Predictive Analytics for Octane Number: A Novel Hybrid Approach of KPCA and GS-PSO-SVR Model
Octane number is the most important indicator of reflecting the combustion performance, and a great deal of research has been devoted to improving it. In this paper, a new analytical framework is proposed to predict octane number, kernel principal component analysis (KPCA) is used to reduce the dime...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9420732/ |
| _version_ | 1818600426264592384 |
|---|---|
| author | Baosheng Li Chuandong Qin |
| author_facet | Baosheng Li Chuandong Qin |
| author_sort | Baosheng Li |
| collection | DOAJ |
| description | Octane number is the most important indicator of reflecting the combustion performance, and a great deal of research has been devoted to improving it. In this paper, a new analytical framework is proposed to predict octane number, kernel principal component analysis (KPCA) is used to reduce the dimension of the variables in the process of Fluid Catalytic Cracking (FCC), support vector regression (SVR) is used to construct the gasoline octane number prediction model and the particle swarm optimization algorithm (PSO) is used to select the optimal combination of parameters for the model. The experiments show that the octane number can be improved under a given production environment with a guaranteed desulfurization effect of gasoline products. Furthermore, several key attributes that have a significantly positive or negative correlation with the improvement of gasoline product quality are identified through computing the feature score. The findings can help engineers adjust operational variables to obtain a series of high-quality products. |
| first_indexed | 2024-12-16T12:35:18Z |
| format | Article |
| id | doaj.art-5cb8356afc2b4d928de17f2a6a7c9e2b |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-16T12:35:18Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-5cb8356afc2b4d928de17f2a6a7c9e2b2022-12-21T22:31:36ZengIEEEIEEE Access2169-35362021-01-019665316654110.1109/ACCESS.2021.30770289420732Predictive Analytics for Octane Number: A Novel Hybrid Approach of KPCA and GS-PSO-SVR ModelBaosheng Li0https://orcid.org/0000-0002-0578-6001Chuandong Qin1https://orcid.org/0000-0002-6234-2490School of Mathematics and Information Science, North Minzu University, Yinchuan, ChinaSchool of Mathematics and Information Science, North Minzu University, Yinchuan, ChinaOctane number is the most important indicator of reflecting the combustion performance, and a great deal of research has been devoted to improving it. In this paper, a new analytical framework is proposed to predict octane number, kernel principal component analysis (KPCA) is used to reduce the dimension of the variables in the process of Fluid Catalytic Cracking (FCC), support vector regression (SVR) is used to construct the gasoline octane number prediction model and the particle swarm optimization algorithm (PSO) is used to select the optimal combination of parameters for the model. The experiments show that the octane number can be improved under a given production environment with a guaranteed desulfurization effect of gasoline products. Furthermore, several key attributes that have a significantly positive or negative correlation with the improvement of gasoline product quality are identified through computing the feature score. The findings can help engineers adjust operational variables to obtain a series of high-quality products.https://ieeexplore.ieee.org/document/9420732/Gasoline octane numberkernel principal component analysissupport vector regressionparticle swarm optimization |
| spellingShingle | Baosheng Li Chuandong Qin Predictive Analytics for Octane Number: A Novel Hybrid Approach of KPCA and GS-PSO-SVR Model IEEE Access Gasoline octane number kernel principal component analysis support vector regression particle swarm optimization |
| title | Predictive Analytics for Octane Number: A Novel Hybrid Approach of KPCA and GS-PSO-SVR Model |
| title_full | Predictive Analytics for Octane Number: A Novel Hybrid Approach of KPCA and GS-PSO-SVR Model |
| title_fullStr | Predictive Analytics for Octane Number: A Novel Hybrid Approach of KPCA and GS-PSO-SVR Model |
| title_full_unstemmed | Predictive Analytics for Octane Number: A Novel Hybrid Approach of KPCA and GS-PSO-SVR Model |
| title_short | Predictive Analytics for Octane Number: A Novel Hybrid Approach of KPCA and GS-PSO-SVR Model |
| title_sort | predictive analytics for octane number a novel hybrid approach of kpca and gs pso svr model |
| topic | Gasoline octane number kernel principal component analysis support vector regression particle swarm optimization |
| url | https://ieeexplore.ieee.org/document/9420732/ |
| work_keys_str_mv | AT baoshengli predictiveanalyticsforoctanenumberanovelhybridapproachofkpcaandgspsosvrmodel AT chuandongqin predictiveanalyticsforoctanenumberanovelhybridapproachofkpcaandgspsosvrmodel |