Combining CFD and AI/ML Modeling to Improve the Performance of Polypropylene Fluidized Bed Reactors
Polypropylene is one of the most widely used polymers in various applications, ranging from packaging materials to automotive components. This paper proposes the Computational Fluid Dynamics (CFD) and AI/ML simulation of a polypropylene fluidized bed reactor to reduce reactor loss and facilitate pro...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Fluids |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2311-5521/9/12/298 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846104642287566848 |
|---|---|
| author | Nayef Ghasem |
| author_facet | Nayef Ghasem |
| author_sort | Nayef Ghasem |
| collection | DOAJ |
| description | Polypropylene is one of the most widely used polymers in various applications, ranging from packaging materials to automotive components. This paper proposes the Computational Fluid Dynamics (CFD) and AI/ML simulation of a polypropylene fluidized bed reactor to reduce reactor loss and facilitate process understanding. COMSOL Multiphysics 6.2<sup>®</sup> solves a 2D multiphase CFD model for the reactor’s complex gas–solid interactions and fluid flows. The model is compared to experimental results and shows excellent predictions of gas distribution, fluid velocity, and temperature gradients. Critical operating parameters like feed temperature, catalyst feed rate, and propylene inlet concentration are all tested to determine their impact on the single-pass conversion of the reactor. The simulation simulates their effects on polypropylene yield and reactor efficiency. It also combines CFD with artificial intelligence and machine learning (AI/ML) algorithms, like artificial neural networks (ANN), resulting in a powerful predictive tool for accurately predicting reactor metrics based on operating conditions. The multifaceted CFD-AI/ML tool provides deep insight into improving reactor design, and it also helps save computing time and resources, giving industrial polypropylene plant growth a considerable lift. |
| format | Article |
| id | doaj-art-b136c340d063407da72cf804f39b8a34 |
| institution | Kabale University |
| issn | 2311-5521 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Fluids |
| spelling | doaj-art-b136c340d063407da72cf804f39b8a342024-12-27T14:26:08ZengMDPI AGFluids2311-55212024-12-0191229810.3390/fluids9120298Combining CFD and AI/ML Modeling to Improve the Performance of Polypropylene Fluidized Bed ReactorsNayef Ghasem0Department of Chemical and Petroleum Engineering, United Arab Emirates University, Al-Ain 15551, United Arab EmiratesPolypropylene is one of the most widely used polymers in various applications, ranging from packaging materials to automotive components. This paper proposes the Computational Fluid Dynamics (CFD) and AI/ML simulation of a polypropylene fluidized bed reactor to reduce reactor loss and facilitate process understanding. COMSOL Multiphysics 6.2<sup>®</sup> solves a 2D multiphase CFD model for the reactor’s complex gas–solid interactions and fluid flows. The model is compared to experimental results and shows excellent predictions of gas distribution, fluid velocity, and temperature gradients. Critical operating parameters like feed temperature, catalyst feed rate, and propylene inlet concentration are all tested to determine their impact on the single-pass conversion of the reactor. The simulation simulates their effects on polypropylene yield and reactor efficiency. It also combines CFD with artificial intelligence and machine learning (AI/ML) algorithms, like artificial neural networks (ANN), resulting in a powerful predictive tool for accurately predicting reactor metrics based on operating conditions. The multifaceted CFD-AI/ML tool provides deep insight into improving reactor design, and it also helps save computing time and resources, giving industrial polypropylene plant growth a considerable lift.https://www.mdpi.com/2311-5521/9/12/298computational fluid dynamics (CFD)artificial intelligence (AI)machine learning (ML)polypropylenefluidized bed reactors |
| spellingShingle | Nayef Ghasem Combining CFD and AI/ML Modeling to Improve the Performance of Polypropylene Fluidized Bed Reactors Fluids computational fluid dynamics (CFD) artificial intelligence (AI) machine learning (ML) polypropylene fluidized bed reactors |
| title | Combining CFD and AI/ML Modeling to Improve the Performance of Polypropylene Fluidized Bed Reactors |
| title_full | Combining CFD and AI/ML Modeling to Improve the Performance of Polypropylene Fluidized Bed Reactors |
| title_fullStr | Combining CFD and AI/ML Modeling to Improve the Performance of Polypropylene Fluidized Bed Reactors |
| title_full_unstemmed | Combining CFD and AI/ML Modeling to Improve the Performance of Polypropylene Fluidized Bed Reactors |
| title_short | Combining CFD and AI/ML Modeling to Improve the Performance of Polypropylene Fluidized Bed Reactors |
| title_sort | combining cfd and ai ml modeling to improve the performance of polypropylene fluidized bed reactors |
| topic | computational fluid dynamics (CFD) artificial intelligence (AI) machine learning (ML) polypropylene fluidized bed reactors |
| url | https://www.mdpi.com/2311-5521/9/12/298 |
| work_keys_str_mv | AT nayefghasem combiningcfdandaimlmodelingtoimprovetheperformanceofpolypropylenefluidizedbedreactors |