please enter please select

Applying big data to asset acquisitions

Project Summary

Offshore infrastructure – platforms containing large amount of complex process equipment – frequently change hands. Some installations have been acquired and their process are changed and adapted multiple times since being installed. Understanding the health, condition and level of operational risk in such a facility is critical for a new owner in order to ensure safe and efficient ongoing operations as soon as possible.

OPEX developed a data-driven assurance service for operators. The goal was to provide a quantitative assessment of health, condition and level of operational risk of an asset through the creation of an operational performance baseline. The baseline could then be used to identify and quantify any key historical operational risks to then guide how best to operate the asset going forward.

The Asset Diligence service applies predictive technologies to data, covering both operations and maintenance. Working with data scientists and subject matter experts, Asset Diligence spots any breakdowns in the relationship between data points to form a measure of instability in the process and equipment performance. In other words – they’re able to quickly look at how it should be working and compare that to what the data is telling them.

This process involves identifying the key statistical relationships between all the data points within a critical system and recording any breakdowns in these relationships. For each critical system, which could be a compressor or pump, instability is measured and used as an indication of system performance over time. This insight into process instability can then be correlated with more conventional information, such as downtime and more detailed maintenance histories, to provide fresh insight into system vulnerabilities, as well as threats and opportunities.


Industry value:
Currently, operational due diligence is a costly, lengthy and resource heavy activity that can only identify key financial exposure (inventory size, etc.). To manage uncertainty associated with critical systems condition, new buyers may be required to undertake a full overhaul at considerable impact to production revenue and maintenance cost.

Key results:
The service was trialled on data from assets US-based oil and gas operator Cantium. Key ‘production critical’ systems were identified and modelled using statistical methods and then compared against OEM (original equipment manufacturer) equipment performance data. In this case, the overall maintenance execution was found to be good, with high rates of preventative maintenance leading to decreases in production losses and system instability. Based on the findings of the Asset Diligence assessment, recommendations could be made to either maintain or improve maintenance levels.

The solution provides quick and cost-effective visibility of the actual health of the key production assets. This allows new buyers across the UKCS basin to accurately forecast their operational risk and provide the opportunity to take decisions based on facts/put appropriate mitigating actions in place. The financial impact is difficult to quantify precisely, but it’s expected that once the service is applied across the UKCS, it could generate substantial savings by the:

  • Prevention of unnecessary strip downs/overhauls/maintenance
  • Minimising trips, planned or unplanned shut downs as a result of better information
  • Prevention of unnecessary equipment change-out

Lessons learned / Next steps:
The availability of legacy asset operational data from previous owners can be limited. Getting this data and analysing it also must be done within a meaningful timeframe of an acquisition process to have the most meaningful impact.


Related

Let's work together

"Required" indicates required fields

My name isRequired
My name is
This field is for validation purposes and should be left unchanged.