Affiliation:
1. Department of Chemical Engineering , National Institute of Technology Rourkela , Odisha 769008 , India
Abstract
Abstract
Partial Least Squares (PLS) is a supervised multivariate statistical/machine learning technique, which is used for classification and identification/authentication of a variety of operating conditions in tomato juice concentrator/evaporator, yeast fermentation bioreactor and fluid catalytic cracking process plants. Data for the three processes were generated pertaining to different operating conditions (for each of them) including faulty ones by simulating their mechanistic models over 25 h. The simulated data at transient conditions were chosen for further processing. They were divided into training and testing data pools. After training, the developed PLS model could classify various process operating conditions 100 % accurately and identify unknown process operating conditions (simulated using training pool with certain degree of variations in them) pertaining to the processes.
Subject
Modeling and Simulation,General Chemical Engineering
Reference20 articles.
1. Wold, S, Sjöström, M, Eriksson, L. PLS-regression: a basic tool of chemometrics. Chemometr Intell Lab Syst 2001;58:109–30. https://doi.org/10.1016/s0169-7439(01)00155-1.
2. Wold, H. Estimation of principal components and related models by iterative least squares. In: Krishnaiah, PR, editor. MultiVariate analysis II. New York: Academic Press; 1966:391–420 pp.
3. Zhang, J-N, Luo, A-L, Zhao, Y-H. Automated estimation of stellar fundamental parameters from low resolution spectra: the PLS method, Research in Astron. Astrophys Nor 2009;9:712–24. https://doi.org/10.1088/1674-4527/9/6/010.
4. Karp, N, Griffin, J, Lilley, K. Application of Partial Least Squares discriminant analysis to two-dimensional difference gel studies in expression proteomics. Proteomics 2005;5:81–90. https://doi.org/10.1002/pmic.200400881.
5. Oliver, P, Whelehan, ME, Earll, EJ, Marianne, T, Eriksson, L. Detection of ovarian cancer using chemometric analysis of proteomic profiles. Chemometr Intell Lab Syst 2006;84:82–7. https://doi.org/10.1016/j.chemolab.2006.03.008.