Bidirectional sparse principal component analysis for process monitoring
The Canadian Journal of Chemical Engineering · 2026-05 · 104 (5) · 2515-2530
DOI: 10.1002/cjce.70163 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Canadian Journal of Chemical Engineering, online erschienen am 19.11.2025. Verfasst von Jinziyuan Lv und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 31 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Sparse principal component analysis (SPCA) was proposed to strengthen the interpretability of traditional PCA. However, SPCA remains “semi‐sparse” due to the lack of sparsity in its regression coefficient matrix, which can reduce the interpretability and accuracy of process monitoring results. To address this issue, we propose bidirectional SPCA (BSPCA). To solve the BSPCA modelling challenges, we investigate the matrix structure features and propose an improved particle swarm optimization (IPSO) strategy. Testing on the Tennessee Eastman process demonstrates that BSPCA significantly improves sparsity by eliminating less important relationships between variables. In addition, BSPCA is able to pinpoint specific faults in the relevant process variables, thus highlighting its diagnostic effectiveness.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Lv, J., Wang, J., Lou, Z., Jin, X., Lu, S., & Lan, Y. (2026). Bidirectional sparse principal component analysis for process monitoring. The Canadian Journal of Chemical Engineering, 104(5), 2515-2530. https://doi.org/10.1002/cjce.70163
Vancouver
Lv J, Wang J, Lou Z, Jin X, Lu S, Lan Y. Bidirectional sparse principal component analysis for process monitoring. The Canadian Journal of Chemical Engineering. 2026;104(5):2515-2530. doi:10.1002/cjce.70163
BibTeX
@article{Lv2026,
author = {Lv, Jinziyuan and Wang, Jing and Lou, Zhijiang and Jin, Xin and Lu, Shan and Lan, Yungang},
title = {Bidirectional sparse principal component analysis for process monitoring},
journal = {The Canadian Journal of Chemical Engineering},
year = {2026},
volume = {104},
number = {5},
pages = {2515--2530},
doi = {10.1002/cjce.70163}
}
EUVIMED