In the next 5-10 years, it is to be expected that normally unmanned production platforms (and eventually autonomous platforms) with a single yearly maintenance intervention will become the norm. This paper describes the basis for achieving this objective by integrating digital twins for the Process and Asset Performance/Maintenance domains.
The Process Twin described has been deployed in real-world field applications and provides the necessary level of reliability and accuracy to allow for closed-loop production optimization in real-time (i.e., optimized setpoints are pushed directly to the DCS or SCADA without manual verification or validation). The process model covers the entire production value chain, including reservoir, wells, risers, process facilities, sale of product, etc. Multiple constraints can be entered into the optimization engine, giving operators the ability to define a bespoke landscape for their optimization based on several key performance indicators (KPIs) related to production, process, economic, and environmental requirements.
The Asset Performance Twin complements the Process Twin by continuously generating the remaining Useful Life (RUL) of equipment. In the event that RUL does not match the timing of the next planned maintenance campaign, an alternative operational scenario can be calculated to extend the RUL. The Process Twin then optimizes production around this new constraint, with the ultimate objective being to minimize unplanned downtime and associated manual interventions.