Unsupervised and supervised learning for the reliability analysis of complex systems
Metadatos
Mostrar el registro completo del ítemEditorial
Wiley
Materia
Birnbaum importance measure Dependent components Factor analysis Isotonic smoothing Logistic regression
Fecha
2023-03Referencia bibliográfica
Gámiz ML, Navas-Gómez F, Nozal-Cañadas R, Raya-Miranda R. Unsupervised and supervised learning for the reliability analysis of complex systems. Qual Reliab Eng Int. 2023;1-22. [https://doi.org/10.1002/qre.3311]
Patrocinador
Universidad de Granada / CBUA; Ministry of Science and Innovation, Spain (MICINN) Spanish Government RTI2018-099723-B-I00, PID2020-120217RB-I00; Junta de Andalucia B-FQM-284-UGR20; IMAG-Maria de Maeztu CEX2020-001105-M/AEI/10.13039/501100011033Resumen
In this paper, a strategy to deal with high-dimensional reliability systems with
multiple correlated components is proposed. The goal is to construct a state func-
tion that enables the classification of the states of components in one of two
categories, that is, failure and operative, in case of dealing with a large number
of units in the system. To this end, it is proposed a new algorithm that combines
a factor analysis algorithm (unsupervised learning) with local-logistic and iso-
tonic regression (supervised learning). The reliability function is estimated and
system failures are predicted in terms of the variables in the original state space.
The dimensions in the latent state space are defined by blocks of units with a cer-
tain dependence structure. The flexibility of the model allows quantifying locally
the effect that a particular unit has on the system performance and a ranking
of components can be obtained under the philosophy of the Birnbaum impor-
tance measure. The good performance of the proposal is assessed by means of a
simulation study. Also a real data case is considered to illustrate the method.