Machine Learning for Downstream Oil & Gas Refineries: Applications for Solvent Deasphalting

This thesis seeks to provide continuous DAO yield estimations for an SDA unit by constructing modern machine learning models using data sets from a commercial downstream oil and gas refinery in the United States. These data sets include plant operating parameters and laboratory measurements for feed...

Full description

Bibliographic Details
Main Author: Dowell, Christian
Other Authors: Jacquillat, Alexandre
Format: Thesis
Published: Massachusetts Institute of Technology 2022
Online Access:https://hdl.handle.net/1721.1/140074
_version_ 1826217869306757120
author Dowell, Christian
author2 Jacquillat, Alexandre
author_facet Jacquillat, Alexandre
Dowell, Christian
author_sort Dowell, Christian
collection MIT
description This thesis seeks to provide continuous DAO yield estimations for an SDA unit by constructing modern machine learning models using data sets from a commercial downstream oil and gas refinery in the United States. These data sets include plant operating parameters and laboratory measurements for feed properties. The best machine learning model, determined via an extensive cross-validation procedure, exhibits high out-of-sample R^2 values of 0.76. Furthermore, this predictive machine learning model is incorporated into a linear optimization framework to enhance crude oil purchasing decisions for a downstream refinery. Results suggest that the proposed approach, combining predictive and prescriptive analytics, can result in significant profitability gains estimated at $730,000 annually. The results of this model can be utilized for more accurate plant monitoring within oil & gas downstream refineries, as well as improved decision making by oil and gas planning professionals.
first_indexed 2024-09-23T17:10:09Z
format Thesis
id mit-1721.1/140074
institution Massachusetts Institute of Technology
last_indexed 2024-09-23T17:10:09Z
publishDate 2022
publisher Massachusetts Institute of Technology
record_format dspace
spelling mit-1721.1/1400742022-02-08T03:00:57Z Machine Learning for Downstream Oil & Gas Refineries: Applications for Solvent Deasphalting Dowell, Christian Jacquillat, Alexandre System Design and Management Program. System Design and Management Program. This thesis seeks to provide continuous DAO yield estimations for an SDA unit by constructing modern machine learning models using data sets from a commercial downstream oil and gas refinery in the United States. These data sets include plant operating parameters and laboratory measurements for feed properties. The best machine learning model, determined via an extensive cross-validation procedure, exhibits high out-of-sample R^2 values of 0.76. Furthermore, this predictive machine learning model is incorporated into a linear optimization framework to enhance crude oil purchasing decisions for a downstream refinery. Results suggest that the proposed approach, combining predictive and prescriptive analytics, can result in significant profitability gains estimated at $730,000 annually. The results of this model can be utilized for more accurate plant monitoring within oil & gas downstream refineries, as well as improved decision making by oil and gas planning professionals. S.M. 2022-02-07T15:22:32Z 2022-02-07T15:22:32Z 2021-09 2021-10-21T19:53:31.064Z Thesis https://hdl.handle.net/1721.1/140074 In Copyright - Educational Use Permitted Copyright retained by author(s) https://rightsstatements.org/page/InC-EDU/1.0/ application/pdf Massachusetts Institute of Technology
spellingShingle Dowell, Christian
Machine Learning for Downstream Oil & Gas Refineries: Applications for Solvent Deasphalting
title Machine Learning for Downstream Oil & Gas Refineries: Applications for Solvent Deasphalting
title_full Machine Learning for Downstream Oil & Gas Refineries: Applications for Solvent Deasphalting
title_fullStr Machine Learning for Downstream Oil & Gas Refineries: Applications for Solvent Deasphalting
title_full_unstemmed Machine Learning for Downstream Oil & Gas Refineries: Applications for Solvent Deasphalting
title_short Machine Learning for Downstream Oil & Gas Refineries: Applications for Solvent Deasphalting
title_sort machine learning for downstream oil gas refineries applications for solvent deasphalting
url https://hdl.handle.net/1721.1/140074
work_keys_str_mv AT dowellchristian machinelearningfordownstreamoilgasrefineriesapplicationsforsolventdeasphalting