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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Many industrial sectors have been collecting big sensor data. With recenttechnologies for processing big data, companies can exploit this for automaticfailure detection and prevention. We propose the first completely automatedmethod for failure analysis, machine-learning fault trees from rawobservational data with continuous variables. Our method scales well and istested on a real-world, five-year dataset of domestic heater operations in TheNetherlands, with 31 million unique heater-day readings, each containing 27sensor and 11 failure variables. Our method builds on two previous procedures:the C4.5 decision-tree learning algorithm, and the LIFT fault tree learningalgorithm from Boolean data. C4.5 pre-processes each continuous variable: itlearns an optimal numerical threshold which distinguishes between faulty andnormal operation of the top-level system. These thresholds discretise thevariables, thus allowing LIFT to learn fault trees which model the root failuremechanisms of the system and are explainable. We obtain fault trees for the 11failure variables, and evaluate them in two ways: quantitatively, with asignificance score, and qualitatively, with domain specialists. Some of thefault trees learnt have almost maximum significance (above 0.95), while othershave medium-to-low significance (around 0.30), reflecting the difficulty oflearning from big, noisy, real-world sensor data. The domain specialistsconfirm that the fault trees model meaningful relationships among thevariables.

Automated fault tree learning from continuous-valued sensor data: a case study on domestic heaters