Multiple phase flow identification using computational simulation and convolutional neural network
The Identification of gas-solid flow characterization in dense-phase pneumatic conveying particles is very important to a vast area of industrial fields such as chemical and pharmaceutical industries since a slight change in flow characteristics results in a completely different product. The motion...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2020
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/93119/1/MohamedTawfikIbrahimMSKE2020.pdf |
| _version_ | 1796865558952542208 |
|---|---|
| author | Helmy, Mohamed Tawfik Ibrahim |
| author_facet | Helmy, Mohamed Tawfik Ibrahim |
| author_sort | Helmy, Mohamed Tawfik Ibrahim |
| collection | ePrints |
| description | The Identification of gas-solid flow characterization in dense-phase pneumatic conveying particles is very important to a vast area of industrial fields such as chemical and pharmaceutical industries since a slight change in flow characteristics results in a completely different product. The motion of the gas-solid two-phase flow in densephase usually has a nonlinear and unsteady nature that needs to be examined and analysed to identify the particle flow behaviour in the pneumatic conveying pipelines. In this research a method to identify the type of flow pattern is proposed using a computational method where a gravity flow rig is modelled on Solidworks and multiple flow patterns are simulated with different mass flow rates ranging between 200 to 600 g/s. For changing the flow patterns inside the pipe, an Iris Mechanism is designed according to the specifications of the flow required to achieve the flow pattern control. A sectioning method is implemented to capture flow images at the plane of interest for different flow patterns. Afterwards images are fed to a Convolutional Neural Network which is trained and tested to identify the flowpatterns according to several flowfeatures which resulted in 100% accuracy. A GUI using PyQt is designed to better visualize the whole system and view the predicted flow pattern. |
| first_indexed | 2024-03-05T20:58:50Z |
| format | Thesis |
| id | utm.eprints-93119 |
| institution | Universiti Teknologi Malaysia - ePrints |
| language | English |
| last_indexed | 2024-03-05T20:58:50Z |
| publishDate | 2020 |
| record_format | dspace |
| spelling | utm.eprints-931192021-11-19T03:31:23Z http://eprints.utm.my/93119/ Multiple phase flow identification using computational simulation and convolutional neural network Helmy, Mohamed Tawfik Ibrahim TK Electrical engineering. Electronics Nuclear engineering The Identification of gas-solid flow characterization in dense-phase pneumatic conveying particles is very important to a vast area of industrial fields such as chemical and pharmaceutical industries since a slight change in flow characteristics results in a completely different product. The motion of the gas-solid two-phase flow in densephase usually has a nonlinear and unsteady nature that needs to be examined and analysed to identify the particle flow behaviour in the pneumatic conveying pipelines. In this research a method to identify the type of flow pattern is proposed using a computational method where a gravity flow rig is modelled on Solidworks and multiple flow patterns are simulated with different mass flow rates ranging between 200 to 600 g/s. For changing the flow patterns inside the pipe, an Iris Mechanism is designed according to the specifications of the flow required to achieve the flow pattern control. A sectioning method is implemented to capture flow images at the plane of interest for different flow patterns. Afterwards images are fed to a Convolutional Neural Network which is trained and tested to identify the flowpatterns according to several flowfeatures which resulted in 100% accuracy. A GUI using PyQt is designed to better visualize the whole system and view the predicted flow pattern. 2020 Thesis NonPeerReviewed application/pdf en http://eprints.utm.my/93119/1/MohamedTawfikIbrahimMSKE2020.pdf Helmy, Mohamed Tawfik Ibrahim (2020) Multiple phase flow identification using computational simulation and convolutional neural network. Masters thesis, Universiti Teknologi Malaysia, Faculty of Engineering - School of Electrical Engineering. http://dms.library.utm.my:8080/vital/access/manager/Repository/vital:135980 |
| spellingShingle | TK Electrical engineering. Electronics Nuclear engineering Helmy, Mohamed Tawfik Ibrahim Multiple phase flow identification using computational simulation and convolutional neural network |
| title | Multiple phase flow identification using computational simulation and convolutional neural network |
| title_full | Multiple phase flow identification using computational simulation and convolutional neural network |
| title_fullStr | Multiple phase flow identification using computational simulation and convolutional neural network |
| title_full_unstemmed | Multiple phase flow identification using computational simulation and convolutional neural network |
| title_short | Multiple phase flow identification using computational simulation and convolutional neural network |
| title_sort | multiple phase flow identification using computational simulation and convolutional neural network |
| topic | TK Electrical engineering. Electronics Nuclear engineering |
| url | http://eprints.utm.my/93119/1/MohamedTawfikIbrahimMSKE2020.pdf |
| work_keys_str_mv | AT helmymohamedtawfikibrahim multiplephaseflowidentificationusingcomputationalsimulationandconvolutionalneuralnetwork |