The Challenge

One of VROC's clients is an Oil and Gas operator. Their offshore platform is equipped with two primary Turbine Compressors operating in parallel. The client wanted to predict potential undesirable performance, so that they could intervene early to avoid shutdowns.

The Solution

The offshore platform is actively using VROC's no-code AI Platform, OPUS. Historical data has been ingested into the platform, and live operational data is continuously ingested, this way any models created use live data to predict future outcomes.

A Time-to-Failure (TTF) model was trained in order to predict potential Turbine Compressors (TC) undesirable performance by using TC discharge pressure when it reduces below than 9000 kPag (pre-alarm). However, the actual trip limit for pressure low low is at 5500 kPag.

The Results

The Time to Failure (TTF) model, which was trained by incorporating historical data, warned the operation team of the increase of undesirable performance probabilities, prior to a hiccup. Multiple wells tripped at the client's remote platforms, these were identified as the main root cause of the issue, causing low gas flowrate to compressors. Due to the monsoon season and difficulties of dispatching crew onboard to the remote platform, the low flow issue remain unsolved until the crew landed onboard and flowed back the wells.

Sharing the TTF trending, the offshore team was able to closely monitor the ASV %Opening, Compressor discharge control valve PCV %Opening, and gas flowrate trending, to avoid a Turbine Compressor trip on low gas flowrate.

Get started with VROC today

Ready to embark on a pilot project or roll-out the innovation enterprise wide? Perhaps you need assistance integrating your systems or accessing your data? We have a solution to help you as you progress through your digital transformation.