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

Deep learning (DL) models have seen increased attention for time seriesforecasting, yet the application on cyber-physical systems (CPS) is hindered bythe lacking robustness of these methods. Thus, this study evaluates therobustness and generalization performance of DL architectures on multivariatetime series data from CPS. Our investigation focuses on the models' ability tohandle a range of perturbations, such as sensor faults and noise, and assessestheir impact on overall performance. Furthermore, we test the generalizationand transfer learning capabilities of these models by exposing them toout-of-distribution (OOD) samples. These include deviations from standardsystem operations, while the core dynamics of the underlying physical systemare preserved. Additionally, we test how well the models respond to severaldata augmentation techniques, including added noise and time warping. Ourexperimental framework utilizes a simulated three-tank system, proposed as anovel benchmark for evaluating the robustness and generalization performance ofDL algorithms in CPS data contexts. The findings reveal that certain DL modelarchitectures and training techniques exhibit superior effectiveness inhandling OOD samples and various perturbations. These insights have significantimplications for the development of DL models that deliver reliable and robustperformance in real-world CPS applications.

Robustness and Generalization Performance of Deep Learning Models on Cyber-Physical Systems: A Comparative Study