An industrial process monitoring method based on fusion of multi-scale sparse autoencoder and dual-branch slow feature architecture

•MSAE-DSFA merges multi-scale sparse AEs and dual slow feature for monitoring.•Tackles info redundancy, nonlinearity and slow faults in industrial processes.•Enhances fault detection and outperforms similar methods in two industrial cases.•Delivers solutions and support for process safety and optimi...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Chemical engineering science Ročník 321; s. 122924
Hlavní autoři: Ling, Guobi, Wang, Zhiwen, Wang, Jieying, Shi, Yaoke, Li, Long, Zeng, Jingxiao
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 01.02.2026
Témata:
Dual-branch slow feature structure
Feature extraction
Multi-scale sparse autoencoder
Process monitoring
Whitening operation
Process monitoring
Whitening operation
Feature extraction
Dual-branch slow feature structure
Multi-scale sparse autoencoder
ISSN:0009-2509
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•MSAE-DSFA merges multi-scale sparse AEs and dual slow feature for monitoring.•Tackles info redundancy, nonlinearity and slow faults in industrial processes.•Enhances fault detection and outperforms similar methods in two industrial cases.•Delivers solutions and support for process safety and optimization. With the increasing duration of operation, factors such as process parameters, operating conditions, and environmental variables in industrial processes gradually change, leading to variations in the correlations among process variables. The complexity of process data, characterized by high-dimensional redundancy, nonlinear correlations, noise interference, and slow-varying fault characteristics, poses significant challenges for unsupervised fault detection. Therefore, this article proposes an industrial process monitoring method based on fusion of multi-scale sparse autoencoder and dual-branch slow feature architecture (MSAE-DSFA). In the first stage, the original data is mapped to different dimensions through a multi-scale whitening-sparse encoder, capturing features from local details to global structures. This approach addresses the limitations of single-scale representation capabilities and eliminates issues related to process feature redundancy and decorrelation. Simultaneously, in the second stage, a primary-secondary slow feature extraction method is designed to capture the temporal stability characteristics of latent features from the previous stage, further mitigating environmental noise and other factors while extracting slowly changing latent representations to ensure sensitivity to progressive anomalies. Finally, based on the latent space and reconstruction error, statistical measures are calculated. The features extracted by the MSAE-DSFA method contain crucial information about the operational process, with reconstructed data demonstrating closer alignment to actual industrial processes. Experimental validation is conducted on two industrial cases.
ISSN:0009-2509
DOI:10.1016/j.ces.2025.122924