EUVIMEDEUVIMED entdecken
Crossref

Toward Lightweight Dynamic Convolutional Neural Network Modeling for Soft Sensors

Qiang Liu, Zhiqiang Zhan, Jingjing Wang, Chen Wang, S Joe Qin

IEEE Transactions on Cybernetics · 2026-04 · 56 (4) · 1958-1969

DOI: 10.1109/tcyb.2026.3662472 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Cybernetics, 2026-04. Verfasst von Qiang Liu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 67 Literaturangaben. Gefördert von: National Natural Science Foundation of China, General Research Fund of the Research Grants Council (RGC) of Hong Kong, SAR, China, Research Impact Fund by RGC of Hong Kong.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Soft sensors are essential for advanced monitoring and control to prevent undesirable operations and improve product quality. However, nonlinear, autocorrelated, and cross-correlated behaviors in industrial data demand concurrent modeling of the dynamics and nonlinearities. Deep learning-based soft sensors, such as recurrent neural network (RNN) and long short-term memory (LSTM) networks, often incorporate complex structures and numerous parameters, which can lead to an overly complex model. In practical applications where training data samples are limited, a lightweight neural network with strong generalization capability is preferred. With a simple structure of feed-forward layers of 1-D convolutional neural networks (CNNs) (1-D-CNN) for time-series data modeling, this article proposes a novel lightweight dynamic CNN (LDCNN) for soft sensors. Positional embedding (PE) and simplified temporal attention mechanisms are integrated for improved dynamic modeling, while dilated convolutions and layer normalization (LN) are incorporated to significantly reduce the depth and width of the network and avoid over-parametrization. Experimental results on a real industrial case indicate that a lightweight model outperforms the traditional methods with limited training samples.

Förderung

  • National Natural Science Foundation of China
  • General Research Fund of the Research Grants Council (RGC) of Hong Kong, SAR, China
  • Research Impact Fund by RGC of Hong Kong

Zitieren

APA

Liu, Q., Zhan, Z., Wang, J., Wang, C., & Qin, S. J. (2026). Toward Lightweight Dynamic Convolutional Neural Network Modeling for Soft Sensors. IEEE Transactions on Cybernetics, 56(4), 1958-1969. https://doi.org/10.1109/tcyb.2026.3662472

Vancouver

Liu Q, Zhan Z, Wang J, Wang C, Qin SJ. Toward Lightweight Dynamic Convolutional Neural Network Modeling for Soft Sensors. IEEE Transactions on Cybernetics. 2026;56(4):1958-1969. doi:10.1109/tcyb.2026.3662472

BibTeX
@article{Liu2026,
  author = {Liu, Qiang and Zhan, Zhiqiang and Wang, Jingjing and Wang, Chen and Qin, S Joe},
  title = {Toward Lightweight Dynamic Convolutional Neural Network Modeling for Soft Sensors},
  journal = {IEEE Transactions on Cybernetics},
  year = {2026},
  volume = {56},
  number = {4},
  pages = {1958--1969},
  doi = {10.1109/tcyb.2026.3662472}
}
Kostenlos starten →