FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367016839> ?p ?o ?g. }

• W4367016839 endingPage "12" @default.
• W4367016839 startingPage "1" @default.
• W4367016839 abstract "As deep learning with its powerful fitting representation ability is increasingly applied in intelligent fault diagnosis of mechanical equipment, the interpretability of networks directly affects the credibility and universality of the models with the mechanism of equipment signal characteristic ignored. In order to solve those issues, this study proposes a multiplication-convolution sparse network (MCSN) with interpretable sparse kernels, which contains a simple three layers, including feature separator, feature extractor and logic classifier. Inspired by signal modulation mechanism, the raw spectrum signals are first processed by feature separator with multiple learnable multiplication filtering kernels. The feature separator can effectively separate fault features from complex spectrum in a comprehensible way. Then, feature extractor with convolutional process is also used to min the sequential characteristics and those features are finally input the logic classifier. It should be noted that the combination of the multiplication process and the convolution process aims to achieve efficient feature mining of the signal. In particular, the addition of anti-aliasing constraint and L <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>1</sup> regularization constraint in the training process makes the multiplication filtering kernel parameters sparse and learn as much fault feature information distributed in different frequency bands as possible, which is conducive to the visualization of the spectrum information extraction and thus enhances the interpretability and reliability of the multiplication filtering kernels. The interpretability of the proposed MCSN is verified by a two-class task experiment, and the visualizations of the learned multiplication filtering kernel illustrate a clear and accurate representation related to the fault features. Compared with other six open-source network models, including WKN, LeNet, CNN, ResNet18, AlexNet, and BiLSTM, the proposed MCSN has the highest fault recognition accuracy, with an average recognition accuracy of 99.65% for gear faults and 99.83% for bearing faults. Ablation experiments on CNN indicate the benefit of the proposed feature separator in feature enhancement with an average recognition accuracy improvement of 1.59%." @default.
• W4367016839 created "2023-04-27" @default.
• W4367016839 creator A5008996148 @default.
• W4367016839 creator A5025358476 @default.
• W4367016839 creator A5034422878 @default.
• W4367016839 creator A5054306467 @default.
• W4367016839 creator A5069181198 @default.
• W4367016839 creator A5047724773 @default.
• W4367016839 date "2023-01-01" @default.
• W4367016839 modified "2023-10-18" @default.
• W4367016839 title "An Interpretable Multiplication-Convolution Sparse Network for Equipment Intelligent Diagnosis in Antialiasing and Regularization Constraint" @default.
• W4367016839 cites W1130761448 @default.
• W4367016839 cites W1196380178 @default.
• W4367016839 cites W1970066309 @default.
• W4367016839 cites W2000982976 @default.
• W4367016839 cites W2347027361 @default.
• W4367016839 cites W2595657631 @default.
• W4367016839 cites W2761196906 @default.
• W4367016839 cites W2767234670 @default.
• W4367016839 cites W2791694051 @default.
• W4367016839 cites W2794869810 @default.
• W4367016839 cites W2954351926 @default.
• W4367016839 cites W2956467153 @default.
• W4367016839 cites W2966507006 @default.
• W4367016839 cites W2977117446 @default.
• W4367016839 cites W2989818023 @default.
• W4367016839 cites W2995140071 @default.
• W4367016839 cites W2997353220 @default.
• W4367016839 cites W3003397973 @default.
• W4367016839 cites W3007857598 @default.
• W4367016839 cites W3008309516 @default.
• W4367016839 cites W3009370740 @default.
• W4367016839 cites W3039300052 @default.
• W4367016839 cites W3046716936 @default.
• W4367016839 cites W3116528219 @default.
• W4367016839 cites W3118765904 @default.
• W4367016839 cites W3122347867 @default.
• W4367016839 cites W3129676456 @default.
• W4367016839 cites W3138869797 @default.
• W4367016839 cites W3178658307 @default.
• W4367016839 cites W3195621661 @default.
• W4367016839 cites W3201753566 @default.
• W4367016839 cites W4200024486 @default.
• W4367016839 cites W4206568770 @default.
• W4367016839 cites W4210725851 @default.
• W4367016839 cites W4225517134 @default.
• W4367016839 cites W4285124025 @default.
• W4367016839 cites W4285237966 @default.
• W4367016839 cites W4312893865 @default.
• W4367016839 doi "https://doi.org/10.1109/tim.2023.3269122" @default.
• W4367016839 hasPublicationYear "2023" @default.
• W4367016839 type Work @default.
• W4367016839 citedByCount "0" @default.
• W4367016839 crossrefType "journal-article" @default.
• W4367016839 hasAuthorship W4367016839A5008996148 @default.
• W4367016839 hasAuthorship W4367016839A5025358476 @default.
• W4367016839 hasAuthorship W4367016839A5034422878 @default.
• W4367016839 hasAuthorship W4367016839A5047724773 @default.
• W4367016839 hasAuthorship W4367016839A5054306467 @default.
• W4367016839 hasAuthorship W4367016839A5069181198 @default.
• W4367016839 hasConcept C11413529 @default.
• W4367016839 hasConcept C114614502 @default.
• W4367016839 hasConcept C153180895 @default.
• W4367016839 hasConcept C154945302 @default.
• W4367016839 hasConcept C2780595030 @default.
• W4367016839 hasConcept C2781067378 @default.
• W4367016839 hasConcept C33923547 @default.
• W4367016839 hasConcept C41008148 @default.
• W4367016839 hasConcept C52622490 @default.
• W4367016839 hasConcept C95623464 @default.
• W4367016839 hasConceptScore W4367016839C11413529 @default.
• W4367016839 hasConceptScore W4367016839C114614502 @default.
• W4367016839 hasConceptScore W4367016839C153180895 @default.
• W4367016839 hasConceptScore W4367016839C154945302 @default.
• W4367016839 hasConceptScore W4367016839C2780595030 @default.
• W4367016839 hasConceptScore W4367016839C2781067378 @default.
• W4367016839 hasConceptScore W4367016839C33923547 @default.
• W4367016839 hasConceptScore W4367016839C41008148 @default.
• W4367016839 hasConceptScore W4367016839C52622490 @default.
• W4367016839 hasConceptScore W4367016839C95623464 @default.
• W4367016839 hasFunder F4320321001 @default.
• W4367016839 hasFunder F4320335777 @default.
• W4367016839 hasLocation W43670168391 @default.
• W4367016839 hasOpenAccess W4367016839 @default.
• W4367016839 hasPrimaryLocation W43670168391 @default.
• W4367016839 hasRelatedWork W2022996092 @default.
• W4367016839 hasRelatedWork W2188464267 @default.
• W4367016839 hasRelatedWork W2545275226 @default.
• W4367016839 hasRelatedWork W2784352036 @default.
• W4367016839 hasRelatedWork W2807311372 @default.
• W4367016839 hasRelatedWork W2811390910 @default.
• W4367016839 hasRelatedWork W2905846897 @default.
• W4367016839 hasRelatedWork W2995914718 @default.
• W4367016839 hasRelatedWork W4221015625 @default.
• W4367016839 hasRelatedWork W4367598285 @default.
• W4367016839 hasVolume "72" @default.
• W4367016839 isParatext "false" @default.
• W4367016839 isRetracted "false" @default.

• next