Methods and systems for determining well shut-in pressures of oil and gas well drilling

Patent metadata

Field	Value
Publication number	US-2025101865-A1
Application number	US-202318523838-A
Country	US
Kind code	A1
Filing date	Nov 29, 2023
Priority date	Sep 27, 2023
Publication date	Mar 27, 2025
Grant date	—

Abstract

Methods and systems for determining a well shut-in pressure of oil and gas well drilling are provided. The method comprises: obtaining, by a first processor, a basic parameter of a target oil and gas well, the basic parameter including at least one of a wellbore structure parameter, a well drilling fluid performance parameter, or a casing string parameter; obtaining, by the first processor, a pressure calculation model; and determining, by the first processor, a maximum well shut-in pressure during well drilling of the target oil and gas well based on the pressure calculation model and the basic parameter.

First claim

What is claimed is:

1 . A method for determining a well shut-in pressure of oil and gas well drilling, comprising:
obtaining, by a first processor, a basic parameter of a target oil and gas well, the basic parameter including at least one of a wellbore structure parameter, a well drilling fluid performance parameter, or a casing string parameter; obtaining, by the first processor, a pressure calculation model; and determining, by the first processor, a maximum well shut-in pressure during well drilling of the target oil and gas well based on the pressure calculation model and the basic parameter.

2 . The method according to claim 1 , further comprising:
determining, by the first processor, a recommended monitoring parameter and a recommended well drilling parameter based on the maximum well shut-in pressure and based on a wellhead pressure sequence and a bottomhole pressure sequence in a preset time period collected by a monitoring device; generating, by the first processor, a monitoring adjustment instruction based on the recommended monitoring parameter and sending the monitoring adjustment instruction to the monitoring device; and generating, by the first processor, a well drilling operation instruction based on the recommended well drilling parameter and sending the well drilling operation instruction to a second processor, the second processor being located at a terminal device.

3 . The method according to claim 2 , wherein the recommended well drilling parameter includes a recommended well shut-in time, and determining, by the first processor, a recommended well drilling parameter based on the maximum well shut-in pressure and based on a wellhead pressure sequence and a bottomhole pressure sequence in a preset time period collected by a monitoring device includes
obtaining, by the first processor, a parameter recommendation model based on preliminary training; and predicting, by the first processor, the recommended well shut-in time by processing the maximum well shut-in pressure, the wellhead pressure sequence, and the bottomhole pressure sequence based on the parameter recommendation model, the parameter recommendation model being a machine learning model.

4 . The method according to claim 3 , further comprising:
in response to receiving a feedback signal from the monitoring device and/or a well drilling operation device, sending, by the first processor, an update instruction to the second processor; and in response to receiving the update instruction, obtaining, by the second processor, an updated wellhead pressure sequence and an updated bottomhole pressure sequence from the monitoring device, processing the updated wellhead pressure sequence and the updated bottomhole pressure sequence, and determining an updated recommended well shut-in time based on the parameter recommendation model obtained from the first processor.

5 . The method according to claim 3 , wherein the parameter recommendation model includes:
a sequence feature extraction layer, an input of the sequence feature extraction layer including the wellhead pressure sequence and the bottomhole pressure sequence and an output of the sequence feature extraction layer including a fused sequence feature; and a prediction layer, an input of the prediction layer including the fused sequence feature and the maximum well shut-in pressure and an output of the prediction layer including the recommended well shut-in time, wherein the sequence feature extraction layer and the prediction layer are obtained through joint training.

6 . The method according to claim 5 , wherein different oil and gas wells correspond to different terminal devices, and different second processors and different monitoring devices corresponding to the different oil and gas wells are disposed in the different terminal devices; and
the second processors of the different terminal devices perform enhanced training on the parameter recommendation model based on well drilling feature information of the oil and gas wells corresponding to the different terminal devices.

7 . The method according to claim 6 , wherein the performing, by the second processors of the different terminal devices, enhanced training on the parameter recommendation model based on the well drilling feature information of the oil and gas well drillings corresponding to the different terminal devices includes:
for each of the different second processors and each of the different oil and gas wells corresponding to the each of the different second processors,
obtaining, by the second processor, actual well drilling data of the oil and gas well from a storage device as a training sample of the enhanced training;
obtaining, by the second processor, a predicted value by inputting the training sample into the parameter recommendation model obtained by the first processor; and
determining, by the second processor, a difference value based on the predicted value and a labeled value of the training sample and sending the difference value to the first processor;
constructing, by the second processor, a first loss function based on the difference values and updating the parameter recommendation model of the second processor based on the first loss function;
generating, by the first processor, a fused difference value by fusing different difference values obtained from the different second processors; and constructing, by the first processor, a second loss function based on the fused difference value and updating the parameter recommendation model of the first processor based on the second loss function.

8 . The method according to claim 1 , wherein the pressure calculation model is:

P
Cmax

=

min
⁢

{

P
1

=

0.8

(

min
⁢

{

P
T

,

P
R

}

)

;

Assignees

• Univ Southwest Petroleum

Inventors

• Zhang Jie
• Li Rongxin
• Li Cuinan
• Pang Ping
• Qing Yu
• Wang Liuyang
• Li Runze

Classifications

• E21B44/00

  Automatic control systems specially adapted for drilling operations, i.e. self-operating systems which function to carry out or modify a drilling operation without intervention of a human operator, e.g. computer-controlled drilling systems; Systems specially adapted for monitoring a plurality of drilling variables or conditions · CPC title

• E21B49/087

  Well testing, e.g. testing for reservoir productivity or formation parameters · CPC title

• E21B47/0025

  generating an image of the borehole wall using down-hole measurements, e.g. acoustic or electric · CPC title

• E21B47/06

  Measuring temperature or pressure · CPC title

• E21B2200/20

  Computer models or simulations, e.g. for reservoirs under production, drill bits · CPC title