Processing

Please wait...

Settings

Settings

Goto Application

1. WO2021080691 - SYSTEMS AND METHODS FOR TRAINING A WELL MODEL TO PREDICT MATERIAL LOSS FOR A PIPE STRING WITHIN A BOREHOLE

Publication Number WO/2021/080691
Publication Date 29.04.2021
International Application No. PCT/US2020/048796
International Filing Date 31.08.2020
IPC
E21B 41/00 2006.01
EFIXED CONSTRUCTIONS
21EARTH OR ROCK DRILLING; MINING
BEARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
41Equipment or details not covered by groups E21B15/-E21B40/95
E21B 47/10 2006.01
EFIXED CONSTRUCTIONS
21EARTH OR ROCK DRILLING; MINING
BEARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
47Survey of boreholes or wells
10Locating fluid leaks, intrusions or movements
E21B 47/12 2006.01
EFIXED CONSTRUCTIONS
21EARTH OR ROCK DRILLING; MINING
BEARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
47Survey of boreholes or wells
12Means for transmitting measuring-signals or control signals from the well to the surface, or from the surface to the well, e.g. for logging while drilling
E21B 47/26 2012.01
EFIXED CONSTRUCTIONS
21EARTH OR ROCK DRILLING; MINING
BEARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
47Survey of boreholes or wells
26Storing data down-hole, e.g. in a memory or on a record carrier
CPC
G01V 99/005
GPHYSICS
01MEASURING; TESTING
VGEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
99Subject matter not provided for in other groups of this subclass
005Geomodels or geomodelling, not related to particular measurements
G06F 2113/08
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
2113Details relating to the application field
08Fluids
G06F 2113/14
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
2113Details relating to the application field
14Pipes
G06F 30/27
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
30Computer-aided design [CAD]
20Design optimisation, verification or simulation
27using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
G06N 20/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
Applicants
  • LANDMARK GRAPHICS CORPORATION [US]/[US]
Inventors
  • KROCZKA, Sebastian
  • SOUZA, Welton Danniel
  • BADIS, Chafaa
Agents
  • ROSE, Collin
  • GOODE, Matthew
Priority Data
62/923,72921.10.2019US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) SYSTEMS AND METHODS FOR TRAINING A WELL MODEL TO PREDICT MATERIAL LOSS FOR A PIPE STRING WITHIN A BOREHOLE
(FR) SYSTÈMES ET PROCÉDÉS D'APPRENTISSAGE D'UN MODÈLE DE PUITS PERMETTANT DE PRÉDIRE UNE PERTE DE MATÉRIAUX D'UN TRAIN DE TIGES À L'INTÉRIEUR D'UN TROU DE FORAGE
Abstract
(EN)
A method for training a well model to predict material loss for a pipe string having a wall thickness and located within a borehole. The method may include measuring the wall thickness of a first pipe string at locations axially along the first pipe string with a logging tool at a first time. The method may also include measuring the wall thickness of the first pipe string at the locations with the logging tool at a second time. The method may further include training a first well model based on a machine learning ("ML") algorithm to predict a predicted amount of material loss in the future for the first pipe string at a selected location using the wall thickness measurements at the first and second times and well operating condition information related to the first pipe string.
(FR)
La présente invention concerne un procédé d'apprentissage d'un modèle de puits permettant de prédire une perte de matériaux d’un train de tiges présentant une certaine épaisseur de paroi et situé à l'intérieur d'un trou de forage. Le procédé peut consister à mesurer à un premier moment l'épaisseur de la paroi d'un premier train de tiges à des emplacements situés axialement le long du premier train de tiges à l'aide un outil de diagraphie. Le procédé peut également consister à mesurer à un second moment l'épaisseur de la paroi du premier train de tiges au niveau des emplacements à l'aide de l'outil de diagraphie. Le procédé peut également consister à former un premier modèle de puits sur la base d'un algorithme d'apprentissage automatique (« ML ») afin de prédire une quantité prédite de perte de matériaux future du premier train de tiges à un emplacement sélectionné à l'aide des mesures d'épaisseur de la paroi au premier et au second moments et d'informations sur l'état de l'exploitation du puits concernant le premier train de tiges.
Also published as
Latest bibliographic data on file with the International Bureau