Exebenus and Ops Excellence sign partnership agreement to promote machine learning and automation solutions in Oman

Exebenus News

Exebenus AS and Ops Excellence LLC have signed a partnership agreement to promote machine learning and automation solutions to oil and gas operators in Oman, with particular focus on the Exebenus Current ML™ Real-Time ROP Optimization and Stuck Pipe machine learning agents. “The partnership with Exebenus gives us the opportunity to support our clients in making a step change in their digital transformation,” said Michael Schonewald, Ops Excellence Managing Director.

Machine learning agent significantly reduces drilling time on ultra-deepwater exploration well

Case studies

Location Gabon, West Africa Ultra deepwater Challenge Show that real-time rate of penetration (ROP) optimization can signifi cantly contribute to improving ROP, decreasing drilling time and reducing costs, even when an auto driller is used. Solution The agent was used by RTO engineers to provide the rig crew with real-time drilling parameter recommendations for optimizing…

Real-time predictions and risk awareness help prevent nonproductive time

Case studies

Location Magdalena River Valley Basin, South America Challenge Differential sticking is a known risk in the depleted reservoirs of the mature Magdalena River Valley basin, causing operators significant nonproductive time (NPT) during drilling and tripping operations. Solution Monitor real-time feed remotely using Exebenus Current ML. Provide risk awareness of situations that can cause stuck pipe…

ROP optimization agent reduces drilling time in offshore development side-track well

Case studies

Location Offshore, deepwater, Malaysia Challenge Improve formation insight and increase drilling performance in a clay and sandstone environment known to cause slow rate of penetration (ROP). Solution Field trial real-time ROP optimization agent in a side-track well section. Run stuck pipe hole cleaning agent to understand risk of increased cuttings in suspension and cave-ins. Results…

Digitalized Operation Procedures Provide Rig Automation System With Context To Manage Longer And Broader Sequences Of Activities

Abstract

SPE-208767-MS: Pourya Farmanbar, Anne Siw Berge, Olav Revheim, Alexander Chekushev, Serafima Schaefer, Exebenus. 

Abstracts: The exact definition of all types of activities in well construction, from spud to completion, is an area of great challenges for an automation system to function successfully in. In an operation plan, these activities can be categorized into three subgroups: standard and repetitive sub-activities, customized sub-activities, and manual sub-activities. A digitalized detailed operation procedure (DOP) provides the appropriate context by defining the machine-readable version of these activities.

Real-time Estimation Of Downhole Equivalent Circulating Density (ECD) Using Machine Learning And Applications

Abstract

SPE-208675-MS: Tim S. Robinson, Dalila Gomes, Exebenus;  Meor M. Hakeem Meor Hashim, M. Hazwan Yusoff, M. Faris Arriffin, and Azlan Mohamad, PETRONAS Carigali Sdn Bhd; Tengu Ezharudin, Eswadi Othman, Faazmiar Technology SDN BHD

Abstracts: Despite many drilling technology improvements during recent years, hole cleaning remains a significant challenge. The variation of equivalent circulation density (ECD) is a symptom of borehole instability. Therefore, the ability to accurately estimate ECD is a key consideration for preventing hole cleaning problems that may lead to a stuck pipe, and well pressure management more generally.

Unsupervised machine learning: A well planning tool for the future

Abstract

OMEA2022-78423: Peter Batruny, PETRONAS Carigali Sdn Bhd, Tim Robinson, Exebenus

Abstracts: In recent years, the industry has sought insights from abundant data generated by drilling operations. One of the key focus areas is the rate of penetration (ROP) which impacts costs directly, and emissions indirectly. Previous work has succeeded in predicting and optimizing ROP, however was limited to specific fields and small-scale applications. This limitation stems from unobserved information between different fields or operations that often impacts model usability. This paper provides a new way of well planning by leveraging the power of unsupervised machine learning to deliver higher drilling efficiency, lower costs, and less uncertainty.

Successful Development and Deployment of a Global ROP Optimization Machine Learning Model

Abstract

OTC-31680-MS: Timothy S. Robinson, Dalila Gomes, Exebenus, Peter Batruny, Meor M. Hakeem Meor Hashim, M. Hazwan Yusoff, M. Faris Arriffin, and Azlan Mohamad, PETRONAS Carigali Sdn Bhd

Abstracts: Drilling rate of penetration (ROP) is a major contributor to drilling costs. ROP is influenced by many different controllable and uncontrollable factors that are difficult to distinguish with the naked eye. Thus, machine learning (ML) models such as neural networks (NN) have gained momentum in the drilling industry. Existing models were either field-based or tool-based, which impacted the accuracy outside of the trained field. This work aims to develop one generally applicable global ROP model, reducing the effort needed to re-develop models for every application.