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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Aircraft industry is constantly striving for more efficient designoptimization methods in terms of human efforts, computation time, and resourceconsumption. Hybrid surrogate optimization maintains high results quality whileproviding rapid design assessments when both the surrogate model and the switchmechanism for eventually transitioning to the HF model are calibrated properly.Feedforward neural networks (FNNs) can capture highly nonlinear input-outputmappings, yielding efficient surrogates for aircraft performance factors.However, FNNs often fail to generalize over the out-of-distribution (OOD)samples, which hinders their adoption in critical aircraft design optimization.Through SmOOD, our smoothness-based out-of-distribution detection approach, wepropose to codesign a model-dependent OOD indicator with the optimized FNNsurrogate, to produce a trustworthy surrogate model with selective but crediblepredictions. Unlike conventional uncertainty-grounded methods, SmOOD exploitsinherent smoothness properties of the HF simulations to effectively expose OODsthrough revealing their suspicious sensitivities, thereby avoidingover-confident uncertainty estimates on OOD samples. By using SmOOD, onlyhigh-risk OOD inputs are forwarded to the HF model for re-evaluation, leadingto more accurate results at a low overhead cost. Three aircraft performancemodels are investigated. Results show that FNN-based surrogates outperformtheir Gaussian Process counterparts in terms of predictive performance.Moreover, SmOOD does cover averagely 85% of actual OODs on all the study cases.When SmOOD plus FNN surrogates are deployed in hybrid surrogate optimizationsettings, they result in a decrease error rate of 34.65% and a computationalspeed up rate of 58.36 times, respectively.

SmOOD: Smoothness-based Out-of-Distribution Detection Approach for Surrogate Neural Networks in Aircraft Design