Digitalization trends combined with advanced analytics solutions help organizations drive measurable progress in production optimization and emissions reduction.
Our last blog discussed trends in digitalization for the oil and gas industry including cloud technologies, digital twins, and simplicity at scale. In today’s edition, we will look more closely at how these trends combined with advanced analytics solutions help organizations drive measurable progress in production optimization and emissions reduction.
Advanced analytics enable teams to capture value
Before advanced analytics SaaS solutions, like Seeq, subject matter experts (SMEs) spent significant time manually collecting, cleansing, and analyzing their data for each individual asset. Today, as organizations progress toward digital maturity, teams have access to live data in one place, the capability to cleanse, contextualize, monitor, and model their equipment in ways they couldn’t before, and the ability to take advantage of asset hierarchies to automatically scale calculations to many like pieces of equipment. Two of the most common use cases for advanced analytics in the oil and gas space are production optimization and emissions reduction.
Production optimization can mean different things and target different technical use cases depending on which sector of the oil and gas space a company serves. At its core, production optimization is the practice of maximizing production, and therefore asset value, by ensuring all available assets are running optimally. For downstream, this could mean optimizing coke drum outages or deploying a heat exchanger preventative maintenance program to plan maintenance proactively. In the midstream, this could mean optimizing pipeline lockout pressures to reduce unnecessary shutdown events and increase production. Lastly, in the upstream, this could mean predicting sand uptake events that cause a well to go offline, intelligent alerting to identify rod pumps that need hot oil jobs, or plunger lift surveillance.
Equipped with a live connection to data from the field, teams can build monitoring programs that enable emissions reduction in several areas, including flaring, hydrocarbon leaks, excess water usage, and inefficient rotating equipment operations. For example, emissions reduction can result from efficiently identifying and eliminating flaring sources above baseline. Similarly, teams can build monitoring programs for NOx emissions on furnaces. By deploying a “what-if” prediction model across a fleet of furnaces, teams gain an understanding of projected emissions for different modes of operations. This enables the team to select the most optimal mode of operation based on the current feedstock of the facility.
As mentioned in our last blog post, the most common request after deploying an initial use case on one piece of equipment, such as production optimization or emissions reduction, is to scale it across hundreds or thousands of like pieces of equipment. To do this, teams require solutions that allow them to leverage existing asset hierarchies or build custom hierarchies based on the use case. Once the right template and hierarchy have been created, the calculation can be scaled. Applications that take advantage of cloud elasticity can scale the analytics performed before more efficiently.
Exception-based surveillance is also key in scaling analytics because it allows teams to prioritize resources where they are needed instead of spending unnecessary time monitoring assets that are operating within their normal bounds of operations.
Driving Measurable Progress
The success of any digital strategy or project hinges on the ability to prove value and impact to the bottom line. The two use cases below discuss how teams are proving this value using Seeq.
Marathon Oil deploys exception-based surveillance at scale
In a recent webinar, Mark Betts, IT Manager at Marathon Oil, discussed how Marathon Oil is monitoring thousands of wells with a finite number of resources. Historically, the teams were faced with a very cumbersome and manual data analysis process. This manual process combined with disparate systems and long lead times to get internal development resources led the organization to deploy a Digital Oilfield Project. The project is focused on providing automated, user-friendly time series analytics to SMEs, along with full autonomy to create intelligent alerts in Seeq. With more proactive alerts, the team can reduce unplanned outages, ultimately keeping production online longer. Additionally, the autonomy to create alerts within the integration hub empowers teams to work on new high-value problems and saves internal development resources.
Parkland Mitigates Flaring
Flares are safety devices present at many facilities to relieve tank pressure, prevent over-pressure events and manage unexpected operational upsets. Flaring above design purge requirements wastes valuable energy and adds to greenhouse gas emissions. At Conneqt 2022, Parkland Refinery discussed using Seeq to establish a baseline flaring metric and create a model to alert operations when flare loads crossed the baseline. This enabled the team to rapidly detect even the smallest of flaring sources, such as open valves at a sample station. The ability to identify baseline exceedances quickly and guide operations directly to the source saved CAD $0.6M in reduced flaring through the first five months of 2022.
The time is now
As demonstrated above, companies now see the importance and value that can be gained by deploying self-service, advanced analytics solutions. Digital transformation in oil and gas is no longer a choice but a requirement to remain competitive in cost of production.
If you are ready to learn more about how Seeq can empower your organization, please contact us to speak with one of our industry experts and schedule a demo today.