Estimation of autoignition temperatures of hydrocarbons, alcohols, and esters from molecular structure

Egolf, Leanne M.; Jurs, Peter C.

doi:10.1021/ie00007a027

Cited by 44 publications

(34 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All other models show deviations higher than the GCM + ANN + PSO technique, with an AAE higher than 16 K and an AARD greather than 3 %. The low deviations found with the proposed GCM + ANN + PSO model (AAE of 10 K with AAE max a little higher than 30 K, AARD of 1.6 % and AARD max a little higher than 7 %), indicate that it can estimate the AIT of organic compounds with better accuracy than other methods available in the literature [1][2][3][4][5][6][7][8][9][10][11][12]. These results represent a tremendous increase in accuracy to predict this important property, and show that the incorporation of the descriptors: M (size) and μ (polarity and symmetry), for distinguishing between the different physical and chemical charasteristics of the substances was crucial.…”

Section: Training and Predictionmentioning

confidence: 86%

“…Molecular mass and dipole moment were chosen to characterize the different molecules [13][14][15][16][17]. Note that in other study for estimating the AIT [5][6][7][8][9][10][11][12], the authors compare their models with a great number of experimental data points for different substances. The problem is that the reliability of these experimental data was never established.…”

Section: Training and Predictionmentioning

confidence: 99%

“…In this case, the correlation coefficient R 2 is 0.9899, and for the total set, R 2 is 0.9900. Many published methods relating the AIT to chemical structure are confined to limited or small sets of substances [1][2][3][5][6][7][8][9][10][11][12]. In the literature, there are very few studies with data sets for diverse substances.…”

Section: Training and Predictionmentioning

confidence: 99%

“…Properties that are related to combustion such as the flash point, flammability limits, and AIT are often unavailable [4]. Autoignition is also studied in relation to the performance of combustion engines through the phenomenon of engine knock [5].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Autoignition Temperature Prediction Using an Artificial Neural Network with Particle Swarm Optimization

Lazzús

2011

Int J Thermophys

View full text Add to dashboard Cite

The autoignition temperatures of organic compounds were estimated using a hybrid method that includes a simple group contribution method (GCM) implemented in an artificial neural network (ANN) replacing a standard back-propagation algorithm with particle swarm optimization (PSO). A data set of 250 compounds was used for training the network. The optimal condition of the network was obtained by adjusting various parameters by trial-and-error. The capabilities of the designed network were tested in the prediction of the autoignition temperature of 93 compounds not considered during the training step. The proposed model is shown to be more accurate than those of other published works. The results show that the proposed GCM + ANN + PSO method represent an excellent alternative for the estimation of this property with acceptable accuracy (AARD = 1.7 %; AAE = 10 K).

show abstract