Digitalization of the aviation, automotive and other industries has fundamentally improved the way these industries manage production by leveraging automation in the manufacturing process. Automating the process improves efficiency by enabling management by exception—that is, focusing on how to mitigate or eliminate shortcomings rather than trying to manage every detail of the operation.

The digital oil field (DOF) aims to advance the way the oil and gas industry manages producing assets by leveraging automation and modeling of large volumes of real-time data to improve process efficiencies and output while reducing cost. Within the DOF, the end goal of integrated asset management is to accurately model hydrocarbon flow throughout its life cycle from the reservoir through pipelines using advanced petroleum engineering science. As in the automotive industry, automating the process can enable management by exception and make the industry more efficient—never more critical than in a low-market environment.

One area where DOF initiatives can play a major role is in production efficiency—the ratio of actual production to maximum production potential. Designed specifically for such initiatives, Baker Hughes’ FieldPulse software combines real-time production monitoring and model- based predictive analytics to increase production efficiency by enhancing the line of sight into asset performance. Actionable information is automatically generated through real-time modeling, which enables asset teams to manage complex fields or large well counts more efficiently. The software combines data connectivity, well models, asset key performance indicators (KPIs) and tailored workflows into a single platform that can be applied at scale across thousands of wells, deployed quickly and repeated across multiple assets (Figure 1).

The ability to apply this predictive platform on a large-well-count or multiple-asset scale without having to invest in new modeling licenses and engineering analysis can ultimately result in millions of dollars of savings in technology and time costs.

Managing for the life of the asset

Technological advances in the oil industry have led to the construction of more complex wells which, in turn, have generated more sources of information and more corresponding data that must be tracked and optimized. True DOF products are much more than aggregations of Big Data. Data analytics are being adopted rapidly across the industry as a means to improve performance by tracking and optimizing the wells within existing assets. However, data-driven analytics alone will not sustain higher production efficiency over the life of the asset. What is needed is improved use of models of the entire hydrocarbon production path, updated continuously with integration of field and well data.

Underperforming wells, unplanned shut-ins and inefficiencies within the supply chain can affect production efficiency and significantly reduce return on investment. Through insight into a field’s past, present and future using model-based analytics, a team with large numbers of wells can manage its asset proactively in real time. The model-based predictive analytics software uses the latest surveillance techniques to manage wells by exception, identify events and then trigger customizable workflows that integrate existing models, databases and work processes to allow the asset team to take action and minimize downtime.

Over time operational efficiency gains ultimately free engineering resources, which enable asset teams to proactively manage their expansive operations. Being proactive helps keep wells operating closer to their potential while lowering production losses and reducing service costs. Following this approach, improved efficiency is not necessarily linked to higher levels of investment. Instead, higher production efficiency is directly linked to quality of operations (Figure 2).

Asset-level scalability

The uniqueness of the DOF software described in this article is that it can apply model-based well surveillance at scale. As assets mature and the performance of the wells changes, traditional threshold (high/low)-based KPIs need to be constantly updated to reflect changes in the state of the reservoir. With large numbers of wells, threshold-based KPIs become difficult to maintain and are not applicable. At large scale it becomes necessary to use a tolerance- and volatility-based approach rather than a mere good/bad approach. Using dynamic volatility-based interpretation significantly reduces the need to modify KPIs. This reduces the number of false positive or “stale” KPIs, which often can hinder the adoption of large-scale surveillance products.

A unique built-in vendor-neutral nodal analysis engine makes it possible to use existing well models for real-time surveillance without having to incur additional costs for well modeling licenses. The predictive analytics software automatically and continually updates well models within entire assets with more insightful KPIs from real-time data. Running in real time and at scale enables critical operational workflows such as virtual metering, artificial lift diagnostics, model deviation, well test validation and automatic well model calibration.

Applying the models to perform basic scenario modeling significantly reduces the time required to make informed operational decisions. The nodal technology also supports multilateral and smart-well completions, enabling workflows such as zonal rate allocations and KPIs such as crossflow detection. As a result, any well deviating at a moment’s notice can be managed preventively rather than after the fact.

This DOF platform is one of the first fully integrated products to support smart well technology with a modeling workbench that allows engineers to model complex completions in highly visual single-well models. The software supports zonal rate allocations and can detect changes in zonal flowing conditions, inflow control valve (ICV) or choke changes, and potential crossflow issues. The models generated can be seamlessly applied to the real-time environment to monitor smart well performance.

Field case study

A Middle East oil company sought a DOF solution to enhance key production workflows using both modeland data-driven analytics. The software was deployed in less than three weeks for an asset that included two smart wells. The software was connected to the operator’s existing data sources. Existing well models were loaded into the application and repurposed for run-time use. Model-based workflows included rate estimation, zonal rate allocation, well test validation and model calibration. Data-driven workflows included automatic well test reporting and production target tracking, including a rate vs. allowable rate KPI.

Applying four different virtual metering techniques enabled real-time model-based rate estimations. Zonal allocations and ICV modeling also were performed on the smart wells. Well test records were generated from a tower-based multiphase flowmeter test unit. Data-driven logic was used to automatically detect whether wells were on test and whether the test was valid as well as to automatically record the results. The software automatically compared the test data with the well model and alerted the asset team to deviations.

The integrated nodal technology was used to recalibrate well models to match the well tests. Oil, gas and water estimates were then used to calculate the KPI to measure production targets vs. the allowable rates. The end objective for the operator is to apply the DOF software to improve production efficiency across 1,000 wells and, in the process, possibly save millions of dollars in costs.

Comments