Saldana, D. A.; Starck, L.; Mougin, P.; Rousseau, B.; Pidol, L.; Jeuland, N.; Creton, B. Flash Point and Cetane Number Predictions for Fuel Compounds Using Quantitative Structure Property Relationship (QSPR) Methods. Energy Fuels 2011, 25, 9, 3900–3908.

QsarDB Repository

Saldana, D. A.; Starck, L.; Mougin, P.; Rousseau, B.; Pidol, L.; Jeuland, N.; Creton, B. Flash Point and Cetane Number Predictions for Fuel Compounds Using Quantitative Structure Property Relationship (QSPR) Methods. Energy Fuels 2011, 25, 9, 3900–3908.

QDB archive DOI: 10.15152/QDB.123   DOWNLOAD

QsarDB content

Property FP: Flash point [K]

FP_PLS-MD: PLS-MD model for flash point i

Regression model (regression)

Open in:QDB ExplorerQDB Predictor

NameTypen

R2

σ

Training set itraining4450.93614.387
Test set iexternal validation630.85921.994
Validation set iexternal validation1230.93613.703
Prediction set itesting528N/AN/A
FP_SVM-GD: SVM-GD model for flash point i

Support vector machine (regression)

Open in:QDB ExplorerQDB Predictor

NameTypen

R2

σ

Training set itraining4450.96610.550
Test set iexternal validation630.94213.861
Validation set iexternal validation1230.95311.685
Prediction set itesting528N/AN/A
FP_NN-MD: NN-MD model for flash point i

Neural network ensemble (regression)

Open in:QDB ExplorerQDB Predictor

NameTypen

R2

σ

Training set itraining4450.94713.247
Test set iexternal validation630.93814.201
Validation set iexternal validation1230.96110.710
Prediction set itesting528N/AN/A
FP_NN-GD: NN-GD model for flash point i

Neural network ensemble (regression)

Open in:QDB ExplorerQDB Predictor

NameTypen

R2

σ

Training set itraining4450.95512.133
Validation set iexternal validation1230.95910.941
Test set iexternal validation630.93814.152
Prediction set itesting528N/AN/A
FP_consensus: Consensus model for flash point i

Ensemble model (regression)

Open in:QDB ExplorerQDB Predictor

NameTypen

R2

σ

Training set itraining4450.96410.902
Test set iexternal validation630.94513.308
Validation set iexternal validation1230.9709.429
Prediction set itesting528N/AN/A

Property CN: Cetane number

CN_SVM-GD: SVM-GD model for cetane number i

Support vector machine (regression)

Open in:QDB ExplorerQDB Predictor

NameTypen

R2

σ

Training set itraining2080.9605.401
Test set iexternal validation200.72714.893
Validation set iexternal validation560.80612.458
Unreliable experimental values iexternal validation460.71117.536
Prediction set itesting829N/AN/A
CN_SVM-MD: SVM-MD model for cetane number i

Support vector machine (regression)

Open in:QDB ExplorerQDB Predictor

NameTypen

R2

σ

Training set itraining2080.9555.713
Test set iexternal validation200.9366.615
Validation set iexternal validation560.9008.615
Unreliable experimental values iexternal validation460.72716.916
Prediction set itesting829N/AN/A
CN_NN-MD: NN-MD model for cetane number i

Neural network ensemble (regression)

Open in:QDB ExplorerQDB Predictor

NameTypen

R2

σ

Training set itraining2080.9635.356
Test set iexternal validation200.9784.623
Validation set iexternal validation560.84611.367
Unreliable experimental values iexternal validation460.66818.751
Prediction set itesting829N/AN/A
CN_GRNN-MD: GRNN-MD model for cetane number i

Neural network (regression)

Open in:QDB ExplorerQDB Predictor

NameTypen

R2

σ

Training set itraining2080.8889.247
Test set iexternal validation200.57916.931
Validation set iexternal validation560.63216.099
Unreliable experimental values iexternal validation460.54822.583
Prediction set itesting829N/AN/A

Citing

When using this QDB archive, please cite (see details) it together with the original article:

  • Piir, G. Data for: Flash Point and Cetane Number Predictions for Fuel Compounds Using Quantitative Structure Property Relationship (QSPR) Methods. QsarDB repository, QDB.123. 2014. http://dx.doi.org/10.15152/QDB.123

  • Saldana, D. A.; Starck, L.; Mougin, P.; Rousseau, B.; Pidol, L.; Jeuland, N.; Creton, B. Flash Point and Cetane Number Predictions for Fuel Compounds Using Quantitative Structure Property Relationship (QSPR) Methods. Energy Fuels 2011, 25, 3900–3908. http://dx.doi.org/10.1021/ef200795j

Metadata

Show simple item record

dc.date.accessioned2014-11-07T12:43:12Z
dc.date.available2014-11-07T12:43:12Z
dc.date.issued2014-11-07*
dc.identifier.urihttp://hdl.handle.net/10967/123
dc.identifier.urihttp://dx.doi.org/10.15152/QDB.123
dc.description.abstractIn the present work, we report the development of models for the prediction of two fuel properties: flash points (FPs) and cetane numbers (CNs), using quantitative structure property relationship (QSPR) approaches. Compounds inside the scope of the QSPR models are those likely to be found in alternative jet and diesel fuels, i.e., hydrocarbons, alcohols, and esters. A database containing FPs and CNs for these types of molecules has been built using experimental data available in the literature. Various approaches have been used, ranging from those leading to linear models, such as genetic function approximation and partial least squares, to those leading to nonlinear models, such as feed-forward artificial neural networks, general regression neural networks, support vector machines, and graph machines. Except for the case of the graph machine method, for which the only inputs are the simplified molecular input line entry specification (SMILES) formulas, previously listed approaches working on molecular descriptors and functional group count descriptors were used to build specific models for FPs and CNs. For each property, the predictive models return slightly different responses for each molecular structure. Thus, final models labeled as “consensus models” were built by averaging the predicted values of selected individual models. Predicted results were compared with respect to experimental data and predictions of existing models in the literature. Models were used to predict FPs and CNs of molecules for which to the best of our knowledge there is no experimental data in the literature. Using information in the database, evolutions of properties when increasing the number of carbon atoms in families of compounds were studied.
dc.publisherGeven Piir
dc.rightsAttribution 4.0 International
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.titleSaldana, D. A.; Starck, L.; Mougin, P.; Rousseau, B.; Pidol, L.; Jeuland, N.; Creton, B. Flash Point and Cetane Number Predictions for Fuel Compounds Using Quantitative Structure Property Relationship (QSPR) Methods. Energy Fuels 2011, 25, 9, 3900–3908.
qdb.property.endpoint1. Physical Chemical Properties 1.19. Flash pointen_US
qdb.property.endpoint6. Other (Cetane number)en_US
qdb.descriptor.applicationMaterials Studio 5.0en_US
bibtex.entryarticleen_US
bibtex.entry.authorSaldana, D. A.
bibtex.entry.authorStarck, L.
bibtex.entry.authorMougin, P.
bibtex.entry.authorRousseau, B.
bibtex.entry.authorPidol, L.
bibtex.entry.authorJeuland, N.
bibtex.entry.authorCreton, B.
bibtex.entry.doi10.1021/ef200795jen_US
bibtex.entry.journalEnergy Fuelsen_US
bibtex.entry.monthSep
bibtex.entry.number9en_US
bibtex.entry.pages3900–3908en_US
bibtex.entry.titleFlash Point and Cetane Number Predictions for Fuel Compounds Using Quantitative Structure Property Relationship (QSPR) Methodsen_US
bibtex.entry.volume25en_US
bibtex.entry.year2011
qdb.model.typeRegression model (regression)en_US
qdb.model.typeSupport vector machine (regression)en_US
qdb.model.typeEnsemble model (regression)en_US
qdb.model.typeNeural network (regression)en_US
qdb.model.typeNeural network ensemble (regression)


Files in this item

NameDescriptionFormatSizeView
2011EF3900.zipQSPR models for the flash point and cetane numberapplication/zip1.976MbView/Open
Files associated with this item are distributed
under Creative Commons license.

This item appears in the following Collection(s)

Show simple item record