Predictive operations program turns offshore point solutions into digital twin workflows
A Norway offshore operator linked condition monitoring, flow assurance, VR, and handheld tools into predictive workflows that improved safety, reduced deferments, and eased POB pressure.
Starting point
Norway upstream operator already had several advanced tools in place. Condition and performance monitoring for subsea systems (CPM), flow assurance tools (FAS), equipment condition monitoring systems, VR environments, and handheld field tools all existed. Each worked reasonably well on its own.
The problem was that these solutions were under used as a system. Maintenance and operations teams still spent much of their time reacting to events. Data from CPM, FAS, and condition monitoring did not consistently feed into forecasting and optimization workflows. VR and digital twin tools were used for specific tasks rather than as part of an integrated way of planning and executing work. Leadership wanted to move toward predictive operations and digital twin driven workflows that would improve safety, reduce deferments, and increase workforce productivity.
Approach
The operator brought in a digital strategy consulting team that included Bhuvan Maingi, now at Strathen Group, to frame a predictive operations program and a practical digital twin roadmap. The work started with a review of existing tools across TechnipFMC CPM, Schlumberger FAS, Bentley Nevada and TurboWatch, PaleBlue VR, WalkInside, COMOS handhelds, and collaboration platforms. The goal was not to buy new technology, but to connect what already existed into a coherent system of work.
First, the team mapped forecasting and optimization workflows that would link CPM, FAS, and condition monitoring into the production and maintenance planning cycle. This clarified how alerts, trends, and model outputs should move from these systems into decisions about set points, planned interventions, and deferral management. PO3 and PO4 became the anchors for predictive maintenance and optimization, with clear roles for each tool.
Next, a digital twin maturity model was defined. It set out a path from passive twin, where data is mainly visual, to contextual, dynamic, and eventually intelligent or full field twins. For each maturity step, the team specified what data and tag structures were required, what use cases would be unlocked, and what changes in ways of working would be needed. This gave operations a realistic sequence rather than a vague “build a digital twin” ambition.
The program then focused on execution tools and workforce enablement. PaleBlue VR and WalkInside were positioned as core capabilities for familiarization, scenario training, and permit planning. COMOS was deployed on handheld devices to let field staff access and update engineering information at the point of work. These tools were tied into twin enabled workflows, so that planning, training, and field execution all used consistent models and data.
Onshore collaboration patterns and people on board (POB) efficiency levers were designed alongside the technical changes. The team defined which tasks could shift onshore when twins and collaboration tools were in place, how onshore and offshore teams should share situational awareness, and how to schedule work to reduce unnecessary POB load. This included guidance on which inspections, reviews, and planning activities could be done remotely using VR and twin views.
Finally, the program built adoption playbooks, KPIs, and a benefit tracking approach. Playbooks detailed how different roles would use predictive tools, VR, twins, and handhelds in their day to day work. KPIs covered deferment, upset recovery times, safety indicators, tool time, and POB metrics. A light benefits tracking approach made it possible to show value early and often without creating a new administrative burden.
The real step change came from wiring existing tools into end to end workflows, not from buying another platform or rebadging digital twin as a concept.
Outcome
The predictive operations program gave Norway operations a clearer path out of reactive firefighting. With CPM, FAS, and condition monitoring feeding into agreed forecasting and optimization workflows, teams could intervene earlier and manage deferments more deliberately. Upsets were still unavoidable, but recovery was faster because relevant data and models were tied into decision making routines.
Digital twin maturity moved from an abstract ambition to a concrete roadmap. Operations knew which use cases would be enabled at each step, what data work was required, and how workforce practices would evolve. VR and twin environments became part of standard planning and training, improving safety and familiarity before workers went offshore or into complex tasks.
Field execution became more efficient as COMOS handhelds and twin driven planning reduced time spent searching for information or clarifying scope. Tool time improved because work packs, permits, and engineering context were more complete and consistent. Onshore collaboration patterns allowed some tasks to be moved off the installation, easing POB pressure without reducing oversight or quality.
Leaders had a structured view of how predictive operations, digital twins, and workforce productivity linked together. The program did not claim full automation or a perfect twin. Instead, it gave the operator a practical sequence of steps with clear benefits, governance, and measures of success. This made it easier to secure support, allocate resources, and adapt as technologies and priorities evolved.
Predictive operations are most credible when they start with the work and the workforce, then connect tools and twins to those realities instead of the other way around.
This work now guides how Strathen Group frames predictive operations and digital twin programs. Start with existing tools and workflows, define a realistic maturity path, and design changes in collaboration and execution that teams can adopt and measure.
