Smart filter aided domain adversarial neural network for fault diagnosis in noisy industrial scenarios

Dai, Baorui; Frusque, Gaëtan; Li, Tianfu; Li, Qi; Fink, Olga

doi:10.1016/j.engappai.2023.107202

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

Publication Types

Select...

Article3

Other2

Relationship

Self Cite0

Independent5

Authors

Journals

Cited by 7 publications

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Variational autoencoder based on knowledge sharing and correlation weighting for process-quality concurrent fault detection

Wang,

2024

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

Variational autoencoder based on knowledge sharing and correlation weighting for process-quality concurrent fault detection

Wang,

2024

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

An unsupervised learning framework for health diagnosis by incorporating multiscale data

Fang,

Zhu,

Zhang

et al. 2024

Structures

View full text Add to dashboard Cite

An enhanced meta-learning network with sensitivity penalty for cross-domain few-shot fault diagnosis

Mu,

Jiang,

Jiang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Big data-driven rotating machine intelligent diagnostic technology has gained widespread applications. In practice, however, fault data are limited as well as inconsistencies in fault categories among different domains are widespread. These make developing robust intelligent diagnostic models a challenge. To this end, this paper develops an enhanced meta-learning network with a sensitivity penalization mechanism (EMLN-SP) for few-shot fault diagnosis in severe domain bias. First, lightweight channel attention is introduced to establish an enhanced feature encoder under meta-learning framework, which elevates the key feature expression to facilitate the extraction of generalized diagnostic knowledge within limited samples. Second, a boundary-enhanced loss calculation method is designed, which boosts the focus for decision boundary information to prevent the model from the overfitting dilemma in the case of few-shot. Finally, a sensitivity penalty mechanism is constructed to adjust the optimization direction, which prevents the model from falling into a local optimum, to boost the generalization of the model performance. The effectiveness of EMLN-SP is validated by three cross-domain diagnostic cases with diverse domain offsets.

show abstract

Smart filter aided domain adversarial neural network for fault diagnosis in noisy industrial scenarios

Cited by 7 publications

References 31 publications

Variational autoencoder based on knowledge sharing and correlation weighting for process-quality concurrent fault detection

Variational autoencoder based on knowledge sharing and correlation weighting for process-quality concurrent fault detection

An unsupervised learning framework for health diagnosis by incorporating multiscale data

An enhanced meta-learning network with sensitivity penalty for cross-domain few-shot fault diagnosis

Contact Info

Product

Resources

About