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/

Zendy Plus

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

Zendy Tools

Zendy Open

Polynomial chaos expansion (PCE) is a powerful surrogate model-basedreliability analysis method. Generally, a PCE model with a higher expansionorder is usually required to obtain an accurate surrogate model for somecomplex non-linear stochastic systems. However, the high-order PCE increasesthe number of labeled data required for solving the expansion coefficients. Toalleviate this problem, this paper proposes a consistency regularization-baseddeep polynomial chaos neural network (Deep PCNN) method, including thelow-order adaptive PCE model (the auxiliary model) and the high-orderpolynomial chaos neural network (the main model). The expansion coefficients ofthe main model are parameterized into the learnable weights of the polynomialchaos neural network, realizing iterative learning of expansion coefficients toobtain more accurate high-order PCE models. The auxiliary model uses a proposedconsistency regularization loss function to assist in training the main model.The consistency regularization-based Deep PCNN method can significantly reducethe number of labeled data in constructing a high-order PCE model withoutlosing accuracy by using few labeled data and abundant unlabeled data. Anumerical example validates the effectiveness of the consistencyregularization-based Deep PCNN method, and then this method is applied toanalyze the reliability of two aerospace engineering systems.

Consistency regularization-based Deep Polynomial Chaos Neural Network Method for Reliability Analysis