Petronas Center of Excellence deploys cloud-based monitoring and maintenance

Aveva Predictive Analytics asset performance management underpins "P-MMPD", the Petronas machinery monitoring and prescriptive diagnostics program.

Microsoft reports* that Petronas has ‘saved $17.4 million in just 12 months’ by deploying Aveva predictive analytics in the Azure cloud. Petronas was at risk of unexpected rotary equipment failures which could potentially shut down an entire plant and lead to ‘catastrophic consequences’. To optimize equipment reliability, Petronas deployed Predictive Analytics (PA), a.k.a. Aveva’s asset performance management (APM) solution, following a six-month trial at four upstream platforms and two downstream plants.

Systems integrator Trisystem Engineering deployed the solution using an agile/sprint methodology leveraging Aveva’s ‘no-code’ artificial intelligence, customized for the energy industry. A templated approach saw the solution operating in under two months. PA ingests data from the PI System from OSIsoft (now part of Aveva), already deployed on Petronas’ critical assets.

The solution works in parallel with the ‘traditional’ plant control (DCS) system. Operation engineers use the DCS system to operate the plant, while maintenance and reliability engineers use PA for their daily tasks and monitor assets across the sites. In the first year of pilot implementation (2020) with 200 models deployed, PA gave 51 early warnings of impending equipment failures, including 12 high-impact warnings. These were resolved ahead of actual failure, significantly decreasing unscheduled downtime, saving an estimated $17.4 million. The solution is also said to improve collaboration between operators and specialists at the Petronas remote monitoring center, a.k.a. the Petronas Center of Excellence.

Azizol Kamaruddin, Petronas’ head of rotating equipment said, ‘The solution deliver early detection of anomalies and failure and captures years of our machine operation experience into a digital platform. We have integrated our own failure mode and effects analysis methodology into PA’.

Following the pilot, the system, branded as the Petronas machinery monitoring and prescriptive diagnostics (P-MMPD), is now running on an additional 10 plants with a total of 150 equipment trains. The company is rolling-out Aveva APM across its assets along with the cloud-based Aveva Unified Supply Chain to optimize its supply and distribution network, ‘cutting crude evaluation time and lowering margins’ (sic).

* In the Autumn 2021 Microsoft Technology Record.

Click here to comment on this article

Click here to view this article in context on a desktop

© Oil IT Journal - all rights reserved.