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

Conventional damage localization algorithms used in ultrasonic guidedwave-based structural health monitoring (GW-SHM) rely on physics-definedfeatures of GW signals. In addition to requiring domain knowledge of theinteraction of various GW modes with various types of damages, they also sufferfrom errors due to variations in environmental and operating conditions (EOCs)in practical use cases. While several machine learning tools have been reportedfor EOC compensation, they need to be custom-designed for each combination ofdamage and structure due to their dependence on physics-defined featureextraction. In this work, we propose a CNN-based automated feature extractionframework coupled with Gaussian mixture model (GMM) based EOC compensation anddamage classification and localization method. Features learnt by the CNNs areused for damage classification and localization of damage by modeling theprobability distribution of the features using GMMs. The Kullback-Leibler (KL)divergence of these GMMs with respect to corresponding baseline GMMs are usedas signal difference coefficients (SDCs) to compute damage indices (DIs) alongvarious GW sensor paths, and thus for damage localization. The efficacy of theproposed method is demonstrated using FE generated GW-data for an aluminumplate with a network of six lead zirconate titanate (PZT) sensors, for threedifferent types of damages (rivet hole, added mass, notch) at varioustemperatures, with added white noise and pink noise to incorporate errors dueto EOCs. We also present experimental validation of the method throughcharacterization of notch damage in an aluminum panel under varying andnon-uniform temperature profiles, using a portable custom-designed fieldprogrammable gate array (FPGA) based signal transduction and data acquisitionsystem.

smart materials and structures

Environmental variation compensated damage classification and  localization in ultrasonic guided wave SHM using self-learnt features and  Gaussian mixture models