Prediction of Density and Viscosity of Biofuel Compounds Using Machine Learning Methods

Abstract

In the present work, temperature dependent models for the prediction of densities and dynamic viscosities of pure compounds within the range of possible alternative fuel mixture components are presented. The proposed models have been derived using machine learning methods including Artificial Neural Networks and Support Vector Machines. Experimental data used to train and validate the models was extracted from the DIPPR database. A comparison between models using an ample range of molecular descriptors and models using only functional group count descriptors as inputs was performed, and consensus models were created by testing different combinations of the individual models. The resulting consensus models’ predictions were in agreement with the available experimental data. Comparisons were also made between predictions of our models and correlations validated by the DIPPR staff. Our models were used to predict densities and dynamic viscosities of compounds for which no experimental data exists. Our models were also used to estimate other properties such as kinematic viscosities, critical temperatures, and critical pressures for compounds in the database. Finally, predictions were used to study the main trends of density and viscosity at the aforementioned temperatures as a function of the number of carbon atoms for chemical families of interest.

Rational Formulation of Alternative Fuels using QSPR Methods: Application to Jet Fuels

“…The methodology used to develop models concerning the prediction of the targeted properties is fully documented in previous papers [20,21]. The main steps are described in Figure 2.…”

“…Indeed, in our previous work we have seen that, when averaging the predictions of different models, the robustness of the resulting consensus model is better than that of the individual models used to build it [20,21]. This is why, in this work, this methodology has been applied and all possible models (i.e., weighted combinations of individual model predictions) were ranked based on their performance on the validation set.…”

“…For each property, a final performance test of the generalization ability was carried out by looking at the performance of the best consensus model performed on the test set. Full details about the methodology and validation of models are given in our previous works [20,21].…”

“…Esters are high density molecules and the density specification on esters is higher compared to Diesel fuel. Density predictions of biodiesels based on their composition have been done using our consensus model predictions with Kay's mixing [21]. The Kay's mixing is a linear regression between molar fraction and the density of pure compound.…”

Applications of Artificial Neural Networks in Biofuels

“…However, despite the diversity of topics and works published in the scientific literature, the present research is targeted to the study of the application of ANNs in the quality control of biofuels [9][10][11][12][13][14][15]. Typically, studies related to the quality control of biofuels have the goal to search efficient methods that monitor the fuels produced and commercialized avoiding damages to the environment and consumer injury [9,16].…”