Moving-window GPR for nonlinear dynamic system modeling with dual updating and dual preprocessing
The characteristics of nonlinearity and time-varying changes in most industrial processes usually cripple the predictive performance of conventional soft sensors. In this article, moving-window Gaussian process regression (MWGPR) is proposed to effectively capture the process dynamics and to model n...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2013
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/105944 http://hdl.handle.net/10220/16749 http://dx.doi.org/10.1021/ie201898a |
| _version_ | 1826113565712449536 |
|---|---|
| author | Ni, Wangdong Tan, Soon Keat Ng, Wun Jern Brown, Steven D. |
| author2 | School of Civil and Environmental Engineering |
| author_facet | School of Civil and Environmental Engineering Ni, Wangdong Tan, Soon Keat Ng, Wun Jern Brown, Steven D. |
| author_sort | Ni, Wangdong |
| collection | NTU |
| description | The characteristics of nonlinearity and time-varying changes in most industrial processes usually cripple the predictive performance of conventional soft sensors. In this article, moving-window Gaussian process regression (MWGPR) is proposed to effectively capture the process dynamics and to model nonlinearity simultaneously. Applications of the proposed MWGPR method to the modeling of the activity of a catalyst and an industrial propylene polymerization process are presented. The results clearly demonstrate that the MWGPR method effectively tracks the process changes to generate satisfactory predictive performance. Two modeling strategies, namely, dual updating and dual preprocessing, are applied to MWGPR, in an attempt to more efficiently track the process dynamics. Dual updating takes into account both the time-varying variance of the process and the bias between the actual measurement and the model prediction. The improvement in performance is illustrated by a case study on modeling catalyst activity. Simultaneous removal of embedded noise in both process parameters and process output variables by dual preprocessing could significantly improve the predictive capability of MWGPR, as illustrated by the performance of a modeling study of an industrial propylene polymerization process. |
| first_indexed | 2024-10-01T03:25:18Z |
| format | Journal Article |
| id | ntu-10356/105944 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:25:18Z |
| publishDate | 2013 |
| record_format | dspace |
| spelling | ntu-10356/1059442019-12-06T22:01:14Z Moving-window GPR for nonlinear dynamic system modeling with dual updating and dual preprocessing Ni, Wangdong Tan, Soon Keat Ng, Wun Jern Brown, Steven D. School of Civil and Environmental Engineering Maritime Research Centre Nanyang Environment and Water Research Institute DRNTU::Engineering::Civil engineering::Water resources The characteristics of nonlinearity and time-varying changes in most industrial processes usually cripple the predictive performance of conventional soft sensors. In this article, moving-window Gaussian process regression (MWGPR) is proposed to effectively capture the process dynamics and to model nonlinearity simultaneously. Applications of the proposed MWGPR method to the modeling of the activity of a catalyst and an industrial propylene polymerization process are presented. The results clearly demonstrate that the MWGPR method effectively tracks the process changes to generate satisfactory predictive performance. Two modeling strategies, namely, dual updating and dual preprocessing, are applied to MWGPR, in an attempt to more efficiently track the process dynamics. Dual updating takes into account both the time-varying variance of the process and the bias between the actual measurement and the model prediction. The improvement in performance is illustrated by a case study on modeling catalyst activity. Simultaneous removal of embedded noise in both process parameters and process output variables by dual preprocessing could significantly improve the predictive capability of MWGPR, as illustrated by the performance of a modeling study of an industrial propylene polymerization process. 2013-10-23T07:55:35Z 2019-12-06T22:01:14Z 2013-10-23T07:55:35Z 2019-12-06T22:01:14Z 2012 2012 Journal Article Ni, W., Tan, S. K., Ng, W. J., & Brown, S. D. (2012). Moving-Window GPR for Nonlinear Dynamic System Modeling with Dual Updating and Dual Preprocessing. Industrial & Engineering Chemistry Research, 51(18), 6416-6428. 0888-5885 https://hdl.handle.net/10356/105944 http://hdl.handle.net/10220/16749 http://dx.doi.org/10.1021/ie201898a en Industrial & engineering chemistry research © 2012 American Chemical Society |
| spellingShingle | DRNTU::Engineering::Civil engineering::Water resources Ni, Wangdong Tan, Soon Keat Ng, Wun Jern Brown, Steven D. Moving-window GPR for nonlinear dynamic system modeling with dual updating and dual preprocessing |
| title | Moving-window GPR for nonlinear dynamic system modeling with dual updating and dual preprocessing |
| title_full | Moving-window GPR for nonlinear dynamic system modeling with dual updating and dual preprocessing |
| title_fullStr | Moving-window GPR for nonlinear dynamic system modeling with dual updating and dual preprocessing |
| title_full_unstemmed | Moving-window GPR for nonlinear dynamic system modeling with dual updating and dual preprocessing |
| title_short | Moving-window GPR for nonlinear dynamic system modeling with dual updating and dual preprocessing |
| title_sort | moving window gpr for nonlinear dynamic system modeling with dual updating and dual preprocessing |
| topic | DRNTU::Engineering::Civil engineering::Water resources |
| url | https://hdl.handle.net/10356/105944 http://hdl.handle.net/10220/16749 http://dx.doi.org/10.1021/ie201898a |
| work_keys_str_mv | AT niwangdong movingwindowgprfornonlineardynamicsystemmodelingwithdualupdatinganddualpreprocessing AT tansoonkeat movingwindowgprfornonlineardynamicsystemmodelingwithdualupdatinganddualpreprocessing AT ngwunjern movingwindowgprfornonlineardynamicsystemmodelingwithdualupdatinganddualpreprocessing AT brownstevend movingwindowgprfornonlineardynamicsystemmodelingwithdualupdatinganddualpreprocessing |