ,  G01V1/22 ,  G01V1/42

    Abstract: Monitoring and diagnosing completion during hydraulic fracturing operations provides insights into the fracture geometry, inter-well frac hits and connectivity. Conventional monitoring methods (microseismic, borehole gauges, tracers, etc.) can provide a range of information about the stimulated rock volume but may often be limited in detail or clouded by uncertainty. Utilization of DAS as a fracture monitoring tool is growing, however most of the applications have been limited to acoustic frequency bands of the DAS recorded signal. In this paper, we demonstrate some examples of using the low-frequency band of Distributed Acoustic Sensing (DAS) signal to constrain hydraulic fracture geometry. DAS data were acquired in both offset horizontal and vertical monitor wells. In horizontal wells, DAS data records formation strain perturbation due to fracture propagation. Events like fracture opening and closing, stress shadow creation and relaxation, ball seat and plug isolation can be clearly identified. In vertical wells, DAS response agrees well with co-located pressure and temperature gauges, and illuminates the vertical extent of hydraulic fractures. DAS data in the low-frequency band is a powerful attribute to monitor small strain and temperature perturbation in or near the monitor wells. With different fibered monitor well design, the far-field fracture length, height, width, and density can be accurately measured using cross-well DAS observations.

    MACHINE LOGIC MULTI-PHASE METERING USING DISTRIBUTED ACOUSTIC SENSING DATA
    15.
    发明公开
    MACHINE LOGIC MULTI-PHASE METERING USING DISTRIBUTED ACOUSTIC SENSING DATA 审中-公开

    公开(公告)号：US20230160726A1

    公开(公告)日：2023-05-25

    申请号：US17983699

    申请日：2022-11-09

    Applicant: ConocoPhillips Company

    Inventor： Upendra K. Tiwari ,  Baishali Roy ,  Nan Ma ,  Ge Jin

    IPC: G01D5/353 ,  G01F1/661 ,  E21B47/07

    CPC classification number: G01D5/35361 ,  E21B47/07 ,  G01F1/661

    Abstract: A method for predicting fluid fractions is provided. The method includes building, from pressure, temperature, a fluid speed parameter, speed of sound, and fluid fractions of a first fluid flow, a machine learning model programmed to estimate fluid fractions of a fluid flow as a function of at least one Distributed Acoustic Sensing (“DAS”) fluid flow parameter and at least one physical characteristic of the fluid flow; receiving at least one DAS fluid flow parameter and the at least one physical characteristic of a second fluid flow; and determining, using the machine learning model, fluid fractions of the second fluid flow from at least the at least one DAS fluid flow parameter for the second fluid flow and the at least one physical characteristic of the second fluid flow.

    Low frequency distributed acoustic sensing
    19.
    发明授权
    Low frequency distributed acoustic sensing 有权

    公开(公告)号：US10458228B2

    公开(公告)日：2019-10-29

    申请号：US15453434

    申请日：2017-03-08

    Applicant: CONOCOPHILLIPS COMPANY

    Inventor： Ge Jin ,  Charles C. Mosher ,  Frank P. Filice ,  Kyle R. Krueger ,  Baishali Roy ,  Ali Tura ,  Dana M. Jurick

    IPC: E21B47/12 ,  G01V1/22 ,  E21B47/022 ,  G01H9/00 ,  E21B47/10 ,  G01K11/32 ,  G01V1/40

    Abstract: The invention relates to DAS observation has been proven to be useful for monitoring hydraulic fracturing operations. While published literature has shown focus on the high-frequency components (>1 Hz) of the data, this invention discloses that much of the usable information may reside in the very low frequency band (0-50 milliHz). Due to the large volume of a DAS dataset, an efficient workflow has been developed to process the data by utilizing the parallel computing and the data storage. The processing approach enhances the signal while decreases the data size by 10000 times, thereby enabling easier consumption by other multi-disciplinary groups for further analysis and interpretation. The polarity changes as seen from the high signal to noise ratio (SNR) low frequency DAS images are currently being utilized for interpretation of completions efficiency monitoring in hydraulically stimulated wells.

Patent Agency Ranking