Fuzzy Rule-Building Expert System Classification of Fuel Using Solid-Phase Microextraction Two-Way Gas Chromatography Differential Mobility Spectrometric Data

Abstract

Gas chromatography/differential mobility spectrometry (GC/DMS) has been investigated for characterization of fuels. Neat fuel samples were sampled using solid-phase microextraction (SPME) and analyzed using a micromachined differential mobility spectrometer with a photoionization source interfaced to a gas chromatograph. The coupling of DMS to GC offers an additional order of information in that two-way data are obtained with respect to compensation voltages and retention time. A fuzzy rule-building expert system (FuRES) was used as a multivariate classifier for the two-way gas chromatograms of fuels, including rocket (RP-1, RG-1), diesel, and jet (JP-4, JP-5, JP-7, JP-TS, JetA-3639, Jet A-3688, Jet A-3690, Jet A-3694, and Jet A-generic) fuels. The GC-DMS with SPME was able to produce characteristic profiles of the fuels and a classification rate of 95 +/- 0.3% obtained with a FuRES model. The classification system also had perfect classification for each fuel sample when applied one month later.

Transportation mode-based segmentation and classification of movement trajectories

“…In this paper, an expert system approach is chosen because of its maturity and because it has been used successfully at solving other problems (Holzmann et al, 1999;Rearden et al, 2007;Wentz et al, 2008). …”

Fire investigation and ignitable liquid residue analysis—A review: 2001–2007

“…Two-dimensional GC was used in conjunction with PCA to classify samples of jet fuel [305]. Samples of diesel fuel and jet fuel were classified using a differential mobility spectrometer (DMS) with a photoionization source interfaced to a gas chromatograph [306]. Principal component analysis was used to distinguish between samples of evaporated kerosene and diesel fuel [307].…”

Supervised semi-automated data analysis software for gas chromatography / differential mobility spectrometry (GC/DMS) metabolomics applications

“…But generally in these data sets, we seek to determine relatively simple information from the data stream. Occasionally, we also may be interested in detecting groups of several chemicals from a complex mixtures, but still only identifying a handful of major chemical features which is a small finite number (Camara et al 2013; Lu and Harrington 2007; Rearden et al 2007). In some examples, signal alignment has been used (Krebs et al 2006a), along with feature selection procedures (Fong et al 2011; Zhao et al 2009) to assist in chemical identification.…”

“…Frequently these local optima are not general enough to be applied to data not used in training the model. A fuzzy rule building expert system (Rearden et al 2007) has also been demonstrated for synthetic complex mixtures, such as JP-8 jet fuel, and may also be appropriate for metabolomic data sets. Linear discriminant analysis (Covington et al 2013; Rutolo et al 2014) and Fisher discriminant analysis (Arasaradnam et al 2014b) have been used as classification methods for biological data as well.…”