1
|
Zou T, Yajima T, Kawajiri Y. A parameter estimation method for chromatographic separation process based on physics-informed neural network. J Chromatogr A 2024; 1730:465077. [PMID: 38879976 DOI: 10.1016/j.chroma.2024.465077] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/17/2024] [Revised: 06/08/2024] [Accepted: 06/10/2024] [Indexed: 06/18/2024]
Abstract
Chromatographic separation processes are most often modeled in the form of partial differential equations (PDEs) to describe the complex adsorption equilibria and kinetics. However, identifying parameters in such a model requires substantial computational effort. In this work, a novel parameter estimation approach using a Physics-informed Neural Network (PINN) model is developed and tested for a binary component system. Numerical accuracy of our PINN model is confirmed by validating its simulations against those of the finite element method (FEM). Furthermore, model parameters in the kinetic model are estimated by the PINN model with sufficient accuracy from the observed data at the column outlet, where parameter fitting error can be reduced by up to 35.0 % from the conventional method. In a comparison with the conventional numerical method, our approach can reduce the computational time by up to 95 %. The robustness of the PINN model has also been demonstrated by estimating model parameters from noisy artificial experimental data.
Collapse
Affiliation(s)
- Tao Zou
- Department of Materials Process Engineering, Nagoya University, Furo-cho 1, Chikusa, Nagoya, Aichi, 464-8603 Japan
| | - Tomoyuki Yajima
- Department of Materials Process Engineering, Nagoya University, Furo-cho 1, Chikusa, Nagoya, Aichi, 464-8603 Japan
| | - Yoshiaki Kawajiri
- Department of Materials Process Engineering, Nagoya University, Furo-cho 1, Chikusa, Nagoya, Aichi, 464-8603 Japan; School of Engineering Science, LUT University, Mukkulankatu 19, 15210 Lahti, Finland.
| |
Collapse
|
2
|
Estimation and statistical analysis of model parameters using sequential Monte Carlo for phenol and p-cresol separation. J Chromatogr A 2023; 1688:463703. [PMID: 36528903 DOI: 10.1016/j.chroma.2022.463703] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/07/2022] [Revised: 11/26/2022] [Accepted: 12/05/2022] [Indexed: 12/12/2022]
Abstract
Model-based design and optimization methods facilitate industrial applications of chromatographic separations. The uncertainty of the model parameters must be quantified to ensure robust design and control. In this study, we propose an approach using the sequential Monte Carlo (SMC) method based on the Bayesian principle to estimate the uncertainty of the parameters. The linear driving force model for separation of phenol and p-cresol was considered as an example. By comparing different injection tests, we confirmed the necessity of pulse injection and breakthrough experiments to estimate parameters with sufficient accuracy and precision. We also found that modeling observation errors carefully is critical to obtain reasonable estimation.
Collapse
|
3
|
Harada H, Suzuki K, Sato K, Okada K, Tsuruta M, Yajima T, Kawajiri Y. Process development for advanced simulated moving bed (ASMB) chromatography by parameter refinement using pilot plant experimental data. Sep Purif Technol 2022. [DOI: 10.1016/j.seppur.2021.119932] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
|
4
|
Yamamoto Y, Yajima T, Kawajiri Y. Uncertainty quantification for chromatography model parameters by Bayesian inference using sequential Monte Carlo method. Chem Eng Res Des 2021. [DOI: 10.1016/j.cherd.2021.09.003] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
|
5
|
Santos RVA, Prudente AN, Ribeiro AM, Rodrigues AE, Loureiro JM, Martins MAF, Pontes KV, Nogueira IBR. Global Approach for Simulated Moving Bed Model Identification: Design of Experiments, Uncertainty Evaluation, and Optimization Strategy Assessment. Ind Eng Chem Res 2021. [DOI: 10.1021/acs.iecr.1c01276] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Affiliation(s)
- Rodrigo V. A. Santos
- Programa de Pós-Graduação em Engenharia Industrial (Industrial Engineering Program), Escola Politécnica (Polytechnique Institute), Universidade Federal da Bahia, 40210-630 Salvador, Bahia, Brazil
- Laboratory of Separation and Reaction Engineering, Associate Laboratory LSRE-LCM, Department of Chemical Engineering, Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal
| | - Anderson N. Prudente
- Programa de Pós-Graduação em Engenharia Industrial (Industrial Engineering Program), Escola Politécnica (Polytechnique Institute), Universidade Federal da Bahia, 40210-630 Salvador, Bahia, Brazil
| | - Ana M. Ribeiro
- Laboratory of Separation and Reaction Engineering, Associate Laboratory LSRE-LCM, Department of Chemical Engineering, Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal
| | - Alírio E. Rodrigues
- Laboratory of Separation and Reaction Engineering, Associate Laboratory LSRE-LCM, Department of Chemical Engineering, Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal
| | - José M. Loureiro
- Laboratory of Separation and Reaction Engineering, Associate Laboratory LSRE-LCM, Department of Chemical Engineering, Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal
| | - Márcio A. F. Martins
- Programa de Pós-Graduação em Engenharia Industrial (Industrial Engineering Program), Escola Politécnica (Polytechnique Institute), Universidade Federal da Bahia, 40210-630 Salvador, Bahia, Brazil
| | - Karen V. Pontes
- Programa de Pós-Graduação em Engenharia Industrial (Industrial Engineering Program), Escola Politécnica (Polytechnique Institute), Universidade Federal da Bahia, 40210-630 Salvador, Bahia, Brazil
| | - Idelfonso B. R. Nogueira
- Laboratory of Separation and Reaction Engineering, Associate Laboratory LSRE-LCM, Department of Chemical Engineering, Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal
| |
Collapse
|
6
|
Barz T, López C. DC, Cruz Bournazou MN, Körkel S, Walter SF. Real-time adaptive input design for the determination of competitive adsorption isotherms in liquid chromatography. Comput Chem Eng 2016. [DOI: 10.1016/j.compchemeng.2016.07.009] [Citation(s) in RCA: 16] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
|
7
|
Sreedhar B, Kawajiri Y. Multi-column chromatographic process development using simulated moving bed superstructure and simultaneous optimization – Model correction framework. Chem Eng Sci 2014. [DOI: 10.1016/j.ces.2014.05.004] [Citation(s) in RCA: 19] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
|
8
|
Systematic optimization and experimental validation of ternary simulated moving bed chromatography systems. J Chromatogr A 2014; 1356:82-95. [DOI: 10.1016/j.chroma.2014.06.028] [Citation(s) in RCA: 19] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/21/2014] [Revised: 06/05/2014] [Accepted: 06/08/2014] [Indexed: 11/19/2022]
|
9
|
Bentley J, Sloan C, Kawajiri Y. Simultaneous modeling and optimization of nonlinear simulated moving bed chromatography by the prediction–correction method. J Chromatogr A 2013; 1280:51-63. [DOI: 10.1016/j.chroma.2013.01.026] [Citation(s) in RCA: 18] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/28/2012] [Revised: 01/03/2013] [Accepted: 01/05/2013] [Indexed: 10/27/2022]
|
10
|
Bentley J, Kawajiri Y. Prediction-correction method for optimization of simulated moving bed chromatography. AIChE J 2012. [DOI: 10.1002/aic.13856] [Citation(s) in RCA: 26] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Affiliation(s)
- Jason Bentley
- School of Chemical and Biomolecular Engineering; Georgia Institute of Technology; Atlanta; GA; 30332
| | - Yoshiaki Kawajiri
- School of Chemical and Biomolecular Engineering; Georgia Institute of Technology; Atlanta; GA; 30332
| |
Collapse
|
11
|
Vilas C, Vande Wouwer A. Combination of multi-model predictive control and the wave theory for the control of simulated moving bed plants. Chem Eng Sci 2011. [DOI: 10.1016/j.ces.2010.11.022] [Citation(s) in RCA: 10] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
|
12
|
Grosfils V, Hanus R, Wouwer AV, Kinnaert M. Parametric uncertainties and influence of the dead volume representation in modelling simulated moving bed separation processes. J Chromatogr A 2010; 1217:7359-71. [DOI: 10.1016/j.chroma.2010.09.030] [Citation(s) in RCA: 13] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/01/2010] [Revised: 09/05/2010] [Accepted: 09/08/2010] [Indexed: 11/24/2022]
|
13
|
Szabelski P, Kaczmarski K. Phenomenological modeling of separation of enantiomers by nonlinear chromatography. ACTA CHROMATOGR 2008. [DOI: 10.1556/achrom.20.2008.4.1] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022]
|