Artificial Neural Network for Predicting Cetane Number of Biofuel Candidates Based on Molecular Structure

Sennott, Timothy; Gotianun, Chris; Serres, Romain; Ziabasharhagh, Masoud; Mack, J. Hunter; Dibble, Robert W.

doi:10.1115/icef2013-19185

Cited by 14 publications

(22 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ANNs provide a non-linear model architecture, allowing a multidimensional input vector containing a suite of individual QSPR values to be correlated to an experimental property value. QSPR descriptors are utilized due to the wide range of physical and chemical property representations available, subsequently distinguishing one molecule from another [26].…”

Section: Predicting Cetane Number and Yield Sooting Indexmentioning

confidence: 99%

Screening Compounds for Fast Pyrolysis and Catalytic Biofuel Upgrading Using Artificial Neural Networks

Kessler¹,

Schwartz²,

Wong³

et al. 2019

Preprint

View full text Add to dashboard Cite

There is significant interest among researchers in finding economically sustainable alternatives to fossil-derived drop-in fuels and fuel additives. Fast pyrolysis, a method for converting biomass into liquid hydrocarbons with the potential for use as fuels or fuel additives, is a promising technology that can be two to three times less expensive at scale when compared to alternative approaches such as gasification and fermentation. However, many bio-oils directly derived from fast pyrolysis have a high oxygen content and high acidity, indicating poor performance in diesel engines when used as fuels or fuel additives. Thus, a combination of selective fast pyrolysis and chemical catalysis could produce tuned bioblendstocks that perform optimally in diesel engines. The variance in performance for derived compounds introduces a feedback loop in researching acceptable fuels and fuel additives, as various combustion properties for these compounds must be determined after pyrolysis and catalytic upgrading occurs. The present work aims to reduce this feedback loop by utilizing artificial neural networks trained with quantitative structure-property relationship values to preemptively screen pure component compounds that will be produced from fast pyrolysis and catalytic upgrading. The quantitative structure-property relationship values selected as inputs for models are discussed, the cetane number and sooting propensity of compounds derived from the catalytic upgrading of phenol are predicted, and the viability of these compounds as fuels and fuel additives is analyzed. The model constructed to predict cetane number has a test set prediction root-mean-squared error of 9.874 cetane units, and the model constructed to predict yield sooting index has a test set prediction root-mean-squared error of 13.478 yield sooting index units (on the unified scale).

show abstract

Section: Predicting Cetane Number and Yield Sooting Indexmentioning

confidence: 99%

Screening Compounds for Fast Pyrolysis and Catalytic Biofuel Upgrading Using Artificial Neural Networks

Kessler¹,

Schwartz²,

Wong³

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…This is due to the fact that many of the values for some parameters are equal for the majority of molecules, which is detrimental to the neural network and unhelpful in capturing the nonlinear behavior. Historically, 14-23 descriptors have been chosen for similar approaches in the literature [5][6][7]11]. The process is repeatable across multiple attempts, which suggests that the chosen set is likely to be the most influential descriptors in regards to CN prediction for this database.…”

Section: Neural Network Architecturementioning

confidence: 99%

“…In light of the advances and drawbacks inherent to previous models, this paper adopts a backpropagation neural network approach since it appears to be more robust across multiple molecular classes/families due to their nonlinear architecture, which allows for a representation of very complex relationships between input and output vectors [11]. The goal of this paper is twofold: (1) improve upon the state-of-the art models for predicting CN for a diverse data set, and (2) extend the model to consider a new molecular class (furanic compounds).…”

Section: Predicting the Cetane Numbermentioning

confidence: 99%

Predicting the Cetane Number of Furanic Biofuel Candidates Using an Improved Artificial Neural Network Based on Molecular Structure

Kessler¹,

Sacia²,

Bell³

et al. 2017

Preprint

View full text Add to dashboard Cite

TitlePredicting the cetane number of furanic biofuel candidates using an improved artificial neural network based on molecular structure b s t r a c tThe next generation of alternative fuels is being investigated through advanced chemical and biological production techniques for the purpose of finding suitable replacements for diesel and gasoline while lowering production costs and increasing process yields. Chemical conversion of biomass to fuels provides a plethora of pathways with a variety of fuel molecules, both novel and traditional, which may be targeted. In the search for new fuels, an initial, intuition-driven evaluation of fuel compounds with desired properties is required. Due to the high cost and significant production time needed to synthesize these materials at a scale sufficient for exhaustive testing, a predictive model would allow chemists to preemptively screen fuel properties of potentially desirable fuel candidates. Recent work has shown that predictive models, in this case artificial neural networks (ANN's) analyzing quantitative structure property relationships (QSPR's), can predict the cetane number (CN) of a proposed fuel molecule with relatively small error. A fuel's CN is a measure of its ignition quality, typically defined using prescribed ASTM standards and a cetane testing engine. Alternatively, the analogous derived cetane number (DCN), obtained using an Ignition Quality Tester (IQT), is a direct measurement alternative to the CN that uses an empirical inverse relationship to the ignition delay found in the constant volume combustion chamber apparatus. DCN data points acquired using an IQT were utilized for model validation and expansion of the experimental database used in this study. The present work improves on an existing model by optimizing the model architecture along with the key learning variables of the ANN and by making the model more generalizable to a wider variety of fuel candidate types, specifically the class of furans and furan derivatives, by including specific molecules for the model to incorporate. The new molecules considered include tetrahydrofuran, 2-methylfuran, 2-methyltetrahydrofuran, 5,5 0 -(furan-2-ylmethylene)bis(2-methyl furan), 5,5 0 -((tetrahydrofuran-2-yl)methylene)bis(2-methyltetrahydrofuran), tris(5-methylfuran-2-yl) methane, and tris(5-methyltetrahydrofuran-2-yl)methane. Model architecture adjustments improved the overall root-mean-square error (RMSE) of the base database predictions by 5.54%. Additionally, through the targeted database expansion, it is shown that the predicted cetane number of the furanbased molecules improves on average by 49.21% (3.74 CN units) and significantly for a few of the individual molecules. This indicates that a selected subset of representative molecules can be used to extend the model's predictive accuracy to new molecular classes. The approach, bolstered by the improvements http://dx

show abstract

“…However, multiple linear regression models are shown to be outperformed by ANN's when predicting cetane number using fatty acid methyl esters [7]. This paper adopts feed-forward ANN's trained through backpropagation and QSPR input data, as they have recently shown to be more flexible for predicting CN across multiple molecular classes, in part due to the ANN's nonlinear architecture allowing complex analysis of multidimensional input and output vectors, and the range of physical and chemical attributes represented in the QSPR input data [8]. The goal of this paper is to improve the accuracy and robustness of predictive models on a diverse dataset of molecular compounds.…”

Section: Predicting the Cetane Numbermentioning

confidence: 99%

“…Experimental methods for determining CN with a CFR is outlined through American Society for Testing and Materials (ASTM) Standard D613 [1]. This method uses two reference compounds: n-hexadecane and isocetane (2,2,4,4,6,8,8-heptamethyl-nonane, or HMN), with CN values of 100 and 15 respectively. Using an equivalent blend of n-hexadecane and isocetane, the resultant volume fractions of each compound after a fuel in question is ignited is linearly related to the CN of the fuel.…”

Section: Cetane Numbermentioning

confidence: 99%

Application of a Rectified Linear Unit (ReLU) Based Artificial Neural Network to Cetane Number Predictions

Kessler

Dorian

Mack

2017

Volume 1: Large Bore Engines; Fuels; Advanced Combustion

View full text Add to dashboard Cite

Due to the high cost and time required to synthesize alternative fuel candidates for comprehensive testing, an Artificial Neural Network (ANN) can be used to predict fuel properties, allowing researchers to preemptively screen desirable fuel candidates. However, the accuracy of an ANN is limited by its error, measured by the root mean square error (RMSE), standard deviation, and r-squared values derived from a given input database. The present work improves upon an existing model for predicting the Cetane Number (CN) by changing the neuron activation function of the ANN from sigmoid to rectified linear unit (ReLU). This change to the ANN's architecture provides an increase in accuracy by reducing the RMSE by 21.4% (1.35 CN units), the average standard deviation across models by 28%, and increasing the r-squared value by 0.0492 across a wide range of molecular structures. Additionally, by using the ReLU activation function, input data is not required to be normalized, which reduces the likelihood of an inaccurate prediction on future fuel candidates which may have input parameters outside the range of normalization. Increasing the accuracy of the predictive ANN in this way will allow researchers to obtain more accurate fuel property predictions for promising fuel candidates.

show abstract

Artificial Neural Network for Predicting Cetane Number of Biofuel Candidates Based on Molecular Structure

Cited by 14 publications

References 0 publications

Screening Compounds for Fast Pyrolysis and Catalytic Biofuel Upgrading Using Artificial Neural Networks

Screening Compounds for Fast Pyrolysis and Catalytic Biofuel Upgrading Using Artificial Neural Networks

Predicting the Cetane Number of Furanic Biofuel Candidates Using an Improved Artificial Neural Network Based on Molecular Structure

Application of a Rectified Linear Unit (ReLU) Based Artificial Neural Network to Cetane Number Predictions

Contact Info

Product

Resources

About