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

The problem of detecting and identifying sensor faults is critical forefficient, safe, regulatory-compliant and sustainable operations of modernsystems. Their increasing complexity brings new challenges for the Sensor FaultDetection and Isolation (SFD-SFI) tasks. One of the key enablers for anySFD-SFI methods employed in modern complex sensor systems, is the so-calledanalytical redundancy, which is nothing but building an analytical model of thesensors observations (either derived from first principles or identified fromhistorical data in a data-driven fashion). In a nutshell, SFD amounts togenerate and to monitor residuals by comparing the sensor measurements with themodel predictions with the idea that the faulty sensors will result in largeresiduals (i.e. the defective sensors generate measurement that areinconsistent with their expected behavior represented by the model). In thispaper we introduce a disentangled Recurrent Neural Network (RNN) with theobjective to cope with the \textit{smearing-out} effect, i.e. the propagationof a sensor fault to the non-faulty sensors resulting in large misleadingresiduals. Moreover, the introduction of a probabilistic model for the residualgeneration allows us to develop a novel procedure for the identification of thefaulty sensors. The computational complexity of the proposed algorithm islinear in the number of sensors as opposed to the combinatorial nature of theSFI problem. Finally, we empirically verify the performances of the proposedSFD-SFI architecture using a real data set collected at a petrochemical plant.

A scalable algorithm for identifying multiple sensor faults using disentangled RNNs