FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3206917900> ?p ?o ?g. }

• W3206917900 endingPage "73" @default.
• W3206917900 startingPage "59" @default.
• W3206917900 abstract "The new generation of edge computing supported industrial cyber–physical system (ICPS) promotes the deep integration of sensing and control. The unknown model is one of the key challenges to characterize their interactions. In most existing works, many efforts have been devoted to overcoming the challenge for the single aspect of sensing and control. However, the industrial revolution puts forward the higher requirements of the overall production performance. To solve this problem, we propose a novel framework for learning-based edge sensing and control co-design. Specifically, the model learning error is first analyzed to bound the actual control performance. Then, the bound is further linked to the sensing design through the bridge of relaxed assumptions of the nonzero initial state and unknown order. Besides, the cloud-edge symphony (CES) algorithm is designed for the co-design problem solving considering the defects of the single edge computing unit (ECU). In the novel framework, the processes of sensing, control, and learning are comprehensively considered for global optimization. Finally, the proposed algorithm is applied to the personalized production of laminar cooling based on the semiphysical evaluation, and the effectiveness is verified by the results. Note to Practitioners—Edge computing supported ICPS deeply integrates the sensing and control processes. It is beneficial to realize the small-batch customized production for the individual demands in intelligent manufacturing. However, the inevitable problem of weak prior knowledge of system models motivates us to adopt appropriate learning methods to deal with the model inaccuracy and characterize the internal relationship between sensing, control, and model learning. In this article, we propose a novel framework to comprehensively consider the performance of different aspects for global optimization. Specifically, the relaxed assumptions of the nonzero initial state and unknown order are regarded as the bridge to combine edge sensing and control. The cloud-edge symphony (CES) algorithm is proposed to solve the co-design problem and applied to the laminar cooling process for evaluation. It is observed that better overall performance is achieved than previous methods. In the future, our framework can be further extended from the single edge computing unit (ECU) and collaboration with the industrial cloud platform to coordinate sensing and control between the multiple ECUs. Besides, the production requirements of specific applications can be further considered including the real-time response and the reuse of production experience." @default.
• W3206917900 created "2021-10-25" @default.
• W3206917900 creator A5004668792 @default.
• W3206917900 creator A5007013035 @default.
• W3206917900 creator A5038267080 @default.
• W3206917900 creator A5044496582 @default.
• W3206917900 creator A5057826180 @default.
• W3206917900 date "2023-01-01" @default.
• W3206917900 modified "2023-10-10" @default.
• W3206917900 title "Learning-Based Edge Sensing and Control Co-Design for Industrial Cyber–Physical System" @default.
• W3206917900 cites W1971835972 @default.
• W3206917900 cites W1999654112 @default.
• W3206917900 cites W2019369181 @default.
• W3206917900 cites W2076936031 @default.
• W3206917900 cites W2108476371 @default.
• W3206917900 cites W2142635246 @default.
• W3206917900 cites W2150053932 @default.
• W3206917900 cites W2208102648 @default.
• W3206917900 cites W2341523100 @default.
• W3206917900 cites W2344935686 @default.
• W3206917900 cites W2401294332 @default.
• W3206917900 cites W2464325750 @default.
• W3206917900 cites W2570060561 @default.
• W3206917900 cites W2575234888 @default.
• W3206917900 cites W2609433253 @default.
• W3206917900 cites W2757342969 @default.
• W3206917900 cites W2766792137 @default.
• W3206917900 cites W2767464971 @default.
• W3206917900 cites W2786070938 @default.
• W3206917900 cites W2786312736 @default.
• W3206917900 cites W2787444476 @default.
• W3206917900 cites W2796431263 @default.
• W3206917900 cites W2890636089 @default.
• W3206917900 cites W2905802048 @default.
• W3206917900 cites W2933397912 @default.
• W3206917900 cites W2952672134 @default.
• W3206917900 cites W2957568672 @default.
• W3206917900 cites W2963683522 @default.
• W3206917900 cites W2964333506 @default.
• W3206917900 cites W2968069769 @default.
• W3206917900 cites W2972772269 @default.
• W3206917900 cites W2972915637 @default.
• W3206917900 cites W2984637522 @default.
• W3206917900 cites W2997764834 @default.
• W3206917900 cites W3030409210 @default.
• W3206917900 cites W3104091323 @default.
• W3206917900 cites W3123364465 @default.
• W3206917900 cites W3134811048 @default.
• W3206917900 cites W4240790602 @default.
• W3206917900 doi "https://doi.org/10.1109/tase.2021.3115937" @default.
• W3206917900 hasPublicationYear "2023" @default.
• W3206917900 type Work @default.
• W3206917900 sameAs 3206917900 @default.
• W3206917900 citedByCount "1" @default.
• W3206917900 countsByYear W32069179002023 @default.
• W3206917900 crossrefType "journal-article" @default.
• W3206917900 hasAuthorship W3206917900A5004668792 @default.
• W3206917900 hasAuthorship W3206917900A5007013035 @default.
• W3206917900 hasAuthorship W3206917900A5038267080 @default.
• W3206917900 hasAuthorship W3206917900A5044496582 @default.
• W3206917900 hasAuthorship W3206917900A5057826180 @default.
• W3206917900 hasConcept C111919701 @default.
• W3206917900 hasConcept C119599485 @default.
• W3206917900 hasConcept C120314980 @default.
• W3206917900 hasConcept C127413603 @default.
• W3206917900 hasConcept C133731056 @default.
• W3206917900 hasConcept C13736549 @default.
• W3206917900 hasConcept C139719470 @default.
• W3206917900 hasConcept C154945302 @default.
• W3206917900 hasConcept C162307627 @default.
• W3206917900 hasConcept C162324750 @default.
• W3206917900 hasConcept C17500928 @default.
• W3206917900 hasConcept C179768478 @default.
• W3206917900 hasConcept C26517878 @default.
• W3206917900 hasConcept C2775924081 @default.
• W3206917900 hasConcept C2778348673 @default.
• W3206917900 hasConcept C2778456923 @default.
• W3206917900 hasConcept C38652104 @default.
• W3206917900 hasConcept C41008148 @default.
• W3206917900 hasConcept C79974875 @default.
• W3206917900 hasConceptScore W3206917900C111919701 @default.
• W3206917900 hasConceptScore W3206917900C119599485 @default.
• W3206917900 hasConceptScore W3206917900C120314980 @default.
• W3206917900 hasConceptScore W3206917900C127413603 @default.
• W3206917900 hasConceptScore W3206917900C133731056 @default.
• W3206917900 hasConceptScore W3206917900C13736549 @default.
• W3206917900 hasConceptScore W3206917900C139719470 @default.
• W3206917900 hasConceptScore W3206917900C154945302 @default.
• W3206917900 hasConceptScore W3206917900C162307627 @default.
• W3206917900 hasConceptScore W3206917900C162324750 @default.
• W3206917900 hasConceptScore W3206917900C17500928 @default.
• W3206917900 hasConceptScore W3206917900C179768478 @default.
• W3206917900 hasConceptScore W3206917900C26517878 @default.
• W3206917900 hasConceptScore W3206917900C2775924081 @default.
• W3206917900 hasConceptScore W3206917900C2778348673 @default.
• W3206917900 hasConceptScore W3206917900C2778456923 @default.
• W3206917900 hasConceptScore W3206917900C38652104 @default.
• W3206917900 hasConceptScore W3206917900C41008148 @default.

• next