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

Accurate structural response prediction forms a main driver for structuralhealth monitoring and control applications. This often requires the proposedmodel to adequately capture the underlying dynamics of complex structuralsystems. In this work, we utilize a learnable Extended Kalman Filter (EKF),named the Neural Extended Kalman Filter (Neural EKF) throughout this paper, forlearning the latent evolution dynamics of complex physical systems. The NeuralEKF is a generalized version of the conventional EKF, where the modeling ofprocess dynamics and sensory observations can be parameterized by neuralnetworks, therefore learned by end-to-end training. The method is implementedunder the variational inference framework with the EKF conducting inferencefrom sensing measurements. Typically, conventional variational inference modelsare parameterized by neural networks independent of the latent dynamics models.This characteristic makes the inference and reconstruction accuracy weaklybased on the dynamics models and renders the associated training inadequate. Inthis work, we show that the structure imposed by the Neural EKF is beneficialto the learning process. We demonstrate the efficacy of the framework on bothsimulated and real-world structural monitoring datasets, with the resultsindicating significant predictive capabilities of the proposed scheme.

Neural Extended Kalman Filters for Learning and Predicting Dynamics of Structural Systems