A Multiblock Approach to Fuse Process and Near-Infrared Sensors for On-Line Prediction of Polymer Properties
Petrochemical companies aim at assessing final product quality in real time, in order to rapidly deal with possible plant faults and to reduce chemical wastes and staff effort resulting from the many laboratory analyses performed every day. In order to answer these needs, the main purpose of the cur...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/4/1436 |
| _version_ | 1797476749778354176 |
|---|---|
| author | Lorenzo Strani Raffaele Vitale Daniele Tanzilli Francesco Bonacini Andrea Perolo Erik Mantovani Angelo Ferrando Marina Cocchi |
| author_facet | Lorenzo Strani Raffaele Vitale Daniele Tanzilli Francesco Bonacini Andrea Perolo Erik Mantovani Angelo Ferrando Marina Cocchi |
| author_sort | Lorenzo Strani |
| collection | DOAJ |
| description | Petrochemical companies aim at assessing final product quality in real time, in order to rapidly deal with possible plant faults and to reduce chemical wastes and staff effort resulting from the many laboratory analyses performed every day. In order to answer these needs, the main purpose of the current work is to explore the feasibility of multiblock regression methods to build real-time monitoring models for the prediction of two quality properties of Acrylonitrile-Butadiene-Styrene (ABS) by fusing near-infrared (NIR) and process sensors data. Data come from a production plant, which operates continuously, and where four NIR probes are installed on-line, in addition to standard process sensors. Multiblock-PLS (MB-PLS) and Response-Oriented Sequential Alternation (ROSA) methods were here utilized to assess which of such sensors and plant areas were the most relevant for the quality parameters prediction. Several prediction models were constructed exploiting measurements provided by sensors active at different ABS production process stages. Both methods provided good prediction performances and permitted identification of the most relevant data blocks for the quality parameters’ prediction. Moreover, models built without considering recordings from the final stage of the process yielded prediction errors comparable to those involving all available data blocks. Thus, in principle, allowing final ABS quality to be estimated in real-time before the end of the process itself. |
| first_indexed | 2024-03-09T21:06:08Z |
| format | Article |
| id | doaj.art-60f0e5c7f07341559c4671af20c91c67 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T21:06:08Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-60f0e5c7f07341559c4671af20c91c672023-11-23T21:59:30ZengMDPI AGSensors1424-82202022-02-01224143610.3390/s22041436A Multiblock Approach to Fuse Process and Near-Infrared Sensors for On-Line Prediction of Polymer PropertiesLorenzo Strani0Raffaele Vitale1Daniele Tanzilli2Francesco Bonacini3Andrea Perolo4Erik Mantovani5Angelo Ferrando6Marina Cocchi7Department of Chemical and Geological Sciences, University of Modena and Reggio Emilia, Via 4 Campi 103, 41125 Modena, ItalyCentre National de la Recherche Scientifique (CNRS), Laboratoire de Spectroscopie pour les Interactions, la Réactivitè et l’Environnement (LASIRE), Cité Scientifique, University Lille, F-59000 Lille, FranceDepartment of Chemical and Geological Sciences, University of Modena and Reggio Emilia, Via 4 Campi 103, 41125 Modena, ItalyResearch Center, Versalis (ENI) S.p.A., Via Taliercio 14, 46100 Mantova, ItalyResearch Center, Versalis (ENI) S.p.A., Via Taliercio 14, 46100 Mantova, ItalyResearch Center, Versalis (ENI) S.p.A., Via Taliercio 14, 46100 Mantova, ItalyResearch Center, Versalis (ENI) S.p.A., Via Taliercio 14, 46100 Mantova, ItalyDepartment of Chemical and Geological Sciences, University of Modena and Reggio Emilia, Via 4 Campi 103, 41125 Modena, ItalyPetrochemical companies aim at assessing final product quality in real time, in order to rapidly deal with possible plant faults and to reduce chemical wastes and staff effort resulting from the many laboratory analyses performed every day. In order to answer these needs, the main purpose of the current work is to explore the feasibility of multiblock regression methods to build real-time monitoring models for the prediction of two quality properties of Acrylonitrile-Butadiene-Styrene (ABS) by fusing near-infrared (NIR) and process sensors data. Data come from a production plant, which operates continuously, and where four NIR probes are installed on-line, in addition to standard process sensors. Multiblock-PLS (MB-PLS) and Response-Oriented Sequential Alternation (ROSA) methods were here utilized to assess which of such sensors and plant areas were the most relevant for the quality parameters prediction. Several prediction models were constructed exploiting measurements provided by sensors active at different ABS production process stages. Both methods provided good prediction performances and permitted identification of the most relevant data blocks for the quality parameters’ prediction. Moreover, models built without considering recordings from the final stage of the process yielded prediction errors comparable to those involving all available data blocks. Thus, in principle, allowing final ABS quality to be estimated in real-time before the end of the process itself.https://www.mdpi.com/1424-8220/22/4/1436Acrylonitrile-Butadiene-Styrenelow-level data fusionmultiblock-partial least squares (MB-PLS)multivariate statistical process controlpolymer productionquality prediction |
| spellingShingle | Lorenzo Strani Raffaele Vitale Daniele Tanzilli Francesco Bonacini Andrea Perolo Erik Mantovani Angelo Ferrando Marina Cocchi A Multiblock Approach to Fuse Process and Near-Infrared Sensors for On-Line Prediction of Polymer Properties Sensors Acrylonitrile-Butadiene-Styrene low-level data fusion multiblock-partial least squares (MB-PLS) multivariate statistical process control polymer production quality prediction |
| title | A Multiblock Approach to Fuse Process and Near-Infrared Sensors for On-Line Prediction of Polymer Properties |
| title_full | A Multiblock Approach to Fuse Process and Near-Infrared Sensors for On-Line Prediction of Polymer Properties |
| title_fullStr | A Multiblock Approach to Fuse Process and Near-Infrared Sensors for On-Line Prediction of Polymer Properties |
| title_full_unstemmed | A Multiblock Approach to Fuse Process and Near-Infrared Sensors for On-Line Prediction of Polymer Properties |
| title_short | A Multiblock Approach to Fuse Process and Near-Infrared Sensors for On-Line Prediction of Polymer Properties |
| title_sort | multiblock approach to fuse process and near infrared sensors for on line prediction of polymer properties |
| topic | Acrylonitrile-Butadiene-Styrene low-level data fusion multiblock-partial least squares (MB-PLS) multivariate statistical process control polymer production quality prediction |
| url | https://www.mdpi.com/1424-8220/22/4/1436 |
| work_keys_str_mv | AT lorenzostrani amultiblockapproachtofuseprocessandnearinfraredsensorsforonlinepredictionofpolymerproperties AT raffaelevitale amultiblockapproachtofuseprocessandnearinfraredsensorsforonlinepredictionofpolymerproperties AT danieletanzilli amultiblockapproachtofuseprocessandnearinfraredsensorsforonlinepredictionofpolymerproperties AT francescobonacini amultiblockapproachtofuseprocessandnearinfraredsensorsforonlinepredictionofpolymerproperties AT andreaperolo amultiblockapproachtofuseprocessandnearinfraredsensorsforonlinepredictionofpolymerproperties AT erikmantovani amultiblockapproachtofuseprocessandnearinfraredsensorsforonlinepredictionofpolymerproperties AT angeloferrando amultiblockapproachtofuseprocessandnearinfraredsensorsforonlinepredictionofpolymerproperties AT marinacocchi amultiblockapproachtofuseprocessandnearinfraredsensorsforonlinepredictionofpolymerproperties AT lorenzostrani multiblockapproachtofuseprocessandnearinfraredsensorsforonlinepredictionofpolymerproperties AT raffaelevitale multiblockapproachtofuseprocessandnearinfraredsensorsforonlinepredictionofpolymerproperties AT danieletanzilli multiblockapproachtofuseprocessandnearinfraredsensorsforonlinepredictionofpolymerproperties AT francescobonacini multiblockapproachtofuseprocessandnearinfraredsensorsforonlinepredictionofpolymerproperties AT andreaperolo multiblockapproachtofuseprocessandnearinfraredsensorsforonlinepredictionofpolymerproperties AT erikmantovani multiblockapproachtofuseprocessandnearinfraredsensorsforonlinepredictionofpolymerproperties AT angeloferrando multiblockapproachtofuseprocessandnearinfraredsensorsforonlinepredictionofpolymerproperties AT marinacocchi multiblockapproachtofuseprocessandnearinfraredsensorsforonlinepredictionofpolymerproperties |