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

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

doi:10.1016/j.ifacol.2022.07.566

Cited by 3 publications

(3 citation statements)

References 121 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We set the fault categories in accordance with Table 7, [ 38 ] which includes a number of typical fault scenarios, including process faults and sensor faults. In the source domain, we prepare 100 labelled fault samples for each category (containing nine fault kinds and one normal operation) for each process, while 20 fault samples are gathered for each category in the six target domains.…”

Section: Methodsmentioning

confidence: 99%

“…The result of the blocks division is shown in Table 6. As in the work of Montesuma et al, [ 38 ] we mimic changes in operating conditions using parameter offsets and modifications to the reaction sequence. To be more precise, we add the parametric error

ε

to the six parameters, making them

{\overset{θ}{true}}_{i} = θ_{i} + Δ θ_{i}

, where

Δ θ_{i} : U (- ε, ε)

.…”

Section: Methodsmentioning

confidence: 99%

“…The result of the blocks division is shown in Table 6. As in the work of Montesuma et al, [38] F I G U R E 4 Process variables and parameters. TC, jacket coolant.…”

Section: Continuous Stirred Tank Reactionmentioning

confidence: 99%

See 2 more Smart Citations

Joint alignment network preserving structural information for multimode process fault diagnosis

Tan,

Xu,

Shi

et al. 2023

Can J Chem Eng

View full text Add to dashboard Cite

Production conditions are complex and varied for a number of reasons. Models for defect diagnosis may perform worse as a result of the distributional mismatch between test data and training data. In order to diagnose process faults, it is crucial to take into account the fact that data exhibits varied distribution characteristics under various conditions. In the case of multiple operating conditions, the cross‐domain problem caused by different data distributions can degrade the performance of deep learning‐based fault diagnosis models. To overcome this challenge, a joint alignment network preserving structural information (JANSI) method is proposed. To extract richer and fine‐grained domain‐invariant features, the structural information preservation is proposed, which combines domain labels, category labels, and data distribution structures. To increase intra‐class compactness and inter‐class separability, class centre alignment is proposed. The effectiveness of the method on the cross‐domain unsupervised fault diagnosis problem is verified through three case studies.

show abstract

Section: Methodsmentioning

confidence: 99%