Loading…
A Neural Network Approach to the Prediction of Cetane Number of Diesel Fuels Using Nuclear Magnetic Resonance (NMR) Spectroscopy
In this work, quantitative relationships between the structural parameters of diesel fuels, as observed by 1H NMR spectroscopy, have been established, with their ignition delay characteristics, using the artificial neural network (ANN) technique. Sixty commercial diesel samples were analyzed for thi...
Saved in:
Published in: | Energy & fuels 2003-11, Vol.17 (6), p.1570-1575 |
---|---|
Main Authors: | , , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | cdi_FETCH-LOGICAL-a325t-6db2ec870212130ef1c59b5ed15de2ed78b036882e7bbf2bdb9758ab5a061b9b3 |
---|---|
cites | cdi_FETCH-LOGICAL-a325t-6db2ec870212130ef1c59b5ed15de2ed78b036882e7bbf2bdb9758ab5a061b9b3 |
container_end_page | 1575 |
container_issue | 6 |
container_start_page | 1570 |
container_title | Energy & fuels |
container_volume | 17 |
creator | Basu, B Kapur, G. S Sarpal, A. S Meusinger, R |
description | In this work, quantitative relationships between the structural parameters of diesel fuels, as observed by 1H NMR spectroscopy, have been established, with their ignition delay characteristics, using the artificial neural network (ANN) technique. Sixty commercial diesel samples were analyzed for this study. The cetane number (CN) of the samples was determined on an ignition quality tester (IQT). The 1H NMR spectra of the samples were used as their structural characteristics, and relative intensities of various regions in the spectra were used as neural network inputs. The spectra in each case were divided into 18 regions, representing paraffins (normal and iso), cycloalkanes, olefins, and aromatics (different types). The development of the ANN model presented difficulties, because the data set consisted of only 60 samples for 18 input (NMR) parameters and 1 output (CN) parameter. Therefore, the data set was compressed to 8 input parameters by training a primary neural network in which inputs and outputs were the same. The hidden layer of the developed primary network, containing eight nodes, was then used as the inputs and CN was used as the output for the development of the final network. The primary network for data compression and the final network for CN prediction were then appended together. The pattern set was appropriately divided into subsets for development and validation of the final model. The developed model when tested on the unseen data set, gave a very high correlation between the actual and predicted CN values. |
doi_str_mv | 10.1021/ef030083f |
format | article |
fullrecord | <record><control><sourceid>acs_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1021_ef030083f</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>c203882043</sourcerecordid><originalsourceid>FETCH-LOGICAL-a325t-6db2ec870212130ef1c59b5ed15de2ed78b036882e7bbf2bdb9758ab5a061b9b3</originalsourceid><addsrcrecordid>eNptUMtOwzAQtBBIlMeBP_AFiR4CfuDEOZbyKBKUN0JcLNvZ0LRpHNmuoDc-naAiuHAaaWd2ZncQ2qPkkBJGj6AknBDJyzXUo4KRRBCWr6MekTJLSMqON9FWCFNCSMql6KHPAR7Dwuu6g_ju_AwP2tY7bSc4OhwngG89FJWNlWuwK_EQom4AjxdzA_57cFpBgBqfL6AO-ClUzVtH2hq0x9f6rYFYWXwPwTW6sYAPxtf3ffzQgo3eBeva5Q7aKHUdYPcHt9HT-dnjcJRc3VxcDgdXieZMxCQtDAMrs-5HRjmBklqRGwEFFQUwKDJpCE-lZJAZUzJTmDwTUhuhSUpNbvg26q98bRccPJSq9dVc-6WiRH1Xp36r67T7K22rg9V16bvbq_C3IFh-nHPR6ZKVrgoRPn557WcqzXgm1OPtg6J3rycj-izUy5-vtkFN3cI33cf_5H8B_zmJ3g</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>A Neural Network Approach to the Prediction of Cetane Number of Diesel Fuels Using Nuclear Magnetic Resonance (NMR) Spectroscopy</title><source>American Chemical Society:Jisc Collections:American Chemical Society Read & Publish Agreement 2022-2024 (Reading list)</source><creator>Basu, B ; Kapur, G. S ; Sarpal, A. S ; Meusinger, R</creator><creatorcontrib>Basu, B ; Kapur, G. S ; Sarpal, A. S ; Meusinger, R</creatorcontrib><description>In this work, quantitative relationships between the structural parameters of diesel fuels, as observed by 1H NMR spectroscopy, have been established, with their ignition delay characteristics, using the artificial neural network (ANN) technique. Sixty commercial diesel samples were analyzed for this study. The cetane number (CN) of the samples was determined on an ignition quality tester (IQT). The 1H NMR spectra of the samples were used as their structural characteristics, and relative intensities of various regions in the spectra were used as neural network inputs. The spectra in each case were divided into 18 regions, representing paraffins (normal and iso), cycloalkanes, olefins, and aromatics (different types). The development of the ANN model presented difficulties, because the data set consisted of only 60 samples for 18 input (NMR) parameters and 1 output (CN) parameter. Therefore, the data set was compressed to 8 input parameters by training a primary neural network in which inputs and outputs were the same. The hidden layer of the developed primary network, containing eight nodes, was then used as the inputs and CN was used as the output for the development of the final network. The primary network for data compression and the final network for CN prediction were then appended together. The pattern set was appropriately divided into subsets for development and validation of the final model. The developed model when tested on the unseen data set, gave a very high correlation between the actual and predicted CN values.</description><identifier>ISSN: 0887-0624</identifier><identifier>EISSN: 1520-5029</identifier><identifier>DOI: 10.1021/ef030083f</identifier><identifier>CODEN: ENFUEM</identifier><language>eng</language><publisher>Washington, DC: American Chemical Society</publisher><subject>Applied sciences ; Crude oil, natural gas and petroleum products ; Energy ; Exact sciences and technology ; Fuels ; Petroleum products, gas and fuels. Motor fuels, lubricants and asphalts</subject><ispartof>Energy & fuels, 2003-11, Vol.17 (6), p.1570-1575</ispartof><rights>Copyright © 2003 American Chemical Society</rights><rights>2004 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-a325t-6db2ec870212130ef1c59b5ed15de2ed78b036882e7bbf2bdb9758ab5a061b9b3</citedby><cites>FETCH-LOGICAL-a325t-6db2ec870212130ef1c59b5ed15de2ed78b036882e7bbf2bdb9758ab5a061b9b3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=15294935$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><creatorcontrib>Basu, B</creatorcontrib><creatorcontrib>Kapur, G. S</creatorcontrib><creatorcontrib>Sarpal, A. S</creatorcontrib><creatorcontrib>Meusinger, R</creatorcontrib><title>A Neural Network Approach to the Prediction of Cetane Number of Diesel Fuels Using Nuclear Magnetic Resonance (NMR) Spectroscopy</title><title>Energy & fuels</title><addtitle>Energy Fuels</addtitle><description>In this work, quantitative relationships between the structural parameters of diesel fuels, as observed by 1H NMR spectroscopy, have been established, with their ignition delay characteristics, using the artificial neural network (ANN) technique. Sixty commercial diesel samples were analyzed for this study. The cetane number (CN) of the samples was determined on an ignition quality tester (IQT). The 1H NMR spectra of the samples were used as their structural characteristics, and relative intensities of various regions in the spectra were used as neural network inputs. The spectra in each case were divided into 18 regions, representing paraffins (normal and iso), cycloalkanes, olefins, and aromatics (different types). The development of the ANN model presented difficulties, because the data set consisted of only 60 samples for 18 input (NMR) parameters and 1 output (CN) parameter. Therefore, the data set was compressed to 8 input parameters by training a primary neural network in which inputs and outputs were the same. The hidden layer of the developed primary network, containing eight nodes, was then used as the inputs and CN was used as the output for the development of the final network. The primary network for data compression and the final network for CN prediction were then appended together. The pattern set was appropriately divided into subsets for development and validation of the final model. The developed model when tested on the unseen data set, gave a very high correlation between the actual and predicted CN values.</description><subject>Applied sciences</subject><subject>Crude oil, natural gas and petroleum products</subject><subject>Energy</subject><subject>Exact sciences and technology</subject><subject>Fuels</subject><subject>Petroleum products, gas and fuels. Motor fuels, lubricants and asphalts</subject><issn>0887-0624</issn><issn>1520-5029</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2003</creationdate><recordtype>article</recordtype><recordid>eNptUMtOwzAQtBBIlMeBP_AFiR4CfuDEOZbyKBKUN0JcLNvZ0LRpHNmuoDc-naAiuHAaaWd2ZncQ2qPkkBJGj6AknBDJyzXUo4KRRBCWr6MekTJLSMqON9FWCFNCSMql6KHPAR7Dwuu6g_ju_AwP2tY7bSc4OhwngG89FJWNlWuwK_EQom4AjxdzA_57cFpBgBqfL6AO-ClUzVtH2hq0x9f6rYFYWXwPwTW6sYAPxtf3ffzQgo3eBeva5Q7aKHUdYPcHt9HT-dnjcJRc3VxcDgdXieZMxCQtDAMrs-5HRjmBklqRGwEFFQUwKDJpCE-lZJAZUzJTmDwTUhuhSUpNbvg26q98bRccPJSq9dVc-6WiRH1Xp36r67T7K22rg9V16bvbq_C3IFh-nHPR6ZKVrgoRPn557WcqzXgm1OPtg6J3rycj-izUy5-vtkFN3cI33cf_5H8B_zmJ3g</recordid><startdate>20031101</startdate><enddate>20031101</enddate><creator>Basu, B</creator><creator>Kapur, G. S</creator><creator>Sarpal, A. S</creator><creator>Meusinger, R</creator><general>American Chemical Society</general><scope>BSCLL</scope><scope>IQODW</scope><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20031101</creationdate><title>A Neural Network Approach to the Prediction of Cetane Number of Diesel Fuels Using Nuclear Magnetic Resonance (NMR) Spectroscopy</title><author>Basu, B ; Kapur, G. S ; Sarpal, A. S ; Meusinger, R</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a325t-6db2ec870212130ef1c59b5ed15de2ed78b036882e7bbf2bdb9758ab5a061b9b3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2003</creationdate><topic>Applied sciences</topic><topic>Crude oil, natural gas and petroleum products</topic><topic>Energy</topic><topic>Exact sciences and technology</topic><topic>Fuels</topic><topic>Petroleum products, gas and fuels. Motor fuels, lubricants and asphalts</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Basu, B</creatorcontrib><creatorcontrib>Kapur, G. S</creatorcontrib><creatorcontrib>Sarpal, A. S</creatorcontrib><creatorcontrib>Meusinger, R</creatorcontrib><collection>Istex</collection><collection>Pascal-Francis</collection><collection>CrossRef</collection><jtitle>Energy & fuels</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Basu, B</au><au>Kapur, G. S</au><au>Sarpal, A. S</au><au>Meusinger, R</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Neural Network Approach to the Prediction of Cetane Number of Diesel Fuels Using Nuclear Magnetic Resonance (NMR) Spectroscopy</atitle><jtitle>Energy & fuels</jtitle><addtitle>Energy Fuels</addtitle><date>2003-11-01</date><risdate>2003</risdate><volume>17</volume><issue>6</issue><spage>1570</spage><epage>1575</epage><pages>1570-1575</pages><issn>0887-0624</issn><eissn>1520-5029</eissn><coden>ENFUEM</coden><abstract>In this work, quantitative relationships between the structural parameters of diesel fuels, as observed by 1H NMR spectroscopy, have been established, with their ignition delay characteristics, using the artificial neural network (ANN) technique. Sixty commercial diesel samples were analyzed for this study. The cetane number (CN) of the samples was determined on an ignition quality tester (IQT). The 1H NMR spectra of the samples were used as their structural characteristics, and relative intensities of various regions in the spectra were used as neural network inputs. The spectra in each case were divided into 18 regions, representing paraffins (normal and iso), cycloalkanes, olefins, and aromatics (different types). The development of the ANN model presented difficulties, because the data set consisted of only 60 samples for 18 input (NMR) parameters and 1 output (CN) parameter. Therefore, the data set was compressed to 8 input parameters by training a primary neural network in which inputs and outputs were the same. The hidden layer of the developed primary network, containing eight nodes, was then used as the inputs and CN was used as the output for the development of the final network. The primary network for data compression and the final network for CN prediction were then appended together. The pattern set was appropriately divided into subsets for development and validation of the final model. The developed model when tested on the unseen data set, gave a very high correlation between the actual and predicted CN values.</abstract><cop>Washington, DC</cop><pub>American Chemical Society</pub><doi>10.1021/ef030083f</doi><tpages>6</tpages></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0887-0624 |
ispartof | Energy & fuels, 2003-11, Vol.17 (6), p.1570-1575 |
issn | 0887-0624 1520-5029 |
language | eng |
recordid | cdi_crossref_primary_10_1021_ef030083f |
source | American Chemical Society:Jisc Collections:American Chemical Society Read & Publish Agreement 2022-2024 (Reading list) |
subjects | Applied sciences Crude oil, natural gas and petroleum products Energy Exact sciences and technology Fuels Petroleum products, gas and fuels. Motor fuels, lubricants and asphalts |
title | A Neural Network Approach to the Prediction of Cetane Number of Diesel Fuels Using Nuclear Magnetic Resonance (NMR) Spectroscopy |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T18%3A20%3A04IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-acs_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Neural%20Network%20Approach%20to%20the%20Prediction%20of%20Cetane%20Number%20of%20Diesel%20Fuels%20Using%20Nuclear%20Magnetic%20Resonance%20(NMR)%20Spectroscopy&rft.jtitle=Energy%20&%20fuels&rft.au=Basu,%20B&rft.date=2003-11-01&rft.volume=17&rft.issue=6&rft.spage=1570&rft.epage=1575&rft.pages=1570-1575&rft.issn=0887-0624&rft.eissn=1520-5029&rft.coden=ENFUEM&rft_id=info:doi/10.1021/ef030083f&rft_dat=%3Cacs_cross%3Ec203882043%3C/acs_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-a325t-6db2ec870212130ef1c59b5ed15de2ed78b036882e7bbf2bdb9758ab5a061b9b3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |