Sequential Fault Detection and Classification in Chemical Process Using a Deep Convolutional Encoder-Decoder Architecture Based on System Dynamics

In this paper, we propose a high-level spatiotemporal feature extraction based on deep convolutional bidirectional encoder-decoder representation network with gated recurrent unit (GRU) cell for dynamic fault diagnosis. Although traditional recurrent neural networks (RNNs) have a major issue with ex...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IOP conference series. Earth and environmental science Ročník 696; číslo 1; s. 12052
Hlavní autoři: Wang, Qiao, Luo, Lin
Médium: Journal Article
Jazyk:angličtina
Vydáno: Bristol IOP Publishing 01.03.2021
Témata:
Classification
Coders
Encoders-Decoders
Fault detection
Fault diagnosis
Feature extraction
Long short-term memory
Neural networks
Recurrent neural networks
Representations
Spatial dependencies
System dynamics
ISSN:1755-1307, 1755-1315
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In this paper, we propose a high-level spatiotemporal feature extraction based on deep convolutional bidirectional encoder-decoder representation network with gated recurrent unit (GRU) cell for dynamic fault diagnosis. Although traditional recurrent neural networks (RNNs) have a major issue with extracting the spatial dependencies, temporal convolutional operation is designed to extract the local features which provide insight into different types of faults. The system dynamics are further extracted with the context by the bidirectional encoder-decoder network, which distils the representations from future time steps. Moreover, GRU cell in both encoder and decoder deploys a more compact structure than a usual RNNs network due to the reduction of gates. The resulting deep network is not only generalizing the importance of temporal feature, but it also allows the interpretable feature representation and classification simultaneously. Detailed comparative case study on the benchmark Tennessee Eastman process demonstrates that the proposed method is competitive with the classical long-short term memory (LSTM) network for the fault detection and diagnosis.
Bibliografie:ObjectType-Conference Proceeding-1
SourceType-Scholarly Journals-1
content type line 14
ISSN:1755-1307
1755-1315
DOI:10.1088/1755-1315/696/1/012052