No abstract

No abstract

This paper describes developments in the fatigue counter methodology and how digitalization is used to deliver valuable online technical service. The fatigue counter methodology consists of using a combination of autonomous and online motion response sensors directly installed on the riser and interfacing Floating Production Storage and Offloading vessel (FPSO) structures. The measured environmental data, FPSO and riser response data are utilized in a machine learning (ML) environment to build more realistic riser response and fatigue prediction models. The results of this is significant reduction in uncertainties, enabling live riser fatigue predictions and providing a basis for life extension and improved accuracy of riser and vessel response analysis. As there is a need to run some risers at higher pressures, the optimum time periods for such high-pressure service can be found without compromising the flexible riser service life. A recent field case is presented whereby the fatigue counter ingest, process and present data on a modern digital infrastructure. The full service was setup based on available onboard sensors including a 6 degree of freedom (DOF) vessel motion response unit (MRU), temperature and pressure transmitters and forecast model for weather. Input and output data are shared through well documented and safe application program interfaces (APIs) between the operating company and the fatigue counter 3rd party service. The operating company receives live updates of accumulated fatigue damage and remaining service life. This enables the operating company to build contextualized and high value dashboards presented on their organizational front end. The paper illustrates the power and applicability of combining modern numerical methods with digital techniques, made possible by streaming input and output data on safe and well documented APIs.