The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Sub‐PCA modeling and on‐line monitoring strategy for batch processes
Open accessAbstract
Multivariate statistical methods such as principal component analysis (PCA) and partial least square (PLS) have been successfully used in modeling multivariable continuous processes (Kaspar and Ray, 1992; Kourti and MacGregor, 1995; Chen and McAvoy, 1998). Several extensions of the conventional PCA/PLS to batch processes have also been reported, among which multiway PCA (MPCA) model is the most widely used (Wold et al., 1987; Nomikos and MacGregor, 1994, 1995; Wise et al., 1999; Smilde, 2001). The MPCA model is ill-suited for multistage batch processes, as it takes the entire batch data as a single object, and it is difficult to reveal the changes of process correlation from stage to stage. Considering that the multiplicity of the operation stage is an inherent nature of many batch processes, each stage has its own underlying characteristics and the process can exhibit significantly different behaviors over different operation stages; it is desirable to develop a stage-based model that can reflect the inherent process stage nature to improve the process understanding and monitoring efficiency. Kosanovich et al. (1994) and Dong and McAvoy (1995) developed two MPCA/nonlinear MPCA models, utilizing the two-stage nature of a jacketed exothermic batch chemical reactor. Their results show that the two-stage models are more powerful than a single model. Their stage models, however, inherit the common weakness of the MPCA model that the unavailable future data in an evolving batch should be estimated for on-line monitoring. A new stage-based sub-PCA modeling method is proposed in this article for multistage batch processes, based on the recognition of the following: (1) a batch process may be divided into several "operation" stages reflecting its inherent process correlation nature; (2) despite that the process may be time varying, the correlation of its variables will be largely similar within the same "operation" stage. Changes in the correlation may be used to indicate changes in the process "operation" stages. We have placed a quotation mark around "operation" to indicate that the operation referred to in this article may not, and does not have to, have the exact correspondence to the physical operations of the process. Based on the above recognition, a representative model can be built for each stage, using the conventional two-way PCA model. This allows two-way PCA to be "directly" applied to a batch process after a proper stage division; a stage division algorithm is also developed in the article. A three-tank process, as an experimental verification system, is finally introduced to illustrate the effectiveness of the proposed. Consider a batch process with J process variables measured over sampling points k (k = 1, 2, …, K); a data matrix of dimensions J × K is generated from each batch run. A set of I number of normal batch runs, hence, result in a three-way process data matrix, X(I × J × K), which is the most popular data form for batch processes. The horizontal slice X(J × K) is the data matrix from each batch run. The vertical slice (I × J), a time-slice matrix that is the basic unit in the proposed modeling method, is used to obtain the process correlation at sampling time k. In PCA analysis, the loading matrix represents the information of the process correlation. The stage-based sub-PCA modeling begins with analyzing the loading matrix at each sampling interval. The time-slice matrices k will have a similar loading matrix within each "operation" stage. Different "operation" stage results in different loading matrices, reflecting that process correlation changes over different stages. Likewise, changes in the loading matrices, reflecting changes in the underlying process behavior, can be used to determine the "operation" stages. The k-means clustering will be adopted and modified to partition the K number of loading matrices. The clustering results, associated with process time span or indicator variables, can be used to define process "operation" stages. The Euclidean distance, the most popular metric, can be used to calculate the dissimilarity between two patterns. A variant k-means algorithm (Jain et al., 1999) is adopted for partitioning the K number of patterns k (k = 1, 2, …, K) to determine the optimal number of final clusters by minimizing the local squared error (for patterns within each cluster) and the global squared error (for all the patterns) by specifying a threshold θ of the minimal distance between two clusters' centers, or the maximal radius of a cluster. This algorithm transforms modeling accuracy and complexity into the specification of the threshold. A large threshold results in few clusters, but less accurate modeling. A step is added in the clustering algorithm to eliminate singular clusters that catch few patterns in the iterative clustering procedure to enhance the robustness and reliability of the partition algorithm. The above improved k-means clustering algorithm can group
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Jain, A. K., Murty, M. N., & Flynn, P. J. (1999) · ACM Computing Surveys · doi:10.1145/331499.331504 · Cited by 13,199
Wold, S., Esbensen, K., & Geladi, P. (1987) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/0169-7439(87)80084-9 · Cited by 11,606
A User's Guide to Principal Components
Leigh, S., & Jackson, J. E. (1993) · Technometrics · doi:10.2307/1269292 · Cited by 3,332
A Use's Guide to Principal Components
Jackson, J. E. (1991) · Wiley Series in Probability and Statistics · doi:10.1002/0471725331 · Cited by 2,516
Monitoring batch processes using multiway principal component analysis
Nomikos, P., & MacGregor, J. F. (1994) · AIChE Journal · doi:10.1002/aic.690400809 · Cited by 1,483
Multivariate SPC Charts for Monitoring Batch Processes
Nomikos, P., & MacGregor, J. F. (1995) · Technometrics · doi:10.1080/00401706.1995.10485888 · Cited by 1,422
Control Procedures for Residuals Associated With Principal Component Analysis
Jackson, J. E., & Mudholkar, G. S. (1979) · Technometrics · doi:10.1080/00401706.1979.10489779 · Cited by 1,237
Process analysis, monitoring and diagnosis, using multivariate projection methods
Kourti, T. (1995) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/0169-7439(94)00079-x · Cited by 780
Wise, B. M., Gallagher, N. B., Butler, S. W., White, D. D., & Barna, G. G. (1999) · Journal of Chemometrics · doi:10.1002/(sici)1099-128x(199905/08)13:3/4<379::aid-cem556>3.0.co;2-n · Cited by 296
Chemometric methods for process monitoring and high‐performance controller design
Kaspar, M. H., & Ray, W. H. (1992) · AIChE Journal · doi:10.1002/aic.690381010 · Cited by 121
Cited by
Review of Recent Research on Data-Based Process Monitoring
Ge, Z., Song, Z., & Gao, F. (2013) · Industrial & Engineering Chemistry Research · doi:10.1021/ie302069q · Cited by 967
Self-citationGeometric properties of partial least squares for process monitoring
Li, G., Qin, S. J., & Zhou, D. (2010) · Automatica · doi:10.1016/j.automatica.2009.10.030 · Cited by 368
Challenges in the Development of Soft Sensors for Bioprocesses: A Critical Review
Brunner, V., Siegl, M., Geier, D., & Becker, T. (2021) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2021.722202 · Cited by 100
Metadata
- Authors
- Lu, N., Gao, F., & Wang, F.
- Venue
- AIChE Journal
- Publisher
- Wiley
- Published
- 2004-01
- Volume
- 50
- Issue
- 1
- Pages
- 255-259
- ISSN
- 0001-1541 (ISSN-L)
- 1547-5905
- OpenAlex
- W2039243482
- Cited by
- 267
- References
- 10
- FWCI
- 12.85
- Type
- journal article
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Sub‐PCA modeling and on‐line monitoring strategy for batch processes. https://app.cochat.ai/papers/10.1002/aic.10024
- The paper
- Lu, N., Gao, F., & Wang, F. (2004). Sub‐PCA modeling and on‐line monitoring strategy for batch processes. AIChE Journal. https://doi.org/10.1002/aic.10024
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.