Afficher la couverture 'Cross-domain fault diagnosis through optimal transport for a CSTR process | Fernandes Montesuma, Eduardo' en grand format
/5

0 avis

Cross-domain fault diagnosis through optimal transport for a CSTR process

Archive ouverte

Fernandes Montesuma, Eduardo | Mulas, Michela | Corona, Francesco | Ngolè Mboula, Fred Maurice

Edité par CCSD -

Part of special issue 13th IFAC Symposium on Dynamics and Control of Process Systems, including Biosystems DYCOPS 2022: Busan, Republic of Korea, 14–17 June 2022 Edited by Luis Ricardez-Sandoval, Jesus Pico, Jay H. Lee, Jong Min Lee. International audience. Fault diagnosis is a key task for developing safer control systems, especially in chemical plants. Nonetheless, acquiring good labeled fault data involves sampling from dangerous system conditions. A possible workaround to this limitation is to use simulation data for training data-driven fault diagnosis systems. However, due to modelling errors or unknown factors, simulation data may differ in distribution from real-world data. This setting is known as cross-domain fault diagnosis (CDFD). We use optimal transport for: (i) exploring how modelling errors relate to the distance between simulation (source) and real-world (target) data distributions, and (ii) matching source and target distributions through the framework of optimal transport for domain adaptation (OTDA), resulting in new training data that follows the target distribution. Comparisons show that OTDA outperforms other CDFD methods.

Suggestions

Du même auteur

Multi-Source Domain Adaptation through Wasserstein Barycenters. Adaptation de domaines multi-sources à l'aide des barycentres de Wasserstein

Archive ouverte | Fernandes Montesuma, Eduardo | CCSD

Machine learning systems work under the assumption that training and test conditions are uniform, i.e., they do not change. However, this hypothesis is seldom met in practice. Hence, the system is trained with data that is no long...

Multi-source domain adaptation through dataset dictionary learning in wasserstein space

Archive ouverte | Fernandes Montesuma, Eduardo | CCSD

International audience. This paper seeks to solve Multi-Source Domain Adaptation (MSDA), which aims to mitigate data distribution shifts when transferring knowledge from multiple labeled source domains to an unlabel...

Euclid: Nonparametric point spread function field recovery through interpolation on a graph Laplacian

Archive ouverte | Schmitz, M. A. | CCSD

International audience. Context. Future weak lensing surveys, such as the Euclid mission, will attempt to measure the shapes of billions of galaxies in order to derive cosmological information. These surveys will at...

Chargement des enrichissements...