Predictive Modeling of the Hydrate Formation Temperature in Highly Pressurized Natural Gas Pipelines

In this study, we aim to develop advanced machine learning regression models for the prediction of hydrate temperature based on the chemical composition of sweet gas mixtures. Data were collected in accordance with the BOTAS Gas Network Code specifications, approved by the Turkish Energy Market Regu...

Full description

Saved in:
Bibliographic Details
Main Authors: Mustafa Karaköse, Özgün Yücel
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/17/21/5306
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850041954787655680
author Mustafa Karaköse
Özgün Yücel
author_facet Mustafa Karaköse
Özgün Yücel
author_sort Mustafa Karaköse
collection DOAJ
description In this study, we aim to develop advanced machine learning regression models for the prediction of hydrate temperature based on the chemical composition of sweet gas mixtures. Data were collected in accordance with the BOTAS Gas Network Code specifications, approved by the Turkish Energy Market Regulatory Authority (EMRA), and generated using DNV GasVLe v3.10 software, which predicts the phase behavior and properties of hydrocarbon-based mixtures under various pressure and temperature conditions. We employed linear regression, decision tree regression, random forest regression, generalized additive models, and artificial neural networks to create prediction models for hydrate formation temperature (HFT). The performance of these models was evaluated using the hold-out cross-validation technique to ensure unbiased results. This study demonstrates the efficacy of ensemble learning methods, particularly random forest with an <i>R</i><sup>2</sup> and <i>Adj. R</i><sup>2</sup> of 0.998, for predicting hydrate formation conditions, thereby enhancing the safety and efficiency of gas transport and processing. This research illustrates the potential of machine learning techniques in advancing the predictive accuracy for hydrate formations in natural gas pipelines and suggests avenues for future optimizations through hybrid modeling approaches.
format Article
id doaj-art-65a1e8df45e04ea4b45656500d7e596c
institution DOAJ
issn 1996-1073
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-65a1e8df45e04ea4b45656500d7e596c2025-08-20T02:55:39ZengMDPI AGEnergies1996-10732024-10-011721530610.3390/en17215306Predictive Modeling of the Hydrate Formation Temperature in Highly Pressurized Natural Gas PipelinesMustafa Karaköse0Özgün Yücel1Department of Chemical Engineering, Gebze Technical University, Kocaeli 41400, TurkeyDepartment of Chemical Engineering, Gebze Technical University, Kocaeli 41400, TurkeyIn this study, we aim to develop advanced machine learning regression models for the prediction of hydrate temperature based on the chemical composition of sweet gas mixtures. Data were collected in accordance with the BOTAS Gas Network Code specifications, approved by the Turkish Energy Market Regulatory Authority (EMRA), and generated using DNV GasVLe v3.10 software, which predicts the phase behavior and properties of hydrocarbon-based mixtures under various pressure and temperature conditions. We employed linear regression, decision tree regression, random forest regression, generalized additive models, and artificial neural networks to create prediction models for hydrate formation temperature (HFT). The performance of these models was evaluated using the hold-out cross-validation technique to ensure unbiased results. This study demonstrates the efficacy of ensemble learning methods, particularly random forest with an <i>R</i><sup>2</sup> and <i>Adj. R</i><sup>2</sup> of 0.998, for predicting hydrate formation conditions, thereby enhancing the safety and efficiency of gas transport and processing. This research illustrates the potential of machine learning techniques in advancing the predictive accuracy for hydrate formations in natural gas pipelines and suggests avenues for future optimizations through hybrid modeling approaches.https://www.mdpi.com/1996-1073/17/21/5306machine learninghydrate formationmethanenatural gassupervised
spellingShingle Mustafa Karaköse
Özgün Yücel
Predictive Modeling of the Hydrate Formation Temperature in Highly Pressurized Natural Gas Pipelines
Energies
machine learning
hydrate formation
methane
natural gas
supervised
title Predictive Modeling of the Hydrate Formation Temperature in Highly Pressurized Natural Gas Pipelines
title_full Predictive Modeling of the Hydrate Formation Temperature in Highly Pressurized Natural Gas Pipelines
title_fullStr Predictive Modeling of the Hydrate Formation Temperature in Highly Pressurized Natural Gas Pipelines
title_full_unstemmed Predictive Modeling of the Hydrate Formation Temperature in Highly Pressurized Natural Gas Pipelines
title_short Predictive Modeling of the Hydrate Formation Temperature in Highly Pressurized Natural Gas Pipelines
title_sort predictive modeling of the hydrate formation temperature in highly pressurized natural gas pipelines
topic machine learning
hydrate formation
methane
natural gas
supervised
url https://www.mdpi.com/1996-1073/17/21/5306
work_keys_str_mv AT mustafakarakose predictivemodelingofthehydrateformationtemperatureinhighlypressurizednaturalgaspipelines
AT ozgunyucel predictivemodelingofthehydrateformationtemperatureinhighlypressurizednaturalgaspipelines