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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Data-driven method for Structural Health Monitoring (SHM), that mine thehidden structural performance from the correlations among monitored time seriesdata, has received widely concerns recently. However, missing datasignificantly impacts the conduction of this method. Missing data is afrequently encountered issue in time series data in SHM and many otherreal-world applications, that harms to the standardized data mining anddownstream tasks, such as condition assessment. Imputation approaches based onspatiotemporal relations among monitoring data are developed to handle thisissue, however, no additional information is added during imputation. Thispaper thus develops a robust method for damage identification that considersthe missing data occasions, based on long-short term memory (LSTM) model anddropout mechanism in the autoencoder (AE) framework. Inputs channels arerandomly dropped to simulate the missing data in training, and reconstructionerrors are used as the loss function and the damage indicator. Quasi-staticresponse (cable tension) of a cable-stayed bridge released in 1st IPC-SHM isemployed to verify this proposed method, and results show that the missing dataimputation and damage identification can be implemented together in a unifiedway.

A robust deep learning-based damage identification approach for SHM considering missing data