A method is developed to identify load-driving events based on filtered flow acceleration, regardless of the event-generating mechanism or specific temporal signature. Low-pass filtering enables calculation of acceleration statistics per characteristic turbine response time; this circumvents the classic problem of small-scale noise dominating observed accelerations or extremes, while providing a way to deal with different turbines and controllers. Not only is the flow acceleration physically meaningful, but its use also removes the need for de-trending. Through consideration of the 99th percentile (P99) of filtered acceleration per each 10 min period, we avoid assumptions about distributions of fluctuations or turbulence and derive statistics of load-driving accelerations for offshore conditions from "fast" (10 and 20 Hz) measurements spanning more than 15 years. These statistics depend on low-pass-filter frequency (the reciprocal of turbine response time) but vary in a nontrivial manner with height due to the influence of the atmospheric boundary layer's capping inversion, as well as the surface.We find long-term probability distributions of 10 min P99 of filtered accelerations, which drive loads ranging from fatigue to ultimate; this also includes joint distributions of the P99 with the 10 min mean wind speed (U) or standard deviation of horizontal wind speed fluctuations (sigma s). The long-term mean and mode of the P99 of streamwise acceleration, conditioned on sigma s and U, are found to vary monotonically with sigma s and U, respectively; this corroborates the International Electrotechnical Commission (IEC) 61400-1 prescriptions for fatigue design load cases. An analogous relationship is also seen between lateral (directional) acceleration and the standard deviation of direction, particularly for submesoscale fluctuations.The largest (extreme) P99 of filtered accelerations are seen to be independent of 10 min mean speeds and have only limited connection to 10 min sigma s; traditional 10 min statistics cannot be translated into extreme load-driving acceleration statistics. From measurement heights of 100 and 160 m, time series of the 10 most extreme acceleration events per 1 m s-1 wind speed bin were further investigated; events of diverse character were found to arise from numerous mechanisms, ranging from nonturbulent to turbulent flow regimes and also depending on the filter scale. Different behaviors were noted in the lateral and streamwise directions at different heights, although a small fraction of these events exhibited extreme amplitudes for both horizontal acceleration components and/or were observed at both heights within a given 10 min window. Via fits to the tails of the marginal P99 distributions, curves of offshore extreme P99 of filtered acceleration for return periods up to 50 years were calculated for three characteristic turbine response times (filter scales) at the observation heights of 100 and 160 m.To drive aeroelastic simulations, Mann-model parameters were also calculated from the time series of the most extreme events, allowing constrained simulations embedding the recorded events. To facilitate this for typical industrial measurements that lack three-dimensional anemometry, a new technique for obtaining Mann-model turbulence parameters was also created; this was employed to find the parameters corresponding to the background flow behind the extremes identified and their time series. Further, a method was created to use the extreme acceleration statistics in stochastic simulations for application to loads, including interpretation within the context of the IEC 61400-1 standard. Preliminary parallel work has documented aeroelastic simulations conducted using the extreme event time series identified here, as well as Monte Carlo simulations based on the extreme statistics and new method for stochastic generation of acceleration events.
