Clustering for unsupervised fault diagnosis in nuclear turbine shut-down transients

Piero Baraldi (1) , Francesco Di Maio (1) , Marco Rigamonti (1) , Enrico Zio (2) , Redouane Seraoui (3)

1 Dipartimento di Energia [Milano]
2 SSEC - Chaire Sciences des Systèmes et Défis Energétiques EDF/ECP/Supélec
3 EDF R&D - EDF R&D

Empirical methods for fault diagnosis usually entail a process of supervised training based on a set of examples of signal evolutions " labeled " with the corresponding, known classes of fault. However, in practice, the signals collected during plant operation may be, very often, " unlabeled " , i.e., the information on the corresponding type of occurred fault is not available. To cope with this practical situation, in this paper we develop a methodology for the identification of transient signals showing similar characteristics, under the conjecture that operational/faulty transient conditions of the same type lead to similar behavior in the measured signals evolution. The methodology is founded on a feature extraction procedure, which feeds a spectral clustering technique, embedding the unsupervised Fuzzy C-Means (FCM) algorithm, that evaluates the functional similarity among the different operational/faulty transients. A procedure for validating the plausibility of the obtained clusters is also propounded based on physical considerations. The methodology is applied to a real industrial case, on the basis of 148 shutdown transients of a Nuclear Power Plant (NPP) steam turbine.

Mots clés: Fault Diagnosis; Steam Turbine; Nuclear Power Plant; Unsupervised Clustering; Fuzzy-based Slope Analysis; Fuzzy Similarity; Spectral Clustering; Fuzzy C-Means

Domaines: Energie électrique

Piero Baraldi, Francesco Di Maio, Marco Rigamonti, Enrico Zio, Redouane Seraoui. Clustering for unsupervised fault diagnosis in nuclear turbine shut-down transients. Mechanical Systems and Signal Processing, 2015, 58-59, pp.160-178. ⟨10.1016/j.ymssp.2014.12.018⟩. ⟨hal-01265643⟩