FAILURE PROGNOSTICS BY A DATA-DRIVEN SIMILARITY-BASED APPROACH

Enrico Zio (1) , F. Di Maio (2)

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

This paper presents a data-driven, similarity-based approach for prognostics of industrial and structural components. The potentiality of the approach is demonstrated on a problem of crack propagation, taken from literature. The crack growth process is described by a non linear model affected by non-additive noises. A comparison is provided with a Monte Carlo-based estimation method, known as particle filtering.

Domaines: Sciences de l'ingénieur [physics]

Enrico Zio, F. Di Maio. FAILURE PROGNOSTICS BY A DATA-DRIVEN SIMILARITY-BASED APPROACH. International Journal of Reliability, Quality and Safety Engineering, 2013, 20, pp.1350001. ⟨10.1142/S0218539313500010⟩. ⟨hal-00926377⟩