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/

Zendy Pro

Presents the zaia usage as premium feature

ZAIA

Presents AI Discovery search usage as a premium feature

AI Discovery

Presents AI Discovery explain and summary usage as a premium feature

Content Analysis

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Presents the pdf analysis as premium feature

PDF Analysis

1500 Top-up

3000 Top-up

Zendy Basic

2500 Top-up

Zendy Unlimited

Presents the access of premium content as premium feature

Premium Content

In processing and manufacturing industries, there has been a large push toproduce higher quality products and ensure maximum efficiency of processes.This requires approaches to effectively detect and resolve disturbances toensure optimal operations. While the control system can compensate for manytypes of disturbances, there are changes to the process which it still cannothandle adequately. It is therefore important to further develop monitoringsystems to effectively detect and identify those faults such that they can bequickly resolved by operators. In this paper, a novel probabilistic faultdetection and identification method is proposed which adopts a newly developeddeep learning approach using Bayesian recurrent neural networks~(BRNNs) withvariational dropout. The BRNN model is general and can model complex nonlineardynamics. Moreover, compared to traditional statistic-based data-driven faultdetection and identification methods, the proposed BRNN-based method yieldsuncertainty estimates which allow for simultaneous fault detection of chemicalprocesses, direct fault identification, and fault propagation analysis. Theoutstanding performance of this method is demonstrated and contrasted to(dynamic) principal component analysis, which are widely applied in theindustry, in the benchmark Tennessee Eastman process~(TEP) and a real chemicalmanufacturing dataset.

Fault Detection and Identification using Bayesian Recurrent Neural Networks