English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Heteroscedastic Gaussian process regression, based on the concept of chainedGaussian processes, is used to build surrogates to predict site-specific loadson an offshore wind turbine. Stochasticity in the inflow turbulence andirregular waves results in load responses that are best represented as randomvariables rather than deterministic values. Moreover, the effect of thesestochastic sources on the loads depends strongly on the mean environmentalconditions -- for instance, at low mean wind speeds, inflow turbulence producesmuch less variability in loads than at high wind speeds. Statistically, this isknown as heteroscedasticity. Deterministic and most stochastic surrogates donot account for the heteroscedastic noise, giving an incomplete and potentiallymisleading picture of the structural response. In this paper, we draw on therecent advancements in statistical inference to train a heteroscedasticsurrogate model on a noisy database to predict the conditional pdf of theresponse. The model is informed via 10-minute load statistics of theIEA-10MW-RWT subject to both aero- and hydrodynamic loads, simulated withOpenFAST. Its performance is assessed against the standard Gaussian processregression. The predicted mean is similar in both models, but theheteroscedastic surrogate approximates the large-scale variance of theresponses significantly better.

Probabilistic surrogate modeling of offshore wind-turbine loads with chained Gaussian processes