Oman’s national petroleum investment company OQ is working with Phazero, a local computer engineering company, to develop artificial intelligence software that will predict component malfunctions in the country’s refineries before they happen.
The project to develop the new software has the potential to create significant cost savings for OQ, according to Abdullah al-Shaksy, co- founder and CEO of Phaze Ventures, which owns a stake in Phazero. “Predictive maintenance is a big area of development now,” he said.
Al-Shaksy said that by being able to predict when components will malfunction, OQ will be able to create a more efficient maintenance schedule in which individual components can be effectively targeted and replaced just before they become vulnerable to failing.
The software will allow OQ to focus maintenance efforts on the components that are most likely to break down and will lead to shorter periods of downtime, according to Al-Shaksy.
“OQ will be able to use the software and its historical data sets to figure out what is likely to go wrong and when a malfunction is likely to happen,” he said.
“Phazero is working with OQ’s internal teams and supplementing their efforts to develop predictive maintenance software.”
The predictive maintenance software will largely rely on monitoring devices that are already installed inside OQ’s refineries.
Currently, OQ uses refinery turnarounds to make sure its downstream facilities are well maintained.
A refinery turnaround is a planned, periodic shutdown of one or more refinery processing units, or the entire refinery, to perform maintenance, inspection and repairs, and to replace process materials and equipment that have worn out or broken.
Generally, in the oil sector, routine turnarounds on key fuel production units are planned for every three to five years.
They may involve one to two years of advance planning (sometimes more when major processing or equipment changes are needed) using dedicated teams from the company, as well as outside contracting and engineering firms.
While the objective is to minimise the time a unit is offline, the turnaround can result in a unit being offline for several weeks to several months.
