Functional Soft Sensor Based on Spectra Data for Predicting Multiple Quality Variables
In many complex chemical processes, such as ethanol fermentation process, prediction of the multivariate quality variables based on spectra data presents a great challenge because the dimensions of the spectra far exceed their sampling number. To address this problem, the dimension reduction of the...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9173659/ |
| _version_ | 1818430649400295424 |
|---|---|
| author | Jingxiang Liu Dan Wang Junghui Chen Jie Hou |
| author_facet | Jingxiang Liu Dan Wang Junghui Chen Jie Hou |
| author_sort | Jingxiang Liu |
| collection | DOAJ |
| description | In many complex chemical processes, such as ethanol fermentation process, prediction of the multivariate quality variables based on spectra data presents a great challenge because the dimensions of the spectra far exceed their sampling number. To address this problem, the dimension reduction of the predictors is necessary. It can be conducted either by regressing on components or by smoothing methods with basis functions. Based on the functional data analysis methods, this work introduces a novel wavelet functional partial least squares (WFPLS), which combines both of the foregoing dimension-reduction approaches. The high-dimensional spectra can be well fitted by fewer wavelet basis functions in the proposed method. Using the proposed WFPLS method does not require the measured data to be linear and to be sampled on a regular basis. It will be proved that the proposed WFPLS method can be finally transferred into the traditional PLS method in computation. By comparison with the existing prediction methods, the advantages of the proposed method are well demonstrated via a numerical case and an ethanol fermentation experiment. |
| first_indexed | 2024-12-14T15:36:46Z |
| format | Article |
| id | doaj.art-55336974d25d40849ce5fe24b3a8ae2c |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T15:36:46Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-55336974d25d40849ce5fe24b3a8ae2c2022-12-21T22:55:43ZengIEEEIEEE Access2169-35362020-01-01816035516036210.1109/ACCESS.2020.30186449173659Functional Soft Sensor Based on Spectra Data for Predicting Multiple Quality VariablesJingxiang Liu0Dan Wang1https://orcid.org/0000-0002-4099-6004Junghui Chen2https://orcid.org/0000-0002-9994-839XJie Hou3https://orcid.org/0000-0001-8611-4778School of Marine Electrical Engineering, Dalian Maritime University, Dalian, ChinaSchool of Marine Electrical Engineering, Dalian Maritime University, Dalian, ChinaDepartment of Chemical Engineering, Chung-Yuan Christian University, Taoyuan, TaiwanCollege of Automation, Chongqing University of Posts and Telecommunications, Chongqing, ChinaIn many complex chemical processes, such as ethanol fermentation process, prediction of the multivariate quality variables based on spectra data presents a great challenge because the dimensions of the spectra far exceed their sampling number. To address this problem, the dimension reduction of the predictors is necessary. It can be conducted either by regressing on components or by smoothing methods with basis functions. Based on the functional data analysis methods, this work introduces a novel wavelet functional partial least squares (WFPLS), which combines both of the foregoing dimension-reduction approaches. The high-dimensional spectra can be well fitted by fewer wavelet basis functions in the proposed method. Using the proposed WFPLS method does not require the measured data to be linear and to be sampled on a regular basis. It will be proved that the proposed WFPLS method can be finally transferred into the traditional PLS method in computation. By comparison with the existing prediction methods, the advantages of the proposed method are well demonstrated via a numerical case and an ethanol fermentation experiment.https://ieeexplore.ieee.org/document/9173659/Wavelet functional partial least squaressoft sensorfunctional data analysisspectra data analysisactive learning |
| spellingShingle | Jingxiang Liu Dan Wang Junghui Chen Jie Hou Functional Soft Sensor Based on Spectra Data for Predicting Multiple Quality Variables IEEE Access Wavelet functional partial least squares soft sensor functional data analysis spectra data analysis active learning |
| title | Functional Soft Sensor Based on Spectra Data for Predicting Multiple Quality Variables |
| title_full | Functional Soft Sensor Based on Spectra Data for Predicting Multiple Quality Variables |
| title_fullStr | Functional Soft Sensor Based on Spectra Data for Predicting Multiple Quality Variables |
| title_full_unstemmed | Functional Soft Sensor Based on Spectra Data for Predicting Multiple Quality Variables |
| title_short | Functional Soft Sensor Based on Spectra Data for Predicting Multiple Quality Variables |
| title_sort | functional soft sensor based on spectra data for predicting multiple quality variables |
| topic | Wavelet functional partial least squares soft sensor functional data analysis spectra data analysis active learning |
| url | https://ieeexplore.ieee.org/document/9173659/ |
| work_keys_str_mv | AT jingxiangliu functionalsoftsensorbasedonspectradataforpredictingmultiplequalityvariables AT danwang functionalsoftsensorbasedonspectradataforpredictingmultiplequalityvariables AT junghuichen functionalsoftsensorbasedonspectradataforpredictingmultiplequalityvariables AT jiehou functionalsoftsensorbasedonspectradataforpredictingmultiplequalityvariables |