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

Remaining useful life (RUL) refers to the expected remaining lifespan of acomponent or system. Accurate RUL prediction is critical for prognostic andhealth management and for maintenance planning. In this work, we address threeprevalent challenges in data-driven RUL prediction, namely the handling of highdimensional input features, the robustness to noise in sensor data andprognostic datasets, and the capturing of the time-dependency between systemdegradation and RUL prediction. We devise a highly accurate RUL predictionmodel with uncertainty quantification, which integrates and leverages theadvantages of deep learning and nonstationary Gaussian process regression(DL-NSGPR). We examine and benchmark our model against other advanceddata-driven RUL prediction models using the turbofan engine dataset from theNASA prognostic repository. Our computational experiments show that theDL-NSGPR predictions are highly accurate with root mean square error 1.7 to 6.2times smaller than those of competing RUL models. Furthermore, the resultsdemonstrate that RUL uncertainty bounds with the proposed DL-NSGPR are bothvalid and significantly tighter than other stochastic RUL prediction models. Weunpack and discuss the reasons for this excellent performance of the DL-NSGPR.

Accurate Remaining Useful Life Prediction with Uncertainty Quantification: a Deep Learning and Nonstationary Gaussian Process Approach