Short-Term Prediction for Nuclear Power Plant Failure Scenarios Using an Ensemble-based Approach

Jie Liu (1, 2) , Valeria Vitelli (1, 2) , Redouane Seraoui (3) , Francesco Di Maio (4) , Enrico Zio (2, 1)

1 LGI - Laboratoire Génie Industriel - EA 2606
2 SSEC - Chaire Sciences des Systèmes et Défis Energétiques EDF/ECP/Supélec
3 EDF R&D - EDF R&D
4 Dipartimento di Energia [Milano]

An ensemble-based approach is proposed for the short-term prediction. The proposed approach includes the selection of the inputs using Fuzzy Similarity Analysis (FSA), Probabilistic Support Vector Re-gression (SVR) model as the single model of the ensemble, and the derivation of the Prediction intervals as-sociated with the predicted value. A case study is shown, regarding the prediction of a drifting process param-eter of a Nuclear Power Plant (NPP) component.

Domains: Statistics [stat]; Machine Learning [stat.ML]

Jie Liu, Valeria Vitelli, Redouane Seraoui, Francesco Di Maio, Enrico Zio. Short-Term Prediction for Nuclear Power Plant Failure Scenarios Using an Ensemble-based Approach. ESREL 2013, Sep 2013, Amsterdam, Netherlands. pp.1-5. ⟨hal-00838785⟩