Toxic Gas Dispersion Model Based On Neural Pattern Recognition Networks
The chemical engineering industry has grown steadily for the past few years that causes many catastrophic incidents involving chemical industries. Prairie Grass experiment database is used as a data to develop toxic gas dispersion prediction model based on deep learning networks. Thus, in this study...
| Main Author: | |
|---|---|
| Format: | Monograph |
| Language: | English |
| Published: |
Universiti Sains Malaysia
2022
|
| Subjects: | |
| Online Access: | http://eprints.usm.my/55591/ http://eprints.usm.my/55591/1/TOXIC%20GAS%20DISPERSION%20MODEL%20BASED%20ON%20NEURAL%20PATTERN%20RECOGNITION%20NETWORKS.pdf |
| _version_ | 1848883123678347264 |
|---|---|
| author | Roslan, Nurfarah Arina |
| author_facet | Roslan, Nurfarah Arina |
| author_sort | Roslan, Nurfarah Arina |
| building | USM Institutional Repository |
| collection | Online Access |
| description | The chemical engineering industry has grown steadily for the past few years that causes many catastrophic incidents involving chemical industries. Prairie Grass experiment database is used as a data to develop toxic gas dispersion prediction model based on deep learning networks. Thus, in this study, development of deep neural network is carried out using MATLAB. There are 14 parameters consist of 6583 samples related to toxic gas dispersion from Prairie Grass experiment is used. To achieve the objectives, two phases of structure architecture of NPR is carried out. First, NPR development is developed using three different algorithms which are Levenberg-Marquart (LM), Bayesian Regularization (BR) and Scaled Conjugated Gradient (SCG) to propose the best network algorithm using 70% training and 10-28 hidden neurons. From the analysis, BR shows the best network algorithm compared to others by giving maximum R-value of 0.95. Following the best selection of neural network algorithm, BR algorithm is further trained using 50-70% training with 10-28 hidden neurons. As a result, BR algorithm using 70% training and 28 hidden neurons give the best performance with R-value of 0.95214. Thus, the NPR model is a reliable model for toxic gas dispersion model. |
| first_indexed | 2025-11-15T18:45:49Z |
| format | Monograph |
| id | usm-55591 |
| institution | Universiti Sains Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T18:45:49Z |
| publishDate | 2022 |
| publisher | Universiti Sains Malaysia |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | usm-555912022-11-09T09:05:02Z http://eprints.usm.my/55591/ Toxic Gas Dispersion Model Based On Neural Pattern Recognition Networks Roslan, Nurfarah Arina T Technology TP155-156 Chemical engineering The chemical engineering industry has grown steadily for the past few years that causes many catastrophic incidents involving chemical industries. Prairie Grass experiment database is used as a data to develop toxic gas dispersion prediction model based on deep learning networks. Thus, in this study, development of deep neural network is carried out using MATLAB. There are 14 parameters consist of 6583 samples related to toxic gas dispersion from Prairie Grass experiment is used. To achieve the objectives, two phases of structure architecture of NPR is carried out. First, NPR development is developed using three different algorithms which are Levenberg-Marquart (LM), Bayesian Regularization (BR) and Scaled Conjugated Gradient (SCG) to propose the best network algorithm using 70% training and 10-28 hidden neurons. From the analysis, BR shows the best network algorithm compared to others by giving maximum R-value of 0.95. Following the best selection of neural network algorithm, BR algorithm is further trained using 50-70% training with 10-28 hidden neurons. As a result, BR algorithm using 70% training and 28 hidden neurons give the best performance with R-value of 0.95214. Thus, the NPR model is a reliable model for toxic gas dispersion model. Universiti Sains Malaysia 2022-07-01 Monograph NonPeerReviewed application/pdf en http://eprints.usm.my/55591/1/TOXIC%20GAS%20DISPERSION%20MODEL%20BASED%20ON%20NEURAL%20PATTERN%20RECOGNITION%20NETWORKS.pdf Roslan, Nurfarah Arina (2022) Toxic Gas Dispersion Model Based On Neural Pattern Recognition Networks. Project Report. Universiti Sains Malaysia, Pusat Pengajian Kejuruteraan Kimia. (Submitted) |
| spellingShingle | T Technology TP155-156 Chemical engineering Roslan, Nurfarah Arina Toxic Gas Dispersion Model Based On Neural Pattern Recognition Networks |
| title | Toxic Gas Dispersion Model Based On Neural Pattern Recognition Networks |
| title_full | Toxic Gas Dispersion Model Based On Neural Pattern Recognition Networks |
| title_fullStr | Toxic Gas Dispersion Model Based On Neural Pattern Recognition Networks |
| title_full_unstemmed | Toxic Gas Dispersion Model Based On Neural Pattern Recognition Networks |
| title_short | Toxic Gas Dispersion Model Based On Neural Pattern Recognition Networks |
| title_sort | toxic gas dispersion model based on neural pattern recognition networks |
| topic | T Technology TP155-156 Chemical engineering |
| url | http://eprints.usm.my/55591/ http://eprints.usm.my/55591/1/TOXIC%20GAS%20DISPERSION%20MODEL%20BASED%20ON%20NEURAL%20PATTERN%20RECOGNITION%20NETWORKS.pdf |