Dynamic Interval-Valued PCA for Enhanced Fault Detection

This study introduces three novel dynamic interval-valued principal component analysis (DIPCA) methods: dynamic centers PCA (D-CPCA), dynamic vertices PCA (D-VPCA), and dynamic complete information PCA (D-CIPCA). These methods advance traditional interval-valued PCA (IPCA) by integrating dynamic asp...

Full description

Saved in:
Bibliographic Details
Published inInternational Conference on Control, Decision and Information Technologies (Online) pp. 2911 - 2916
Main Authors Rouani, Lahcene, Harkat, Mohamed Faouzi, Kouadri, Abdelmalek, Bensmail, Abderazak, Mansouri, Majdi, Nounou, Mohamed
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.07.2024
Subjects
Accuracy
Aerodynamics
Cement industry
dynamic process
Fault detection
Indexes
interval-valued data
Principal component analysis
principal component analysis (PCA)
Process monitoring
Real-time systems
Robustness
Uncertainty
Online AccessGet full text

Cover

More Information
Summary:This study introduces three novel dynamic interval-valued principal component analysis (DIPCA) methods: dynamic centers PCA (D-CPCA), dynamic vertices PCA (D-VPCA), and dynamic complete information PCA (D-CIPCA). These methods advance traditional interval-valued PCA (IPCA) by integrating dynamic aspects of industrial processes, thus addressing both data uncertainties and temporal correlations. The DIPCA methods were validated using real-world data from the Ain El Kebira cement plant. Results indicate significant improvements in fault detection accuracy, achieving lower false alarm rates and higher reliability compared to classical IPCA methods. Furthermore, an enhanced combined index for interval-valued data was developed, providing a single, comprehensive statistical measure for streamlined process monitoring.
ISSN:2576-3555
DOI:10.1109/CoDIT62066.2024.10708428