Monitoring pipeline operating conditions is a vital component in pipeline safety and risk management. Although the SCADA system stores a large amount of operational data, the data lacks associated condition labels, making it difficult to mine. Furthermore, the operating circumstances of the multi-product pipeline vary often, and identification and monitoring by on-site employees are prone to error, so the pipeline’s operating conditions cannot be reliably identified. To address the aforementioned challenges, this chapter presents semi-supervised learning for operating condition identification. The findings show that semi-supervised learning has more stability and improved performance regardless of how the neural network is built. The suggested technique may be utilized as a decision-making tool for monitoring and identifying multi-product pipeline operating conditions.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Operation Condition Monitoring for Pipeline


    Beteiligte:
    Su, Huai (Herausgeber:in) / Liao, Qi (Herausgeber:in) / Zhang, Haoran (Herausgeber:in) / Zio, Enrico (Herausgeber:in) / Zhang, Li (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    13.12.2023


    Format / Umfang :

    13 pages




    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Operation Condition Prediction for Pipeline

    Zhang, Li / Su, Huai | Springer Verlag | 2023


    Use of pressure surge for pipeline condition monitoring

    Vardy, A.E. / Mackenzie, H. | Tema Archiv | 2012


    An integrated system for pipeline condition monitoring and pig tracking

    Strong, A.P. / Sanderson, N. / Lees, G. et al. | British Library Online Contents | 2009


    Elevator operation condition monitoring device and method

    MIN YABIN / MIN BOWEN | Europäisches Patentamt | 2024

    Freier Zugriff

    Elevator operation condition bad risk monitoring system

    ZHENG ZHUOHUI / LIU HANG / XU YANG et al. | Europäisches Patentamt | 2023

    Freier Zugriff