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

Eduardo Fernandes Montesuma, Michela Mulas, Francesco Corona, Fred Maurice Ngole Mboula

Research output: Contribution to journalConference articleScientificpeer-review

2 Citations (Scopus)
113 Downloads (Pure)

Abstract

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.

Original languageEnglish
Pages (from-to)946-951
Number of pages6
JournalIFAC-PapersOnLine
Volume55
Issue number7
DOIs
Publication statusPublished - 5 Aug 2022
MoE publication typeA4 Conference publication
EventIFAC Symposium on Dynamics and Control of Process Systems, including Biosystems - Busan, Korea, Republic of
Duration: 14 Jun 202217 Jun 2022
Conference number: 13

Keywords

  • Fault Diagnosis
  • Optimal Transport
  • Transfer Learning

Fingerprint

Dive into the research topics of 'Cross-domain fault diagnosis through optimal transport for a CSTR process'. Together they form a unique fingerprint.

Cite this