Change search
ReferencesLink to record
Permanent link

Direct link
Passive acoustic leak detection for sodium fast reactors using hidden Markov models
KTH, School of Engineering Sciences (SCI), Physics, Reactor Technology. Commisariat Energie Atom & Energies Alternat CEA, France.ORCID iD: 0000-0003-1358-9355
Show others and affiliations
2016 (English)In: IEEE Transactions on Nuclear Science, ISSN 0018-9499, E-ISSN 1558-1578Article in journal (Refereed) Published
Abstract [en]

Acoustic leak detection for steam generators of sodium fast reactors have been an active research topic since the early 1970s and several methods have been tested over the years. Inspired by its success in the field of automatic speech recognition, we here apply hidden Markov models (HMM) in combination with Gaussian mixture models (GMM) to the problem. To achieve this, we propose a new feature calculation scheme, based on the temporal evolution of the power spectral density (PSD) of the signal. Using acoustic signals recorded during steam/water injection experiments done at the Indira Gandhi Centre for Atomic Research (IGCAR), the proposed method is tested. We perform parametric studies on the HMM+GMM model size and demonstrate that the proposed method a) performs well without a priori knowledge of injection noise, b) can incorporate several noise models and c) has an output distribution that simplifies false alarm rate control.

Place, publisher, year, edition, pages
IEEE , 2016.
National Category
Signal Processing
URN: urn:nbn:se:kth:diva-183465DOI: 10.1109/TNS.2015.2502400ISI: 000379928300005OAI: diva2:911525
Swedish Research Council, B0774801

QC 20160329

Available from: 2016-03-13 Created: 2016-03-13 Last updated: 2016-08-12Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full text

Search in DiVA

By author/editor
Riber Marklund, Anders
By organisation
Reactor Technology
In the same journal
IEEE Transactions on Nuclear Science
Signal Processing

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 8 hits
ReferencesLink to record
Permanent link

Direct link