Deep reinforcement learning algorithm for wellbore cleaning across drilling operation

Publikationen: Beitrag in Buch/Bericht/KonferenzbandBeitrag in Konferenzband

Standard

Deep reinforcement learning algorithm for wellbore cleaning across drilling operation. / Keshavarz, Sahar; Elmgerbi, Asad; Thonhauser, Gerhard.
Fourth EAGE Digitalization Conference & Exhibition, Mar 2024, Volume 2024, p.1 - 5. Band 2024 2024.

Publikationen: Beitrag in Buch/Bericht/KonferenzbandBeitrag in Konferenzband

Harvard

Vancouver

Keshavarz S, Elmgerbi A, Thonhauser G. Deep reinforcement learning algorithm for wellbore cleaning across drilling operation. in Fourth EAGE Digitalization Conference & Exhibition, Mar 2024, Volume 2024, p.1 - 5. Band 2024. 2024 doi: 10.3997/2214-4609.202439018

Author

Keshavarz, Sahar ; Elmgerbi, Asad ; Thonhauser, Gerhard. / Deep reinforcement learning algorithm for wellbore cleaning across drilling operation. Fourth EAGE Digitalization Conference & Exhibition, Mar 2024, Volume 2024, p.1 - 5. Band 2024 2024.

Bibtex - Download

@inproceedings{d719d3323f8f4a36bb19fbc4c7fc0d29,
title = "Deep reinforcement learning algorithm for wellbore cleaning across drilling operation",
abstract = "We propose a novel framework for real-time drilling operation planning updates using deep reinforcement learning algorithm, enabling drilling process reactions to be automated. The framework includes a decision tree algorithm to represent the environment dynamic changes based on the imposed actions parallel to a Gaussian process algorithm to quantify the safe operating window in real-time. Combining these two algorithms leads to mounting a Markov Decision Process (MDP) environment for a decision-making system.We demonstrate the effectiveness of our framework by implementing an off-policy deep reinforcement learning algorithm, using a deep Q-learning network to create experiences, and employing synchronous updates on the agent. Given the essence of reinforcement learning, the framework can be efficiently implemented for on-the-spot decision-making, allowing the driller to receive an effective sequence of actions considering company policies.Our algorithm achieves state-of-the-art performance on weight-to-slip hole conditioning operation, a wellbore cleaning operation after drilling a stand before connecting to the next pipe. The performance evaluation exhibits its efficiency in real-time operation overhaul, eliminating non-value-added activities. Our framework thus opens the door for automating the process based on the operating parameters obtained in real-time",
author = "Sahar Keshavarz and Asad Elmgerbi and Gerhard Thonhauser",
year = "2024",
month = mar,
day = "25",
doi = "10.3997/2214-4609.202439018",
language = "English",
volume = "2024",
booktitle = "Fourth EAGE Digitalization Conference & Exhibition, Mar 2024, Volume 2024, p.1 - 5",

}

RIS (suitable for import to EndNote) - Download

TY - GEN

T1 - Deep reinforcement learning algorithm for wellbore cleaning across drilling operation

AU - Keshavarz, Sahar

AU - Elmgerbi, Asad

AU - Thonhauser, Gerhard

PY - 2024/3/25

Y1 - 2024/3/25

N2 - We propose a novel framework for real-time drilling operation planning updates using deep reinforcement learning algorithm, enabling drilling process reactions to be automated. The framework includes a decision tree algorithm to represent the environment dynamic changes based on the imposed actions parallel to a Gaussian process algorithm to quantify the safe operating window in real-time. Combining these two algorithms leads to mounting a Markov Decision Process (MDP) environment for a decision-making system.We demonstrate the effectiveness of our framework by implementing an off-policy deep reinforcement learning algorithm, using a deep Q-learning network to create experiences, and employing synchronous updates on the agent. Given the essence of reinforcement learning, the framework can be efficiently implemented for on-the-spot decision-making, allowing the driller to receive an effective sequence of actions considering company policies.Our algorithm achieves state-of-the-art performance on weight-to-slip hole conditioning operation, a wellbore cleaning operation after drilling a stand before connecting to the next pipe. The performance evaluation exhibits its efficiency in real-time operation overhaul, eliminating non-value-added activities. Our framework thus opens the door for automating the process based on the operating parameters obtained in real-time

AB - We propose a novel framework for real-time drilling operation planning updates using deep reinforcement learning algorithm, enabling drilling process reactions to be automated. The framework includes a decision tree algorithm to represent the environment dynamic changes based on the imposed actions parallel to a Gaussian process algorithm to quantify the safe operating window in real-time. Combining these two algorithms leads to mounting a Markov Decision Process (MDP) environment for a decision-making system.We demonstrate the effectiveness of our framework by implementing an off-policy deep reinforcement learning algorithm, using a deep Q-learning network to create experiences, and employing synchronous updates on the agent. Given the essence of reinforcement learning, the framework can be efficiently implemented for on-the-spot decision-making, allowing the driller to receive an effective sequence of actions considering company policies.Our algorithm achieves state-of-the-art performance on weight-to-slip hole conditioning operation, a wellbore cleaning operation after drilling a stand before connecting to the next pipe. The performance evaluation exhibits its efficiency in real-time operation overhaul, eliminating non-value-added activities. Our framework thus opens the door for automating the process based on the operating parameters obtained in real-time

UR - https://www.earthdoc.org/content/papers/10.3997/2214-4609.202439018

U2 - 10.3997/2214-4609.202439018

DO - 10.3997/2214-4609.202439018

M3 - Conference contribution

VL - 2024

BT - Fourth EAGE Digitalization Conference & Exhibition, Mar 2024, Volume 2024, p.1 - 5

ER -