Ravilya Z. Safieva

Gasoline classification using near infrared (NIR) spectroscopy data: Comparison of multivariate techniques

Near infrared (NIR) spectroscopy is a non-destructive (vibrational spectroscopy based) measurement technique for many multicomponent chemical systems, including products of petroleum (crude oil) refining and petrochemicals, food products (tea, fruits, e.g., apples, milk, wine, spirits, meat, bread, cheese, etc.), pharmaceuticals (drugs, tablets, bioreactor monitoring, etc.), and combustion products. In this paper we have compared the abilities of nine different multivariate classification methods: linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), regularized discriminant analysis (RDA), soft independent modeling of class analogy (SIMCA), partial least squares (PLS) classification, K-nearest neighbor (KNN), support vector machines (SVM), probabilistic neural network (PNN), and multilayer perceptron (ANN-MLP) - for gasoline classification. Three sets of near infrared (NIR) spectra (450, 415, and 345 spectra) were used for classification of gasolines into 3, 6, and 3 classes, respectively, according to their source (refinery or process) and type. The 14,000-8000 cm(-1) NIR spectral region was chosen. In all cases NIR spectroscopy was found to be effective for gasoline classification purposes, when compared with nuclear magnetic resonance (NMR) spectroscopy or gas chromatography (GC). KNN, SVM, and PNN techniques for classification were found to be among the most effective ones. Artificial neural network (ANN-MLP) approach based on principal component analysis (PCA), which was believed to be efficient, has shown much worse results. We hope that the results obtained in this study will help both further chemometric (multivariate data analysis) investigations and investigations in the sphere of applied vibrational (infrared/IR, near-IR, and Raman) spectroscopy of sophisticated multicomponent systems.

Biodiesel classification by base stock type (vegetable oil) using near infrared spectroscopy data

The use of biofuels, such as bioethanol or biodiesel, has rapidly increased in the last few years. Near infrared (near-IR, NIR, or NIRS) spectroscopy (>4000cm(-1)) has previously been reported as a cheap and fast alternative for biodiesel quality control when compared with infrared, Raman, or nuclear magnetic resonance (NMR) methods; in addition, NIR can easily be done in real time (on-line). In this proof-of-principle paper, we attempt to find a correlation between the near infrared spectrum of a biodiesel sample and its base stock. This correlation is used to classify fuel samples into 10 groups according to their origin (vegetable oil): sunflower, coconut, palm, soy/soya, cottonseed, castor, Jatropha, etc. Principal component analysis (PCA) is used for outlier detection and dimensionality reduction of the NIR spectral data. Four different multivariate data analysis techniques are used to solve the classification problem, including regularized discriminant analysis (RDA), partial least squares method/projection on latent structures (PLS-DA), K-nearest neighbors (KNN) technique, and support vector machines (SVMs). Classifying biodiesel by feedstock (base stock) type can be successfully solved with modern machine learning techniques and NIR spectroscopy data. KNN and SVM methods were found to be highly effective for biodiesel classification by feedstock oil type. A classification error (E) of less than 5% can be reached using an SVM-based approach. If computational time is an important consideration, the KNN technique (E=6.2%) can be recommended for practical (industrial) implementation. Comparison with gasoline and motor oil data shows the relative simplicity of this methodology for biodiesel classification.

Capabilities of near infrared spectroscopy for the determination of petroleum macromolecule content in aromatic solutions

In this paper the application of near infrared (NIR) spectroscopy for the determination of petroleum macromolecules content in model systems is reported. Eighty (80) solutions of three main types of oil macromolecules (asphaltenes, resins, and paraffins) in toluene were studied. NIR spectra within the range 8,000–14,000 cm−1 were used to construct calibration models using the partial least squares method. The low prediction error of the models (0.43, 0.79 and 0.39% w/w for asphaltenes, resins and paraffins, respectively) indicate that NIR spectroscopy can be applied to analyse the petroleum macromolecule content in natural systems (crude oil and its refined products).

Universal technique for optimization of neural network training parameters: gasoline near infrared data example

The universal technique of finding optimum training parameters for multi-layer perceptron—such as percentage of samples in a cross-validation set and quantities of training iterations with various initial values—is offered. This technique is aimed at the searching of optimum values of two complex factors depending on accuracy and convergence of a network, and also on the time of its training. Their conventional names are “cross-validation coefficient” and “training iteration coefficient”. Near infrared spectroscopy data for gasoline samples are used to evaluate the efficiency of the method.

The influence of the internal structure and dispersity to structural–mechanical properties of oil systems

Abstract Some oils and oil products are dispersed systems with composite internal organization. The dynamical model of dispersed particle, named complex structural unit (CSU), with complicated internal structure is suggested. A nucleus surrounded by solvate shell contains high-molecular mass components of different natures. Sizes of nuclei and solvate shells change in accordance with the magnitude of external influence. An optimal correlation between parameters of CSU and the value of external factor can be fixed for every technological process. The results of determination of the dispersity degree in oil systems are presented. Connection of nonmonotonous extremal dependence macroscopic parameters (viscosity, stability, etc.) and microscopic ones (particle sizes) with external influence value changing is shown. These regularities are basic for the intensification of technological processes. Technology is tested in practice with good results. For managing structural–mechanical properties, the addition of heavy residue, containing significant amount of resin–asphaltene substances (RAS), has been chosen together with thermal treatment and regulation of speed of cooling. Speed of cooling determines sizes and number of interacting particles. Connections between particles could be realized through the solvate shells formed from RAS or directly with each other. Finally, the structure of coalescence or condensation type is formed. These kinds of structures differ in their structural–mechanical properties. Such oil compositions are basis for specific products, which are used in mining industry for dust depressing and preventing adherence of granular materials to the walls of transportation equipment. The optimal combination of influencing of external factors gives an opportunity to include bigger amount of heavy residues for decreasing the cost.