Real-time state identification of boiling water reactors using relevance vector machines

Miltiadis Alamaniotis, Mauro Cappelli

Research output: Contribution to conferencePaper

2 Citations (Scopus)

Abstract

Automated state identification systems facilitate reactor monitoring and control of nuclear systems by consolidating information collected by deployed sensors. In the current paper, we present the use of relevance vector machines (RVM) for real-time state identification of boiling water reactors (BWR). In particular, RVM models utilize the incoming signals of interest and identify in real time the state of the BWR either as normal or as one of the transition states. Each of the RVM models is assigned to a single signal; it receives the measured value at each instance and outputs the identified BWR state. The state that has been designated by the majority of the signals is displayed to the human operator as the identified BWR state. The proposed methodology is applied and tested on a set of signals taken from the FIX-II experimental facility that is a scaled representation of a BWR.
Original languageEnglish
DOIs
Publication statusPublished - 2016
Externally publishedYes
Event2016 24th International Conference on Nuclear Engineering, ICONE 2016 - Charlotte, United States
Duration: 1 Jan 2016 → …

Conference

Conference2016 24th International Conference on Nuclear Engineering, ICONE 2016
CountryUnited States
CityCharlotte
Period1/1/16 → …

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Nuclear Energy and Engineering

Cite this

Alamaniotis, M., & Cappelli, M. (2016). Real-time state identification of boiling water reactors using relevance vector machines. Paper presented at 2016 24th International Conference on Nuclear Engineering, ICONE 2016, Charlotte, United States. https://doi.org/10.1115/ICONE24-60048