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

Electromagnetic acoustic transducers (EMATs) are noncontact\udtransducers generating ultrasonic waves directly in the conductive sample.\udDespite the advantages, their transduction efficiencies are relatively low,\udso it is imperative to build accurate multiphysics models of EMATs and\udoptimize the structural parameters accordingly, using a suitable optimization\udalgorithm. The optimizing process often involves a large number of runs of\udthe computationally expensive numerical models, so metamodels as substitutes\udfor the real numerical models are helpful for the optimizations. In this work\udthe focus is on the artificial neural networks as the metamodels of an\udomnidirectional EMAT, including the multilayer feedforward networks trained\udwith the basic and improved back propagation algorithms and the radial basis\udfunction networks with exact and nonexact interpolations. The developed\udneural-network programs are tested on an example problem. Then the model of\udan omnidirectional EMAT generating Lamb waves in a linearized steel plate is\udintroduced, and various approaches to calculate the amplitudes of the\uddisplacement component waveforms are discussed. The neural-network metamodels\udare then built for the EMAT model and compared to the displacement\udcomponent amplitude (or ratio of amplitudes) surface data on a discrete grid\udof the design variables as the reference, applying a multifrequency model\udwith FFT (fast Fourier transform)/IFFT (inverse FFT) processing. Finally the\udtwo-objective optimization problem is formulated with one objective function\udminimizing the ratio of the amplitude of the S0-mode Lamb wave to that of\udthe A0 mode, and the other objective function minimizing as the negative\udamplitude of the A0 mode. Pareto fronts in the criterion space are solved\udwith the neural-network models and the total time consumption is greatly\uddecreased. From the study it could be observed that the radial basis function\udnetwork with exact interpolation has the best performance considering its\udaccuracy of approximation and the time required to build the metamodel

Accelerated optimizations of an electromagnetic acoustic transducer with artificial neural networks as metamodels