Artificial Intelligence for Concentrated Solar Plant Maintenance Management

Alfredo Arcos Jimenez, Carlos Munoz, Fausto Marquez, Long Zhang

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    Abstract

    Concentrated Solar Power (CSP) is an alternative to the conventional energy
    sources which has had significant advances nowadays. A proper predictive
    maintenance program for the absorber pipes is required to detect defects in the tubes
    at an early stage, in order to reduce corrective maintenance costs and increase the reliability,
    availability, and safety of the concentrator solar plant. This paper presents
    a novel approach based on signal processing employing neuronal network to determine
    effectively the temperature of pipe, using only ultrasonic transducers. The
    main novelty presented in this paper is to determine the temperature of CSP without
    requiring additional sensors. This is achieved by using existing ultrasonic transducers
    which is mainly designed for inspection of the absorber tubes. It can also identify
    suddenly changes in the temperature of the CSP, e.g. due to faults such as corrosion,
    which generate hot spots close to welds
    Original languageEnglish
    Title of host publicationProceedings of the tenth International Conference on Management Science and Engineering Management
    EditorsJiuping Xu, Asaf Hajiyev, Stefan Nickel, Mitsuo Gen
    Place of PublicationSingapore
    PublisherSpringer Nature
    Pages125-134
    Volume1
    ISBN (Print)9789811018367
    Publication statusPublished - 31 Aug 2016

    Publication series

    NameAdvances in intelligent systems and computing,
    Volume502

    Keywords

    • Fault detection and diagnosis
    • Electromagnetic sensors
    • Macro fiber
    • Wavelet transforms
    • Non destructive tests

    Fingerprint

    Dive into the research topics of 'Artificial Intelligence for Concentrated Solar Plant Maintenance Management'. Together they form a unique fingerprint.

    Cite this