Cetane number predictions of a trial index based on compositional analysis

Pande, Seetar G.; Hardy, Dennis R.

doi:10.1021/ef00015a008

Cited by 10 publications

(11 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Summary of results on the test setThe final metrics for the performance of the model on the test set are shown in Table7. The developed ANN model for DCN prediction has a low average absolute error of 0.91 compared to other DCN models with absolute errors of 1.25[54], 1.47[53], 2[57], 2.11[51], 5.8[39], 6.9[35], 7.1[34] etc. The average absolute error obtained depends on the training and test sets used, modeling approaches and the variety of chemical classes covered and therefore the present model does not claim superiority over other DCN models in lieu of the low error.…”

mentioning

confidence: 93%

“…Several methods and correlations have been developed to predict ignition quality (i.e. D/CN) of n-paraffins [41], pure hydrocarbons [35,37,[42][43][44], blends of pure hydrocarbons [37], oxygenated hydrocarbons [34,39,[45][46][47], diesel fuels [36,37,[48][49][50][51][52][53][54][55][56][57][58], synthetic diesels [59], biofuel candidates [33], furanic biofuel additives [16] and biodiesel [38,[60][61][62]. The D/CN prediction models reported in the literature have used both physical and chemical properties of the fuel as model inputs.…”

Section: Introductionmentioning

confidence: 99%

“…Molecular structure based techniques like quantitative structure property relationships (QSPR) [16,34,35,42,44], group contribution [39,43], hydrocarbon lumps [54], functional groups [37,58,59,64], carbon groups [53] and principal component analysis [45], have also been employed for predicting D/CN. Analytical techniques such as nuclear magnetic resonance (NMR) spectroscopy [37,45,51,53,58,65], gas chromatography coupled with mass spectroscopy (GC-MS) [56], near infra-red spectroscopy (NIR) [50] and high performance liquid chromatography (HPLC) [51] have also found applications in developing chemical composition based techniques for D/CN prediction.…”

Section: Introductionmentioning

confidence: 99%

“…The average absolute error obtained depends on the training and test sets used, modeling approaches and the variety of chemical classes covered and therefore the present model does not claim superiority over other DCN models in lieu of the low error. Some[35,51,53,54] of these DCN models are valid only for non-oxygenated fuels whose fuel chemistry is less complex whilst other models[34,39] cover a wider range of oxygenates including esters, ketones, acids and aldehydes. The present model can predict DCN of pure compounds, pure hydrocarbon and oxygenate blends, and oxygenated petroleum fuels containing alcohol and ether functionalities as these oxygenated chemical classes are more commonly used in diesel fuels as additives.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Predicting Ignition Quality of Oxygenated Fuels Using Artificial Neural Networks

Jameel

Oudenhoven

Naser

et al. 2021

SAE Int. J. Fuels Lubr.

View full text Add to dashboard Cite

Artificial intelligence based computing systems like artificial neural networks (ANN) have recently found increasing applications in predicting complex chemical phenomena like combustion properties. The present work deals with the development of an ANN model which can predict the derived cetane number (DCN) of oxygenated fuels containing alcohol and ether functionalities. Experimental DCN's of 499 fuels comprising of 116 pure compounds, 222 pure compound blends, and 159 real fuel blends were used as the dataset for model development. DCN measurements of sixty new fuels were carried out in the present work and the data for the rest was collected from the literature. Fuel chemical composition expressed in the form of eight functional groups namely paraffinic CH3 groups, paraffinic CH2 groups, paraffinic CH groups, olefinic -CH=CH2 groups, naphthenic CH-CH2 groups, aromatic C-CH groups, alcoholic OH groups and ether O groups, along with two structural parameters namely, molecular weight and branching index (BI), were used as the ten input features of the model. The qualitative and quantitative determination of functional groups present in real fuels was performed using 1 H nuclear magnetic resonance (NMR) spectroscopy. A robust ANN methodology was followed to prevent over fitting using a multilevel grid search and genetic algorithm. The final developed model with two hidden layers was tested with 15 % of randomly generated unseen points from the dataset and a regression coefficient (R 2 ) of 0.992 was observed between the experimental and predicted DCN values. An average absolute error of 0.91 obtained from the test set indicates that the developed ANN model is successful in predicting the DCN of oxygenated fuels and captures the dependence of the fuel's ignition quality (i.e. DCN) on its constituent functional groups.

show abstract

mentioning

confidence: 93%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Predicting Ignition Quality of Oxygenated Fuels Using Artificial Neural Networks

Jameel

Oudenhoven

Naser

et al. 2021

SAE Int. J. Fuels Lubr.

View full text Add to dashboard Cite

show abstract

“…Other studies use analytical methods and chemometrics to relate fuel composition to its ignition quality through nuclear magnetic resonance (NMR), − gas chromatography–mass spectroscopy (GC–MS), − liquid chromatography (LC), , supercritical fluid chromatographic techniques, high-performance liquid chromatography (HPLC), vibrational spectroscopy, and near-infrared spectroscopy (NIR) . For example, some models estimated the cetane number of biodiesels from their fatty acid methyl ester composition − and the relative amounts of CH and CH 2 in synthetic diesel fuels …”

Section: Introductionmentioning

confidence: 99%

Prediction of the Derived Cetane Number and Carbon/Hydrogen Ratio from Infrared Spectroscopic Data

Ibrahim

Farooq

2021

Energy Fuels

View full text Add to dashboard Cite

A model for the prediction of the derived cetane number (DCN) and carbon/hydrogen ratio (C/H) of hydrocarbon mixtures, diesel fuels, and diesel−gasoline blends has been developed on the basis of infrared (IR) spectroscopy data of pure components. IR spectra of 65 neat hydrocarbon species were used to generate spectra of 127 hydrocarbon blends by averaging the spectra of their pure components on a molar basis. The spectra of 44 real fuels were calculated using n-paraffin, isoparaffin, olefin, naphthene, aromatic, and oxygenate (PIONA-O) class averages of pure components. It is shown that this strategy retains knowledge of C/H, an important indicator of the chemical structure. Three methods were compared to assess the prediction of DCN and C/H ratio from the assembled IR spectra, i.e., partial least squares regression (PLSR), support vector machine (SVM), and artificial neural network (ANN). It was found that ANNs gave the best performance with DCN prediction errors of ±1.1 on average and C/H prediction errors of ∼0.8%. Lasso-regularized linear models were also used to find simple combinations of wavenumbers that yield acceptable estimations.

show abstract

Use of Inspection Properties to Predict Hydrocarbon Fraction Physical Properties

Nick¹

2000

Encyclopedia of Analytical Chemistry

View full text Add to dashboard Cite

The chemical complexity of petroleum products has, until recently, precluded calculational techniques based on a definitive analysis of the molecular species involved. Instead, readily observed or easily (quick and inexpensively) measured macroscopic properties (gravity, boiling range, etc.) have been used to correlate information empirically. In some instances, the predictions have been “tweaked” on a local data‐centric basis or extended by quasi‐theoretical analysis. Recent computer‐aided advancements 134 in multivariate electromagnetic emission, NMR (nuclear magnetic resonance) and/or MS (mass spectroscopy) analyses allow for the reliable and repeatable use of much more detailed experimental data. The ability to speciate cuts by individual chemical components will revolutionize both refining and regulation of refined products in response to the availability of quality data. So why would one bother with older analysis and prediction methods? It is likely, given the operational sophistication and investment costs needed to deliver this highly speciated information properly, that the old ways will die but slowly. Most refineries and petrochemical plants try to get by with the minimum amount of expensive on‐line analyzers. Multivariate data generation is not yet at a state where it can easily be used for real‐time process or even product quality control. This barrier will exist for some time to come. The historical development of crude oil processing technology has generated a great volume of data and “general” correlations, some contradictory. Most of the data upon which these methods are based have been around for 60 or more years. Many have withstood the “test of time”, being examined and verified by numerous researchers both public and private. Some of the precision of the older data may not be as good as what is generated today, but new entries to various refinery products' databanks seem to confirm the validity of the best of the older procedures and data. The classical methods allow one to impute several otherwise unavailable characterizing pieces of data. It is essential that those engaged in the design and analysis of refinery units (which have multiple feed and product streams) become familiar with classical terminology and techniques, and eventually acquire an intuitive sense of what constitutes the “best answer” when confronted with several conflicting alternatives. The subject of this article is the proper methodology of imputing this knowledge from whatever data are at hand.

show abstract

Cetane number predictions of a trial index based on compositional analysis

Cited by 10 publications

References 3 publications

Predicting Ignition Quality of Oxygenated Fuels Using Artificial Neural Networks

Predicting Ignition Quality of Oxygenated Fuels Using Artificial Neural Networks

Prediction of the Derived Cetane Number and Carbon/Hydrogen Ratio from Infrared Spectroscopic Data

Use of Inspection Properties to Predict Hydrocarbon Fraction Physical Properties

Contact Info

Product

Resources

About