Using Self-Organizing Maps to Elucidate Patterns among Variables in Simulated Syngas Combustion
This study focused on demonstrating the use of a self-organizing map (SOM) algorithm to elucidate patterns among variables in simulated syngas combustion. The work was implemented in two stages: (1) modelling and simulation of syngas combustion under various feed composition and reactor temperature...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-04-01
|
| Series: | Clean Technologies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2571-8797/2/2/11 |
| _version_ | 1797569434609516544 |
|---|---|
| author | Dhan Lord B. Fortela Matthew Crawford Alyssa DeLattre Spencer Kowalski Mary Lissard Ashton Fremin Wayne Sharp Emmanuel Revellame Rafael Hernandez Mark Zappi |
| author_facet | Dhan Lord B. Fortela Matthew Crawford Alyssa DeLattre Spencer Kowalski Mary Lissard Ashton Fremin Wayne Sharp Emmanuel Revellame Rafael Hernandez Mark Zappi |
| author_sort | Dhan Lord B. Fortela |
| collection | DOAJ |
| description | This study focused on demonstrating the use of a self-organizing map (SOM) algorithm to elucidate patterns among variables in simulated syngas combustion. The work was implemented in two stages: (1) modelling and simulation of syngas combustion under various feed composition and reactor temperature implemented in AspenPlus<sup>TM</sup> chemical process simulation software, and (2) pattern recognition among variables using SOM algorithm implemented in MATLAB. The varied levels of feed syngas composition and reactor temperature was randomly sampled from uniform distributions using the Morris screening technique creating four thousand eight hundred simulation conditions implemented in the process simulation which consequently produced a multivariate dataset used in the SOM analysis. Results show that cylindrical SOM topology models the dataset at lower quantization error and topographic error as compared to the rectangular SOM topology indicating suitability of the former for variables pattern elucidation for the simulated combustion. Nonetheless, the variables pattern between component planes from rectangular SOM (9 × 28 grid) and those from cylindrical SOM (9 × 28 grid) are almost similar, indicating that either rectangular or cylindrical architectures may be used for variables pattern analysis. The component planes of process variables from trained SOM are a convenient visualization of the trends across all process variables. |
| first_indexed | 2024-03-10T20:11:39Z |
| format | Article |
| id | doaj.art-a21ce6db4fa04eb69978866ab629833e |
| institution | Directory Open Access Journal |
| issn | 2571-8797 |
| language | English |
| last_indexed | 2024-03-10T20:11:39Z |
| publishDate | 2020-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Clean Technologies |
| spelling | doaj.art-a21ce6db4fa04eb69978866ab629833e2023-11-19T22:53:59ZengMDPI AGClean Technologies2571-87972020-04-012215616910.3390/cleantechnol2020011Using Self-Organizing Maps to Elucidate Patterns among Variables in Simulated Syngas CombustionDhan Lord B. Fortela0Matthew Crawford1Alyssa DeLattre2Spencer Kowalski3Mary Lissard4Ashton Fremin5Wayne Sharp6Emmanuel Revellame7Rafael Hernandez8Mark Zappi9Department of Chemical Engineering, University of Louisiana, Lafayette, LA 70504, USADepartment of Chemical Engineering, University of Louisiana, Lafayette, LA 70504, USADepartment of Chemical Engineering, University of Louisiana, Lafayette, LA 70504, USADepartment of Chemical Engineering, University of Louisiana, Lafayette, LA 70504, USADepartment of Chemical Engineering, University of Louisiana, Lafayette, LA 70504, USADepartment of Chemical Engineering, University of Louisiana, Lafayette, LA 70504, USAEnergy Institute of Louisiana, University of Louisiana, Lafayette, LA 70504, USAEnergy Institute of Louisiana, University of Louisiana, Lafayette, LA 70504, USADepartment of Chemical Engineering, University of Louisiana, Lafayette, LA 70504, USADepartment of Chemical Engineering, University of Louisiana, Lafayette, LA 70504, USAThis study focused on demonstrating the use of a self-organizing map (SOM) algorithm to elucidate patterns among variables in simulated syngas combustion. The work was implemented in two stages: (1) modelling and simulation of syngas combustion under various feed composition and reactor temperature implemented in AspenPlus<sup>TM</sup> chemical process simulation software, and (2) pattern recognition among variables using SOM algorithm implemented in MATLAB. The varied levels of feed syngas composition and reactor temperature was randomly sampled from uniform distributions using the Morris screening technique creating four thousand eight hundred simulation conditions implemented in the process simulation which consequently produced a multivariate dataset used in the SOM analysis. Results show that cylindrical SOM topology models the dataset at lower quantization error and topographic error as compared to the rectangular SOM topology indicating suitability of the former for variables pattern elucidation for the simulated combustion. Nonetheless, the variables pattern between component planes from rectangular SOM (9 × 28 grid) and those from cylindrical SOM (9 × 28 grid) are almost similar, indicating that either rectangular or cylindrical architectures may be used for variables pattern analysis. The component planes of process variables from trained SOM are a convenient visualization of the trends across all process variables.https://www.mdpi.com/2571-8797/2/2/11chemical process simulationsyngasmachine learningSOM |
| spellingShingle | Dhan Lord B. Fortela Matthew Crawford Alyssa DeLattre Spencer Kowalski Mary Lissard Ashton Fremin Wayne Sharp Emmanuel Revellame Rafael Hernandez Mark Zappi Using Self-Organizing Maps to Elucidate Patterns among Variables in Simulated Syngas Combustion Clean Technologies chemical process simulation syngas machine learning SOM |
| title | Using Self-Organizing Maps to Elucidate Patterns among Variables in Simulated Syngas Combustion |
| title_full | Using Self-Organizing Maps to Elucidate Patterns among Variables in Simulated Syngas Combustion |
| title_fullStr | Using Self-Organizing Maps to Elucidate Patterns among Variables in Simulated Syngas Combustion |
| title_full_unstemmed | Using Self-Organizing Maps to Elucidate Patterns among Variables in Simulated Syngas Combustion |
| title_short | Using Self-Organizing Maps to Elucidate Patterns among Variables in Simulated Syngas Combustion |
| title_sort | using self organizing maps to elucidate patterns among variables in simulated syngas combustion |
| topic | chemical process simulation syngas machine learning SOM |
| url | https://www.mdpi.com/2571-8797/2/2/11 |
| work_keys_str_mv | AT dhanlordbfortela usingselforganizingmapstoelucidatepatternsamongvariablesinsimulatedsyngascombustion AT matthewcrawford usingselforganizingmapstoelucidatepatternsamongvariablesinsimulatedsyngascombustion AT alyssadelattre usingselforganizingmapstoelucidatepatternsamongvariablesinsimulatedsyngascombustion AT spencerkowalski usingselforganizingmapstoelucidatepatternsamongvariablesinsimulatedsyngascombustion AT marylissard usingselforganizingmapstoelucidatepatternsamongvariablesinsimulatedsyngascombustion AT ashtonfremin usingselforganizingmapstoelucidatepatternsamongvariablesinsimulatedsyngascombustion AT waynesharp usingselforganizingmapstoelucidatepatternsamongvariablesinsimulatedsyngascombustion AT emmanuelrevellame usingselforganizingmapstoelucidatepatternsamongvariablesinsimulatedsyngascombustion AT rafaelhernandez usingselforganizingmapstoelucidatepatternsamongvariablesinsimulatedsyngascombustion AT markzappi usingselforganizingmapstoelucidatepatternsamongvariablesinsimulatedsyngascombustion |