Optimal Sensor Placement for Physics-Based Digital Twins
Operations and maintenance (O&M) account for approximately one third of offshore wind farm life-cycle costs. Up to 90% of this operational expenditure (OPEX) involves inspections by engineers and technicians at remote sites within a hostile marine environment. Minimizing the number of required inspections for offshore wind turbines (OWT) is essential to the long-term safety and affordability of the offshore wind energy industry. The technology necessary for minimizing inspections also opens the possibility for increased reliability of the electrical grid, improved resilience in the wake of extreme events, and extended OWT design life.
With availability of low-cost measurements on OWT structures, systems-level, physics-based digital twin (SPDT) technologies can provide actionable and tangible information to guide predictive maintenance and decision-making for optimal OWT asset management. As the United States prepares to construct over 28 GW of utility-scale offshore
wind power by 2035, the opportunity for advanced analytics to help shape U.S. O&M and performance-based safety standards is enormous. In addition to reducing operations and maintenance (O&M) costs over the long-term, our team estimates that SPDTs based on Bayesian data assimilation approach could help improve power production and prolong design life.