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

With the advantages of high modeling accuracy and large bandwidth, recurrentneural network (RNN) based inversion model control has been proposed for outputtracking. However, some issues still need to be addressed when using theRNN-based inversion model. First, with limited number of parameters in RNN, itcannot model the low-frequency dynamics accurately, thus an extra linear modelhas been used, which can become an interference for tracking control at highfrequencies. Moreover, the control speed and the RNN modeling accuracy cannotbe improved simultaneously as the control sampling speed is restricted by thelength of the RNN training set. Therefore, this article focuses on addressingthese limitations of RNN-based inversion model control. Specifically, a novelmodeling method is proposed to incorporate the linear model in a way that itdoes not affect the existing high-frequency control performance achieved byRNN. Additionally, an interpolation method is proposed to double the samplingfrequency (compared to the RNN training sampling frequency). Analysis on thestability issues which may arise when the proposed new model is used forpredictive control is presented along with the instructions on determining theparameters for ensuring the closed-loop stability. Finally, the proposedapproach is demonstrated on a commercial piezo actuator, and the experimentresults show that the tracking performances can be significantly improved.

Towards Improving the Performance of the RNN-based Inversion Model in Output Tracking Control