公开(公告)号：US20240402383A1

公开(公告)日：2024-12-05

申请号：US18325277

申请日：2023-05-30

Applicant: Chevron U.S.A. Inc.

Inventor： Yula Tang ,  Yuanbo Lin ,  Suk Kyoon Choi ,  Jianlei Sun

IPC: G01V99/00 ,  E21B47/06

Abstract: A hybrid modeling approach incorporates both physics-based reservoir modeling and machine learning technique to capture dynamic behavior of unconventional wells. Shut-in bottom hole pressure for unconventional wells are simulated for use as proxy for reservoir pressure in unconventional reservoirs. Production parameters for unconventional wells (e.g., gas/oil ratio, water cut, flowing bottom hole pressure, shut-in bottom hole pressure, productivity index) are determined for use in controlling the operations of unconventional wells.

公开(公告)号：US20230097426A1

公开(公告)日：2023-03-30

申请号：US17936737

申请日：2022-09-29

Applicant: Chevron U.S.A. Inc.

Inventor： Jianlei Sun ,  Brandon Francis Hruby ,  Cory Layne Miller ,  Arvind Reddy Battula

IPC: G06N3/08 ,  G06N3/04

Abstract: A computing system includes a machine learning algorithm executing a machine learning model to predict a probability of a fracture driven interaction associated with a hydrocarbon well. The machine learning algorithm trains the machine learning model using well treatment pumping data, offset well production data, and well stage data. Feature extraction is performed on the pumping data, production data, and well stage data to produce a machine learning model that is used to predict the probability of a fracture driven interaction. The resulting machine learning model can be deployed for use in ongoing hydraulic fracturing operations to predict and reduce real-time fracture driven interactions.