Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385453048> ?p ?o ?g. }
- W4385453048 endingPage "12" @default.
- W4385453048 startingPage "1" @default.
- W4385453048 abstract "Establishing a health indicator (HI) is essential for monitoring the condition of rolling bearings and mitigating failure risks. Unsupervised learning, which eliminates the necessity for manual labeling, has gained considerable attention in constructing HIs. However, existing unsupervised methods mainly suffer from two limitations. First, redundancy analysis is generally disregarded in the feature selection process. Second, temporal dependencies between distinct instants are neglected due to single time-step samples. To address the issue, this paper proposes an innovative unsupervised condition monitoring method based on compound feature selection and a multi-step-aware model. The major contributions are comprehensive feature selection and effective information extraction of continuous sampling instants. Specifically, in feature selection, a novel metric is designed to effectively capture abrupt changes of features proximate to failure. Utilizing this metric, a compound feature selection (CFS) algorithm is proposed to identify a superior feature subset with high correlation to the degradation and low redundancy among features. Additionally, a bidirectional Gated Recurrent Unit based Variational Autoencoder (BiGRU-VAE) with multiple time-step inputs is constructed to leverage the information of different sampling instants. The BiGRU-VAE is trained exclusively on healthy features within the superior subset. The dissimilarity between the input sample and its reconstruction is employed as the HI to represent bearing degradation. Comparative experiments on two run-to-failure datasets validate the superiority of the HIs constructed by the proposed method in presenting the degradation process. Ablation experiments confirm the dominance of the CFS algorithm and the necessity of multiple time-step inputs." @default.
- W4385453048 created "2023-08-02" @default.
- W4385453048 creator A5005384252 @default.
- W4385453048 creator A5008077052 @default.
- W4385453048 creator A5014211366 @default.
- W4385453048 creator A5073034733 @default.
- W4385453048 date "2023-01-01" @default.
- W4385453048 modified "2023-10-17" @default.
- W4385453048 title "An Unsupervised Condition Monitoring Method for Rolling Bearings Based on Compound Feature Selection and Multi-step-aware BiGRU-VAE" @default.
- W4385453048 cites W1862394037 @default.
- W4385453048 cites W1973665104 @default.
- W4385453048 cites W1975687401 @default.
- W4385453048 cites W1978450991 @default.
- W4385453048 cites W2014683958 @default.
- W4385453048 cites W2077204677 @default.
- W4385453048 cites W2137144167 @default.
- W4385453048 cites W2154053567 @default.
- W4385453048 cites W2164104048 @default.
- W4385453048 cites W2286877141 @default.
- W4385453048 cites W2523377413 @default.
- W4385453048 cites W2591055632 @default.
- W4385453048 cites W2619304139 @default.
- W4385453048 cites W2773549135 @default.
- W4385453048 cites W2792018332 @default.
- W4385453048 cites W2801396593 @default.
- W4385453048 cites W2810292802 @default.
- W4385453048 cites W2904460913 @default.
- W4385453048 cites W2915337192 @default.
- W4385453048 cites W2973001054 @default.
- W4385453048 cites W2998506103 @default.
- W4385453048 cites W3007048760 @default.
- W4385453048 cites W3007559859 @default.
- W4385453048 cites W3011785067 @default.
- W4385453048 cites W3021204045 @default.
- W4385453048 cites W3032983473 @default.
- W4385453048 cites W3045078359 @default.
- W4385453048 cites W3046248607 @default.
- W4385453048 cites W3094065942 @default.
- W4385453048 cites W3094146358 @default.
- W4385453048 cites W3106063097 @default.
- W4385453048 cites W3112563862 @default.
- W4385453048 cites W3117204221 @default.
- W4385453048 cites W3164571460 @default.
- W4385453048 cites W3185016559 @default.
- W4385453048 cites W3194431502 @default.
- W4385453048 cites W3212733794 @default.
- W4385453048 cites W3214396588 @default.
- W4385453048 cites W4200209943 @default.
- W4385453048 cites W4211206835 @default.
- W4385453048 cites W4226257732 @default.
- W4385453048 cites W4285116605 @default.
- W4385453048 cites W4296362271 @default.
- W4385453048 cites W4313067792 @default.
- W4385453048 cites W4318148761 @default.
- W4385453048 doi "https://doi.org/10.1109/tim.2023.3300435" @default.
- W4385453048 hasPublicationYear "2023" @default.
- W4385453048 type Work @default.
- W4385453048 citedByCount "0" @default.
- W4385453048 crossrefType "journal-article" @default.
- W4385453048 hasAuthorship W4385453048A5005384252 @default.
- W4385453048 hasAuthorship W4385453048A5008077052 @default.
- W4385453048 hasAuthorship W4385453048A5014211366 @default.
- W4385453048 hasAuthorship W4385453048A5073034733 @default.
- W4385453048 hasConcept C101738243 @default.
- W4385453048 hasConcept C108583219 @default.
- W4385453048 hasConcept C111919701 @default.
- W4385453048 hasConcept C124101348 @default.
- W4385453048 hasConcept C138885662 @default.
- W4385453048 hasConcept C148483581 @default.
- W4385453048 hasConcept C152124472 @default.
- W4385453048 hasConcept C153083717 @default.
- W4385453048 hasConcept C153180895 @default.
- W4385453048 hasConcept C154945302 @default.
- W4385453048 hasConcept C2776401178 @default.
- W4385453048 hasConcept C41008148 @default.
- W4385453048 hasConcept C41895202 @default.
- W4385453048 hasConcept C52622490 @default.
- W4385453048 hasConceptScore W4385453048C101738243 @default.
- W4385453048 hasConceptScore W4385453048C108583219 @default.
- W4385453048 hasConceptScore W4385453048C111919701 @default.
- W4385453048 hasConceptScore W4385453048C124101348 @default.
- W4385453048 hasConceptScore W4385453048C138885662 @default.
- W4385453048 hasConceptScore W4385453048C148483581 @default.
- W4385453048 hasConceptScore W4385453048C152124472 @default.
- W4385453048 hasConceptScore W4385453048C153083717 @default.
- W4385453048 hasConceptScore W4385453048C153180895 @default.
- W4385453048 hasConceptScore W4385453048C154945302 @default.
- W4385453048 hasConceptScore W4385453048C2776401178 @default.
- W4385453048 hasConceptScore W4385453048C41008148 @default.
- W4385453048 hasConceptScore W4385453048C41895202 @default.
- W4385453048 hasConceptScore W4385453048C52622490 @default.
- W4385453048 hasFunder F4320321001 @default.
- W4385453048 hasFunder F4320328872 @default.
- W4385453048 hasFunder F4320335777 @default.
- W4385453048 hasLocation W43854530481 @default.
- W4385453048 hasOpenAccess W4385453048 @default.
- W4385453048 hasPrimaryLocation W43854530481 @default.
- W4385453048 hasRelatedWork W1576462183 @default.