公开(公告)号：US20250131284A1

公开(公告)日：2025-04-24

申请号：US18916824

申请日：2024-10-16

Applicant: Schlumberger Technology Corporation

Inventor： Valerian Guillot ,  Arvind Sharma ,  Mohamed Khalil Nafi ,  Jing Wu ,  Alexey Ruzhnikov

IPC: G06N3/096 ,  G06N3/0455 ,  G06N3/0475

Abstract: A method may include receiving a description of an event occurring at a wellsite; extracting a failure mode from the description using a fine-tuned large language model (LLM); identifying a matching failure mode from historical data processed using the fine-tuned LLM, where the matching failure mode is associated with one or more remedial actions that successfully resolved the matching failure mode; and outputting the one or more remedial actions for implementation at the wellsite.

公开(公告)号：US09977143B2

公开(公告)日：2018-05-22

申请号：US14846693

申请日：2015-09-04

Applicant: Schlumberger Technology Corporation

Inventor： Clement Kostov ,  Jing Wu ,  Debra M. Dishberger

IPC: G01V1/00 ,  G01V1/36

CPC classification number: G01V1/364 ,  G01V1/38 ,  G01V2210/324 ,  G01V2210/56

Abstract: One embodiment of the present disclosure includes a method for processing seismic data comprising the steps of receiving data representing seismic energy gathered from a formation by a plurality of seismic receivers, wherein the data include primary and multiple data. A copy of the received data is created and compensated to reduce amplitude attenuation effects due to transmission and absorption losses. A multiple prediction algorithm is applied to the received and compensated data to obtain a multiple data prediction. The multiple data prediction is subtracted from the received data to obtain primary data. The primary data is processed to reduce attenuation effects in the received data.