Batch process monitoring based on multilevel ICA-PCA

• Published in: Journal of Zhejiang University. A. Science 2008-08, Vol.9 (8), p.1061-1069
• Main Authors: Ge, Zhi-qiang, Song, Zhi-huan
• Format: Article
• Language: English
• Subjects: Civil Engineering; Classical and Continuum Physics; Engineering; Industrial Chemistry/Chemical Engineering; Mechanical Engineering; 独立成分分析; 监视系统; 自动控制理论; 计算机
• ISSN: 1673-565X; 1862-1775
• DOI: 10.1631/jzus.A0720051

In this paper, we describe a new batch process monitoring method based on multilevel independent component analysis and principal component analysis （MLICA-PCA）. Unlike the conventional multi-way principal component analysis （MPCA） method, MLICA-PCA provides a separated interpretation for multilevel batch process data. Batch process data are partitioned into two levels： the within-batch level and the between-batch level. In each level, the Gaussian and non-Gaussian components of process information can be separately extracted.I^2 T^2 and SPE statistics are individually built and monitored. The new method facilitates fault diagnosis. Since the two variation levels are decomposed, the variables responsible for faults in each level can be identified and interpreted more easily. A case study of the Dupont benchmark process showed that the proposed method was more efficient and interpretable in fault detection and diagnosis, compared to the alternative batch process monitoring method.