초록 ▼

A method for predicting properties of lubricant base oil blends, comprising the steps of generating an NMR spectrum, HPLC-UV spectrum, and FIMS spectrum of a sample of a blend of at least two lubricant base oils and determining at least one composite structural molecular parameter of the sample from

A method for predicting properties of lubricant base oil blends, comprising the steps of generating an NMR spectrum, HPLC-UV spectrum, and FIMS spectrum of a sample of a blend of at least two lubricant base oils and determining at least one composite structural molecular parameter of the sample from said spectrums. SIMDIST and HPO analyses of the sample are then generated in order to determine a composite boiling point distribution and molecular weight of the sample from such analysis. A composite structural molecular parameter is applied, and the composite boiling point distribution and the composite molecular weight to a trained neural network is trained to correlate with the composite structural molecular parameter composite boiling point distribution and the composite molecular weight so as to predict composite properties of the sample. The properties comprise Kinematic Viscosity at 40 C, Kinematic Viscosity at 100 C, Viscosity Index, Cloud Point, and Oxidation Performance.

대표청구항 ▼

What is claimed is: 1. A method for predicting properties of lubricant base oil blends, comprising the steps of: a. generating an NMR spectrum, HPLC-UV spectrum, and FIMS spectrum of a sample of a blend of at least two lubricant base oils; b. determining at least one composite structural molecular

What is claimed is: 1. A method for predicting properties of lubricant base oil blends, comprising the steps of: a. generating an NMR spectrum, HPLC-UV spectrum, and FIMS spectrum of a sample of a blend of at least two lubricant base oils; b. determining at least one composite structural molecular parameter of the sample from said spectrums; c. generating SIMDIST and HPO analyses of the sample; d. determining a composite boiling point distribution and molecular weight of the sample from such analysis; e. applying the at least one composite structural molecular parameter, the composite boiling point distribution and the composite molecular weight to a trained neural network trained to correlate with the at least one composite structural molecular parameter, the composite boiling point distribution and the composite molecular weight so as to predict composite properties of the sample, wherein the properties comprise Kinematic Viscosity at 40 C, Kinematic Viscosity at 100 C, Viscosity Index, Cloud Point, and Oxidation Performance. 2. The method of claim 1, further comprising steps of providing a neural network and training said neural network so as to provide said trained neural network. 3. The method according to claim 2, wherein said training step comprises the steps of: a. obtaining a set of lubricant base oil samples; b. generating NMR, HPLC-UV, and FIMS spectra and SIMDIST and VPO data for said set of hydrocarbon samples; c. measuring desired properties, comprising Kinematic Viscosity at 40 C, Kinematic Viscosity at 100 C, Viscosity Index, Cloud Point, and Oxidation Performance, of said set of the lubricant base oil samples so as to provide known properties; d. determining at least one structural molecular parameter, the boiling point distribution and the molecular weight of each of the lubricant base oil samples; e. for each known lubricant base oil property, building a matrix of at least one structural molecular parameter, the boiling point distribution and the molecular weight and known property for the set of lubricant base oil samples, thereby resulting in a model for each lubricant base oil property; and f. training the neural network with the at least one structural molecular parameter, the boiling point distribution and the molecular weight and each lubricant base oil property matrix to obtain a correlation between the at least one structural molecular parameter, the boiling point distribution and the molecular weight inputs and lubricant base oil properties outputs, so as to provide said trained neural network.