Design of adaptive soft sensor based on Bayesian optimization
When adaptive soft sensors are introduced to industrial plants, an appropriate combination of the type of adaptation mechanism, hyperparameters of the mechanism, regression model, and hyperparameters of the model must be selected for predictive soft sensors. We propose an automatic and efficient sel...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-12-01
|
| Series: | Case Studies in Chemical and Environmental Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666016422000597 |
| _version_ | 1811185427891093504 |
|---|---|
| author | Shuto Yamakage Hiromasa Kaneko |
| author_facet | Shuto Yamakage Hiromasa Kaneko |
| author_sort | Shuto Yamakage |
| collection | DOAJ |
| description | When adaptive soft sensors are introduced to industrial plants, an appropriate combination of the type of adaptation mechanism, hyperparameters of the mechanism, regression model, and hyperparameters of the model must be selected for predictive soft sensors. We propose an automatic and efficient selection method for adaptive soft sensors based on Bayesian optimization. A Gaussian process regression model was constructed between the candidates of adaptive soft sensors and their predictive ability to perform Bayesian optimization. The adaptive soft-sensor candidate with the maximum acquisition value function was selected. The effectiveness of the proposed method was confirmed by analyzing two real industrial datasets. |
| first_indexed | 2024-04-11T13:30:31Z |
| format | Article |
| id | doaj.art-e5c454356d2f41d98e9a0610748111b3 |
| institution | Directory Open Access Journal |
| issn | 2666-0164 |
| language | English |
| last_indexed | 2024-04-11T13:30:31Z |
| publishDate | 2022-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Case Studies in Chemical and Environmental Engineering |
| spelling | doaj.art-e5c454356d2f41d98e9a0610748111b32022-12-22T04:21:52ZengElsevierCase Studies in Chemical and Environmental Engineering2666-01642022-12-016100237Design of adaptive soft sensor based on Bayesian optimizationShuto Yamakage0Hiromasa Kaneko1Department of Applied Chemistry, School of Science and Technology, Meiji University, 1-1-1 Higashi-Mita, Tama-ku, Kawasaki, Kanagawa, 214-8571, JapanCorresponding author.; Department of Applied Chemistry, School of Science and Technology, Meiji University, 1-1-1 Higashi-Mita, Tama-ku, Kawasaki, Kanagawa, 214-8571, JapanWhen adaptive soft sensors are introduced to industrial plants, an appropriate combination of the type of adaptation mechanism, hyperparameters of the mechanism, regression model, and hyperparameters of the model must be selected for predictive soft sensors. We propose an automatic and efficient selection method for adaptive soft sensors based on Bayesian optimization. A Gaussian process regression model was constructed between the candidates of adaptive soft sensors and their predictive ability to perform Bayesian optimization. The adaptive soft-sensor candidate with the maximum acquisition value function was selected. The effectiveness of the proposed method was confirmed by analyzing two real industrial datasets.http://www.sciencedirect.com/science/article/pii/S2666016422000597Soft sensorAdaptation mechanismRegressionHyperparameterBayesian optimization |
| spellingShingle | Shuto Yamakage Hiromasa Kaneko Design of adaptive soft sensor based on Bayesian optimization Case Studies in Chemical and Environmental Engineering Soft sensor Adaptation mechanism Regression Hyperparameter Bayesian optimization |
| title | Design of adaptive soft sensor based on Bayesian optimization |
| title_full | Design of adaptive soft sensor based on Bayesian optimization |
| title_fullStr | Design of adaptive soft sensor based on Bayesian optimization |
| title_full_unstemmed | Design of adaptive soft sensor based on Bayesian optimization |
| title_short | Design of adaptive soft sensor based on Bayesian optimization |
| title_sort | design of adaptive soft sensor based on bayesian optimization |
| topic | Soft sensor Adaptation mechanism Regression Hyperparameter Bayesian optimization |
| url | http://www.sciencedirect.com/science/article/pii/S2666016422000597 |
| work_keys_str_mv | AT shutoyamakage designofadaptivesoftsensorbasedonbayesianoptimization AT hiromasakaneko designofadaptivesoftsensorbasedonbayesianoptimization |