Matches in SemOpenAlex for { <https://semopenalex.org/work/W3168567278> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W3168567278 endingPage "107381" @default.
- W3168567278 startingPage "107381" @default.
- W3168567278 abstract "• Condition-based maintenance strategies are gaining popularity, but often lack diagnostics. • Sensor data is leveraged for breakdown prediction models with high prognostic value. • For added diagnostic value, we implement Shapley Values to great success. • Explains “black-box” CBM models in order to improve maintenance strategies. • A framework to compare inspection reports and statistical insights for diagnostics verification. Condition-based maintenance (CBM) is becoming more commonplace within the petrochemical industry. While we find that previous research leveraging machine learning has provided high accuracy in the predictive aspect of machine breakdowns, the diagnostic aspect of these approaches is often lacking. This paper implements a supervised machine learning approach, with the goal of both prediction and diagnosis of machinery breakdowns, emphasizing the latter. To achieve this, it uses an XGBoost model trained on a combination of sensor and report data, and enriches the model with Shapley values for diagnostic insights. We show that this combination of statistical methods, combined with a proper data treatment, can be used to great effect and can vastly improve the diagnostic value of machine learning approaches. The insights that follow from the analysis can subsequently be leveraged by plant operators in CBM strategies or root-cause analyses." @default.
- W3168567278 created "2021-06-22" @default.
- W3168567278 creator A5018820714 @default.
- W3168567278 creator A5026810106 @default.
- W3168567278 date "2021-09-01" @default.
- W3168567278 modified "2023-09-26" @default.
- W3168567278 title "Adding interpretability to predictive maintenance by machine learning on sensor data" @default.
- W3168567278 cites W1551688898 @default.
- W3168567278 cites W1855879034 @default.
- W3168567278 cites W1981780459 @default.
- W3168567278 cites W1998523455 @default.
- W3168567278 cites W2000651380 @default.
- W3168567278 cites W2035629481 @default.
- W3168567278 cites W2037325790 @default.
- W3168567278 cites W2044049559 @default.
- W3168567278 cites W2045186954 @default.
- W3168567278 cites W2064323378 @default.
- W3168567278 cites W2065865325 @default.
- W3168567278 cites W2071918046 @default.
- W3168567278 cites W2083932386 @default.
- W3168567278 cites W2111824912 @default.
- W3168567278 cites W2113860482 @default.
- W3168567278 cites W2157792207 @default.
- W3168567278 cites W2732499510 @default.
- W3168567278 cites W2754370323 @default.
- W3168567278 cites W2768753204 @default.
- W3168567278 cites W2773549135 @default.
- W3168567278 cites W2795411881 @default.
- W3168567278 cites W2808779485 @default.
- W3168567278 cites W2897120700 @default.
- W3168567278 cites W2972137370 @default.
- W3168567278 cites W2989816351 @default.
- W3168567278 cites W2999615587 @default.
- W3168567278 cites W3034202893 @default.
- W3168567278 cites W3141155221 @default.
- W3168567278 cites W4248831067 @default.
- W3168567278 cites W83480120 @default.
- W3168567278 doi "https://doi.org/10.1016/j.compchemeng.2021.107381" @default.
- W3168567278 hasPublicationYear "2021" @default.
- W3168567278 type Work @default.
- W3168567278 sameAs 3168567278 @default.
- W3168567278 citedByCount "4" @default.
- W3168567278 countsByYear W31685672782021 @default.
- W3168567278 countsByYear W31685672782022 @default.
- W3168567278 countsByYear W31685672782023 @default.
- W3168567278 crossrefType "journal-article" @default.
- W3168567278 hasAuthorship W3168567278A5018820714 @default.
- W3168567278 hasAuthorship W3168567278A5026810106 @default.
- W3168567278 hasConcept C119857082 @default.
- W3168567278 hasConcept C124101348 @default.
- W3168567278 hasConcept C127413603 @default.
- W3168567278 hasConcept C154945302 @default.
- W3168567278 hasConcept C200601418 @default.
- W3168567278 hasConcept C2781067378 @default.
- W3168567278 hasConcept C41008148 @default.
- W3168567278 hasConcept C70452415 @default.
- W3168567278 hasConceptScore W3168567278C119857082 @default.
- W3168567278 hasConceptScore W3168567278C124101348 @default.
- W3168567278 hasConceptScore W3168567278C127413603 @default.
- W3168567278 hasConceptScore W3168567278C154945302 @default.
- W3168567278 hasConceptScore W3168567278C200601418 @default.
- W3168567278 hasConceptScore W3168567278C2781067378 @default.
- W3168567278 hasConceptScore W3168567278C41008148 @default.
- W3168567278 hasConceptScore W3168567278C70452415 @default.
- W3168567278 hasLocation W31685672781 @default.
- W3168567278 hasOpenAccess W3168567278 @default.
- W3168567278 hasPrimaryLocation W31685672781 @default.
- W3168567278 hasRelatedWork W1986582023 @default.
- W3168567278 hasRelatedWork W3006943036 @default.
- W3168567278 hasRelatedWork W4200511449 @default.
- W3168567278 hasRelatedWork W4206534706 @default.
- W3168567278 hasRelatedWork W4229079080 @default.
- W3168567278 hasRelatedWork W4299487748 @default.
- W3168567278 hasRelatedWork W4385767940 @default.
- W3168567278 hasRelatedWork W4385957992 @default.
- W3168567278 hasRelatedWork W4385965371 @default.
- W3168567278 hasRelatedWork W4386025632 @default.
- W3168567278 hasVolume "152" @default.
- W3168567278 isParatext "false" @default.
- W3168567278 isRetracted "false" @default.
- W3168567278 magId "3168567278" @default.
- W3168567278 workType "article" @default.