Skip to content

Transforming Offshore Operations to Control Room Operations - An ENERGYai Initiative

Nov 2026 · Abu Dhabi International Petroleum Exhibition & Conference (ADIPEC)
Oil and Gas Production Techniques

Abstract

Abstract Recognizing the fact that Artificial Intelligence (AI) is a pivotal driver of ADNOC's ongoing ENERGYai vision and transformation, a Team in ADNOC Offshore re-evaluated their critical routine operations and successfully developed ideas to convert these physical operations in Offshore into autonomous processes managed from the Control Room. This shift not only saves on logistics and reduces GHG emissions but also eliminates human exposure to hazards. Further, these initiatives demonstrate that implementing AI in the oil and gas industry doesn't always have to be complex. By taking a rational approach of re-examining and remodeling routine operations, we can unlock AI's potential. In line with ADNOC Offshore priorities on embracing Artificial Intelligence, a team in ADNOC Offshore presented a groundbreaking idea during 2025 to convert all Downhole Safety Valve Physical PMs to an Autonomous operation from Control Room. The idea was not only virtually evaluated but also successfully piloted & implemented in Field. As part of the Preventive Maintenance of HSECES Equipment, Periodic Testing/PM is an essential part of ensuring the Integrity of Downhole Safety Valves (a Well HSE Critical Equipment).It is carried out with 6-monthy or yearly frequency with above 4700 activities (work Orders) to be completed per year. However, attending these PMs physically poses huge challenges; such as (i)Human Exposure(ii) GHG emissions (iii) High Cost (iv) Weather restrictions may cause delays. Hence, to convert this Offshore Operations to Control Room, a task force was formed within ADNOC Offshore who worked rigorously for almost 6- months evaluating all P&IDs, cause and effect diagrams, HSE consequences and finally conducted successful test during 2025 in Offshore. The whole operation of DHSV PM/Test was programmed in DCS and SCADA system so that all the steps can be performed without human intervention (including Control Line and related equipment) without any presence of personnel at site. ADNOC offshore requires 4700 DHSV PMs per year (with existing well inventory). This demands 28200 manhours annually. Hence, with this initiative(converting physical operation into autonomous one) would save these manhours equivalent toaround$5.55 Million per year2)Sustainability: Total GHG reduction per year due to initiative = 2237 TonsCO2 Eq(since, One imperial Gallon of Diesel=0.0119 tons CO2eq emissions and Total transportation Hours required per year to perform 4700 PMs = 2350 hours)3)100% HSE - Zero Human Exposure:4) Non-Weather Dependent Operation - No delays in performing critical PMs. This first of its kind initiative is not only new within ADNOC Group of companies but also for the whole region and with great pride, we can say that all steps, from visualizing the idea to execution, were carried out purely by ADNOC Offshore employees (A model initiative for other organizations to adopt).

View source

Similar papers

#artificial intelligence Conference Open access Jun 2018

Gibson Env: Real-World Perception for Embodied Agents

This paper investigates developing real-world perception for active agents, proposes Gibson Environment for this purpose, and showcases a set of perceptual tasks learned therein.

F. Xia, Amir Zamir, Zhi-Yang He et al. · 1,069 citations · ⚡112
#artificial intelligence Open access May 2023

Evaluating the Performance of Large Language Models on GAOKAO Benchmark

GAOKAO-Bench is introduced, an intuitive benchmark that employs questions from the Chinese GAOKAO examination as test samples, including both subjective and objective questions that contribute a robust evaluation benchmark for future large language models and offers valuable insights into the advantages and limitations...

Xiaotian Zhang, Chun-yan Li, Yi Zong et al. · 216 citations · ⚡17

KTO: Model Alignment as Prospect Theoretic Optimization

This work proposes a HALO that directly maximizes the utility of generations instead of maximizing the log-likelihood of preferences, and suggests that the best loss depends on the inductive biases most appropriate for a given setting, an oft-overlooked consideration.

Kawin Ethayarajh, Winnie Xu, Niklas Muennighoff et al. · 195 citations · ⚡28
#artificial intelligence Open access Jul 2024

Gender, Race, and Intersectional Bias in Resume Screening via Language Model Retrieval

This work investigates the possibilities of using LLMs in a resume screening setting via a document retrieval framework that simulates job candidate selection and finds that the MTEs are biased, significantly favoring White-associated names in 85% of cases and female-associated names in only 11.1% of cases.

Kyra Wilson, Aylin Caliskan · 131 citations · ⚡8
#artificial intelligence Review Nov 2024

How to Build a Quantum Supercomputer: Scaling from Hundreds to Millions of Qubits

This work shows that orders of magnitude enhancement in performance could be obtained by a combination of hardware improvements and tight quantum-HPC integration and introduces high-performance architectures for quantum-probabilistic computing with custom-designed accelerators to tackle today's industry-scale classical...

Masoud Mohseni, Artur Scherer, K. Johnson et al. · 121 citations · ⚡9

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.