Linear and Non-Linear Soft Sensors for Predicting the Research Octane Number (RON) through Integrated Synchronization, Resolution Selection and Modelling
The Research Octane Number (RON) is a key quality parameter for gasoline, obtained offline through complex, time-consuming, and expensive standard methods. Measurements are usually only available a few times per week and after long delays, making process control very challenging. Therefore, alternat...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/10/3734 |
| _version_ | 1797495725223837696 |
|---|---|
| author | Tiago Dias Rodolfo Oliveira Pedro M. Saraiva Marco S. Reis |
| author_facet | Tiago Dias Rodolfo Oliveira Pedro M. Saraiva Marco S. Reis |
| author_sort | Tiago Dias |
| collection | DOAJ |
| description | The Research Octane Number (RON) is a key quality parameter for gasoline, obtained offline through complex, time-consuming, and expensive standard methods. Measurements are usually only available a few times per week and after long delays, making process control very challenging. Therefore, alternative methods have been proposed to predict RON from readily available data. In this work, we report the development of inferential models for predicting RON from process data collected in a real catalytic reforming process. Data resolution and synchronization were explicitly considered during the modelling stage, where 20 predictive linear and non-linear machine learning models were assessed and compared using a robust Monte Carlo double cross-validation approach. The workflow also handles outliers, missing data, multirate and multiresolution observations, and processes dynamics, among other features. Low RMSE were obtained under testing conditions (close to 0.5), with the best methods belonging to the class of penalized regression methods and partial least squares. The developed models allow for improved management of the operational conditions necessary to achieve the target RON, including a more effective use of the heating utilities, which improves process efficiency while reducing costs and emissions. |
| first_indexed | 2024-03-10T01:53:44Z |
| format | Article |
| id | doaj.art-21a27e11f464446ea34f23a4d64f702c |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T01:53:44Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-21a27e11f464446ea34f23a4d64f702c2023-11-23T13:00:15ZengMDPI AGSensors1424-82202022-05-012210373410.3390/s22103734Linear and Non-Linear Soft Sensors for Predicting the Research Octane Number (RON) through Integrated Synchronization, Resolution Selection and ModellingTiago Dias0Rodolfo Oliveira1Pedro M. Saraiva2Marco S. Reis3Department of Chemical Engineering, University of Coimbra, CIEPQPF, Rua Sílvio Lima, Pólo II—Pinhal de Marrocos, 3030-790 Coimbra, PortugalPetrogal, S.A., 4451-852 Leça da Palmeira, PortugalDepartment of Chemical Engineering, University of Coimbra, CIEPQPF, Rua Sílvio Lima, Pólo II—Pinhal de Marrocos, 3030-790 Coimbra, PortugalDepartment of Chemical Engineering, University of Coimbra, CIEPQPF, Rua Sílvio Lima, Pólo II—Pinhal de Marrocos, 3030-790 Coimbra, PortugalThe Research Octane Number (RON) is a key quality parameter for gasoline, obtained offline through complex, time-consuming, and expensive standard methods. Measurements are usually only available a few times per week and after long delays, making process control very challenging. Therefore, alternative methods have been proposed to predict RON from readily available data. In this work, we report the development of inferential models for predicting RON from process data collected in a real catalytic reforming process. Data resolution and synchronization were explicitly considered during the modelling stage, where 20 predictive linear and non-linear machine learning models were assessed and compared using a robust Monte Carlo double cross-validation approach. The workflow also handles outliers, missing data, multirate and multiresolution observations, and processes dynamics, among other features. Low RMSE were obtained under testing conditions (close to 0.5), with the best methods belonging to the class of penalized regression methods and partial least squares. The developed models allow for improved management of the operational conditions necessary to achieve the target RON, including a more effective use of the heating utilities, which improves process efficiency while reducing costs and emissions.https://www.mdpi.com/1424-8220/22/10/3734Research Octane Numbercatalytic reformingdynamic soft sensorsdata synchronizationdata resolution |
| spellingShingle | Tiago Dias Rodolfo Oliveira Pedro M. Saraiva Marco S. Reis Linear and Non-Linear Soft Sensors for Predicting the Research Octane Number (RON) through Integrated Synchronization, Resolution Selection and Modelling Sensors Research Octane Number catalytic reforming dynamic soft sensors data synchronization data resolution |
| title | Linear and Non-Linear Soft Sensors for Predicting the Research Octane Number (RON) through Integrated Synchronization, Resolution Selection and Modelling |
| title_full | Linear and Non-Linear Soft Sensors for Predicting the Research Octane Number (RON) through Integrated Synchronization, Resolution Selection and Modelling |
| title_fullStr | Linear and Non-Linear Soft Sensors for Predicting the Research Octane Number (RON) through Integrated Synchronization, Resolution Selection and Modelling |
| title_full_unstemmed | Linear and Non-Linear Soft Sensors for Predicting the Research Octane Number (RON) through Integrated Synchronization, Resolution Selection and Modelling |
| title_short | Linear and Non-Linear Soft Sensors for Predicting the Research Octane Number (RON) through Integrated Synchronization, Resolution Selection and Modelling |
| title_sort | linear and non linear soft sensors for predicting the research octane number ron through integrated synchronization resolution selection and modelling |
| topic | Research Octane Number catalytic reforming dynamic soft sensors data synchronization data resolution |
| url | https://www.mdpi.com/1424-8220/22/10/3734 |
| work_keys_str_mv | AT tiagodias linearandnonlinearsoftsensorsforpredictingtheresearchoctanenumberronthroughintegratedsynchronizationresolutionselectionandmodelling AT rodolfooliveira linearandnonlinearsoftsensorsforpredictingtheresearchoctanenumberronthroughintegratedsynchronizationresolutionselectionandmodelling AT pedromsaraiva linearandnonlinearsoftsensorsforpredictingtheresearchoctanenumberronthroughintegratedsynchronizationresolutionselectionandmodelling AT marcosreis linearandnonlinearsoftsensorsforpredictingtheresearchoctanenumberronthroughintegratedsynchronizationresolutionselectionandmodelling |