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

With the increased availability of condition monitoring data and theincreased complexity of explicit system physics-based models, the applicationof data-driven approaches for fault detection and isolation has recently grown.While detection accuracy of such approaches is generally good, theirperformance on fault isolation often suffers from the fact that faultconditions affect a large portion of the measured signals thereby masking thefault source. To overcome this limitation and enable a more accurate faultdetection, we propose a hybrid approach combining physical performance modelswith deep learning algorithms. Unobserved process variables are inferred with aphysics-based performance model to enhance the input space of a data-drivendiagnostics model. To validate the effectiveness of the proposed method, wegenerate a condition monitoring dataset of an advanced gas turbine duringflight conditions under healthy and four faulty operative conditions based onthe Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dynamicalmodel. We evaluate the performance of the proposed method in combination withtwo different deep learning algorithms: feed forward neural networks andVariational Autoencoders, both of which demonstrate a significant improvementwhen applied within the hybrid fault detection and diagnostics framework. Theproposed method is able to outperform pure data-driven solutions, particularlyfor systems with a high variability of operating conditions. It providessuperior results both for fault detection as well as for fault isolation. Forfault isolation, it overcomes the smearing effect that is observed in puredata-driven approaches and enables a precise isolation of the affected signal.We also demonstrate that deep learning algorithms provide a better performanceon fault detection compared to the traditional machine learning algorithms.

Hybrid deep fault detection and isolation: Combining deep neural networks and system performance models