US2025179904A1PendingUtilityA1
Computer implemented method for real-time lwd profile prediction in the intervals from the drill tip to the limit of the depth profile offsets
Assignee: PETROLEO BRASILEIRO SA PETROBRASPriority: Dec 2, 2023Filed: Dec 2, 2024Published: Jun 5, 2025
Est. expiryDec 2, 2043(~17.3 yrs left)· nominal 20-yr term from priority
Inventors:Plinio Cancio Rocha Da Silva JuniorWillian Andrighetto TrevizanPaulo Romero Zanconato PintoLucas Abreu Blanes De Oliveira
E21B 2200/22E21B 2200/20E21B 49/005E21B 45/00
57
PatentIndex Score
0
Cited by
0
References
0
Claims
Abstract
The present invention relates to a computer implemented method, the main objective of which is to predict real-time LWD profiles in the intervals from the drill tip to the limit of the profile offsets. This becomes a methodology that serves as yet another input to improve assertiveness in decision-making during well drilling operations.
Claims
exact text as granted — not AI-modified1 . A computer implemented method for real-time LWD profile prediction in the intervals from a drill tip to a limit of depth profile offsets, comprising:
(a) importing first data of LWD profiles in depth from an available first database; (b) importing second data of drilling parameters in time from an available second database; (c) applying filters to drilling parameters in real-time by removing records with ROP, WOB, RPM and torque values less than or equal to zero; (d) converting second data in time to depth by calculating statistical attributes of said drilling parameters in time contained in specific intervals and having constant depth spacing; (e) combining said drilling parameters converted to depth in step (d) with said LWD profile data imported in step (a) using depth as a reference; (f) training machine learning models, based on supervised regressions, for each said LWD profile with the first database above each respective depth offset; (g) performing inferences to predict each said LWD profile with its respective model using training features in an interval corresponding to the current depth of a drill up to the respective offset limits; (h) periodically checking whether there has been progress in drilling, if so, repeating step (f) by training the models with any new data and, subsequently, step (g), performing new inferences with respect to the new data; and (i) sending the results of each new prediction to a third database, the results being used by a visualization tool and made available to a user.
2 . The computer implemented method according to claim 1 , wherein the target LWD profiles comprise layers (labels) in step (f).
3 . The computer implemented method according to claim 1 , wherein in step (g) characteristics of statistical attributes of drilling parameters comprise torque, weight on drill (WOB), rate of penetration (ROP), revolutions per minute (RPM), MSE (mechanical specific energy), pumping pressure (SPP), drilled phase, drill type, drill run, or combination thereof.
4 . A non-transitory computer-readable storage medium comprising instructions stored thereon and, when read by a computer, cause the computer to execute the steps of the method as defined by claim 1 .Join the waitlist — get patent alerts
Track US2025179904A1 — get alerts on status changes and closely related new filings.
We store only your email — no account needed. See our privacy policy.