The full text of this item is not available at this time because the student has placed this item under an embargo for a period of time. The Libraries are not authorized to provide a copy of this work during the embargo period, even for Texas A&M users with NetID.
Minimum Ignition Energy Prediction for Organic Gases and Liquids using Group Contribution Method
dc.contributor.advisor | Mashuga, Chad | |
dc.creator | Kevadiya, Jhanvi Manishkumar | |
dc.date.accessioned | 2023-09-18T17:13:24Z | |
dc.date.created | 2022-12 | |
dc.date.issued | 2022-12-09 | |
dc.date.submitted | December 2022 | |
dc.identifier.uri | https://hdl.handle.net/1969.1/198749 | |
dc.description.abstract | Group contribution (GC) models are developed using ordinary least square (OLS) regression, Huber ridge regression (HRR) and kernel ridge regression (KRR) for minimum ignition energy (MIE) prediction of 55 flammable organic gases and liquids. Marrero/Gani (MG) GC method was used to determine structurally dependent parameters (fragment of molecules or group of molecules) that uniquely represent the molecular structure of the compounds. Later, these parameters were used as predictors for OLS regression, Huber ridge regression, and KRR to develop a predictive model. The initial analysis of OLS regression resulted in an R2 of 0.939 but several compounds were overpredicted. So, outlier analysis was conducted, and HRR and KRR models were developed to reduce the influence of outliers on the estimation of MIE and consider the nonlinearity of MIE with the predictors respectively. Additionally, both algorithm uses L2 regularization to reduce the sensitivity of the predictive models on the statistically insignificant predictors. KRR was observed to be reliable on a smaller dataset. The R2 value for optimized HRR and KRR were determined to be 0.878 and 0.991 respectively. Thus, HRR and KRR are the potential alternatives for faster and accurate prediction of MIE. | |
dc.format.mimetype | application/pdf | |
dc.language.iso | en | |
dc.subject | Minimum Ignition Energy (MIE) | |
dc.subject | Group Contribution (GC) | |
dc.subject | Marrero/Gani group Contribution (MG GC) | |
dc.subject | Huber Ridge Regression (HRR) | |
dc.subject | Kernel Ridge Regression (KRR) | |
dc.subject | Machine Learning (ML) | |
dc.title | Minimum Ignition Energy Prediction for Organic Gases and Liquids using Group Contribution Method | |
dc.type | Thesis | |
thesis.degree.department | Chemical Engineering | |
thesis.degree.discipline | Chemical Engineering | |
thesis.degree.grantor | Texas A&M University | |
thesis.degree.name | Master of Science | |
thesis.degree.level | Masters | |
dc.contributor.committeeMember | El-Halwagi, Mahmoud | |
dc.contributor.committeeMember | Kulatilaka, Waruna | |
dc.type.material | text | |
dc.date.updated | 2023-09-18T17:13:28Z | |
local.embargo.terms | 2024-12-01 | |
local.embargo.lift | 2024-12-01 | |
local.etdauthor.orcid | 0000-0002-7989-6967 |
Files in this item
This item appears in the following Collection(s)
-
Electronic Theses, Dissertations, and Records of Study (2002– )
Texas A&M University Theses, Dissertations, and Records of Study (2002– )