Page 8 - MEOG Week 47.pdf
P. 8
MEOG ProJeCts & ComPanies MEOG
ADNOC signs up
Honeywell for predictive
maintenance work
uae
ABU Dhabi National Oil Co. (ADNOC) last week announced that it had agreed to enter a partnership with US services firm Honeywell for a 10-year predictive maintenance (PdM) project.
The move is part of ADNOC’s centralised predictive analytics and diagnostics (CPAD) programme, a significant contributor to the state firm’s 2030 smart growth strategy and Oil & Gas 4.0 initiatives.
The pair will employ Honeywell’s proprietary Forge Asset Monitor and Predictive Analytics solutions at ADNOC’s Panorama Digital Com- mand Center in Abu Dhabi.
In a statement to press, ADNOC said that the Honeywell solutions would “enable the central monitoring of up to 2,500 [pieces of] critical rotating equipment across all ADNOC Group companies”, presumably including assets man- aged both by ADNOC Offshore and ADNOC Onshore.
The state oil firm made mention of other digital transformation initiatives it has already rolled out, including the “smart data analytics Thamama Subsurface Collaboration Center and the use of AI-assisted value chain modelling, rock image pattern recognition technologies, and blockchain-based hydrocarbon accounting”.
The implementation of data analytics across the industry is spreading as understanding improves about its benefits.
A 2018 study by the UK Oil & Gas Technol- ogy Centre (OGTC) found that implementing data analytics technologies across the UKCS basin could result in additional production rev- enues worth more than $2bn per year.
That figure envisages a 25% improvement in reliability of critical systems and associated increased volumes and a 15-20% reduction in overall maintenance spend.
The 1% improvement in production effi- ciency seen in 2017 compared with 2016, which delivered an extra 12mn barrels of oil equivalent (boe) from the UKCS.
In November 2018, LR released a report on predictive analytics, which found that 57 of the world’s top 100 oil and gas firms were using, or had plans to use, predictive analytics.
It also found that those using predictive ana- lytics were benefiting by $325,000 per rig using machine learning to predict drill-bit locations, while companies in the eastern US were also sav- ing costs of $7mn on gas pipelines by predicting failures.
In addition to the massive production prize on offer, improved operational efficiency holds significant potential for cost reduction. By pre- dicting where and when a fault is likely to occur, maintenance can be optimised so as to reduce time costs and spare parts inventory.
In turn, this allows for work processes to be streamlined, asset support efficiency to be improved and for annual shutdowns to be optimised.
Machine learning is already being applied across aviation, power generation, nuclear, rail, renewables and various other industrial sectors for similar reasons.
The technology has matured further in these segments, with the benefits including improved earnings, significantly reduced maintenance costs and greater efficiency across assets and operations.
P8
w w w . N E W S B A S E . c o m
Week 47 27•November•2019
