Artificial Neural Network Based Group Contribution Method for Estimating Cetane and Octane Numbers of Hydrocarbons and Oxygenated Organic Compounds

William L. Kubic; Rhodri W. Jenkins; Cameron M. Moore; Troy A. Semelsberger; Andrew D. Sutton

doi:10.1021/acs.iecr.7b02753

Artificial Neural Network Based Group Contribution Method for Estimating Cetane and Octane Numbers of Hydrocarbons and Oxygenated Organic Compounds

William L. Kubic, Rhodri W. Jenkins, Cameron M. Moore, Troy A. Semelsberger, Andrew D. Sutton

Research output: Contribution to journal › Article › peer-review

59 Scopus citations

Abstract

Chemical pathways for converting biomass into fuels produce compounds for which key physical and chemical property data are unavailable. We developed an artificial neural network based group contribution method for estimating cetane and octane numbers that captures the complex dependence of fuel properties of pure compounds on chemical structure and is statistically superior to current methods.

Original language	English
Pages (from-to)	12236-12245
Number of pages	10
Journal	Industrial and Engineering Chemistry Research
Volume	56
Issue number	42
DOIs	https://doi.org/10.1021/acs.iecr.7b02753
State	Published - Oct 25 2017
Externally published	Yes

Funding

*E-mail: [email protected]. ORCID William L. Kubic Jr.: 0000-0002-5944-7064 Funding We are grateful to the Los Alamos National Laboratory LDRD program (LDRD20160095ER) for financial support. Los Alamos National Laboratory is operated by Los Alamos National Security, LLC, for the National Nuclear Security Administration of the U.S. Department of Energy under Contract DE-AC5206NA25396. Notes The authors declare no competing financial interest.

Access to Document

10.1021/acs.iecr.7b02753

Cite this

@article{62cb8c4be6f547e5b98e19533f63a8f9,

title = "Artificial Neural Network Based Group Contribution Method for Estimating Cetane and Octane Numbers of Hydrocarbons and Oxygenated Organic Compounds",

abstract = "Chemical pathways for converting biomass into fuels produce compounds for which key physical and chemical property data are unavailable. We developed an artificial neural network based group contribution method for estimating cetane and octane numbers that captures the complex dependence of fuel properties of pure compounds on chemical structure and is statistically superior to current methods.",

author = "Kubic, {William L.} and Jenkins, {Rhodri W.} and Moore, {Cameron M.} and Semelsberger, {Troy A.} and Sutton, {Andrew D.}",

note = "Publisher Copyright: {\textcopyright} 2017 American Chemical Society.",

year = "2017",

month = oct,

day = "25",

doi = "10.1021/acs.iecr.7b02753",

language = "English",

volume = "56",

pages = "12236--12245",

journal = "Industrial and Engineering Chemistry Research",

issn = "0888-5885",

publisher = "American Chemical Society",

number = "42",

}

Artificial Neural Network Based Group Contribution Method for Estimating Cetane and Octane Numbers of Hydrocarbons and Oxygenated Organic Compounds. / Kubic, William L.; Jenkins, Rhodri W.; Moore, Cameron M. et al.
In: Industrial and Engineering Chemistry Research, Vol. 56, No. 42, 25.10.2017, p. 12236-12245.

Research output: Contribution to journal › Article › peer-review

TY - JOUR

T1 - Artificial Neural Network Based Group Contribution Method for Estimating Cetane and Octane Numbers of Hydrocarbons and Oxygenated Organic Compounds

AU - Kubic, William L.

AU - Jenkins, Rhodri W.

AU - Moore, Cameron M.

AU - Semelsberger, Troy A.

AU - Sutton, Andrew D.

PY - 2017/10/25

Y1 - 2017/10/25

N2 - Chemical pathways for converting biomass into fuels produce compounds for which key physical and chemical property data are unavailable. We developed an artificial neural network based group contribution method for estimating cetane and octane numbers that captures the complex dependence of fuel properties of pure compounds on chemical structure and is statistically superior to current methods.

AB - Chemical pathways for converting biomass into fuels produce compounds for which key physical and chemical property data are unavailable. We developed an artificial neural network based group contribution method for estimating cetane and octane numbers that captures the complex dependence of fuel properties of pure compounds on chemical structure and is statistically superior to current methods.

UR - http://www.scopus.com/inward/record.url?scp=85032657020&partnerID=8YFLogxK

U2 - 10.1021/acs.iecr.7b02753

DO - 10.1021/acs.iecr.7b02753

M3 - Article

AN - SCOPUS:85032657020

SN - 0888-5885

VL - 56

SP - 12236

EP - 12245

JO - Industrial and Engineering Chemistry Research

JF - Industrial and Engineering Chemistry Research

IS - 42

ER -

Artificial Neural Network Based Group Contribution Method for Estimating Cetane and Octane Numbers of Hydrocarbons and Oxygenated Organic Compounds

Abstract

Funding

Access to Document

Other files and links

Fingerprint

Cite this