A method for measuring the robustness of diagnostic models for predicting the break size during LOCA

Xiange Tian, Victor Becerra, Nils Bausch, Gopika Vinod, T.V. Santhosh

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    38 Downloads (Pure)

    Abstract

    The diagnosis of loss of coolant accidents (LOCA) in nuclear reactors has attracted a great deal of attention in condition monitoring of nuclear power plants (NPPs) because the health of cooling system is crucial to the stability of the nuclear reactor. Multi-layer perceptron (MLP) neural networks have commonly been applied to LOCA diagnosis. The data used for training these models consists of a number of time-series data sets, each for a different break size, with the transient behavior of different measurable variables in the coolant system of the reactor following a LOCA. It is important to select a suitable architecture for the neural network that delivers robust results, in that the predicted break size is deemed to be accurate even for a break size that is not included in the training data sets. The objective of this paper is to present a simple method for measuring the robustness of diagnostic models for predicting the break size during the loss of coolant accidents. A robustness metric is proposed based on the leave-one-out approach and the mean squared error resulting from a diagnostics model. Using this metric it becomes possible to compare the robustness of different diagnostic models. Given data obtained from a high fidelity simulation of the coolant system of a nuclear reactor, four different diagnostic models are obtained and their properties compared and discussed. These models include a fully connected multi-layer perceptron with one hidden layer, a fully connected multi-layer perceptron with two hidden layers, a multi-layer perceptron with one hidden layer that is pruned using the optimal brain surgeon algorithm, a group method of data handling (GMDH) neural network, and an adaptive network based fuzzy inference system (ANFIS).
    Original languageEnglish
    Title of host publicationAnnual Conference of the Prognostics and Health Management Society 2017
    Place of PublicationTampa, Floria, US
    PublisherPrognostics and Health Management Society
    Number of pages9
    Volume8
    Publication statusPublished - 5 Oct 2017
    EventAnnual Conference of the Prognostics and Health Management Society 2017 - St. Petersburg, United States
    Duration: 2 Oct 20175 Oct 2017
    https://www.phmsociety.org/events/conference/phm/17

    Conference

    ConferenceAnnual Conference of the Prognostics and Health Management Society 2017
    Country/TerritoryUnited States
    CitySt. Petersburg
    Period2/10/175/10/17
    Internet address

    Keywords

    • RCUK
    • EPSRC
    • EP/M018709/1

    Fingerprint

    Dive into the research topics of 'A method for measuring the robustness of diagnostic models for predicting the break size during LOCA'. Together they form a unique fingerprint.

    Cite this