Method and device for predicting viscosity of base oil

Abstract

The invention relates to a method and device for predicting the viscosity of base oil. The method comprises the following steps that: the near infrared spectrum of to-be-detected base oil is acquired;the near-infrared spectrum in a preset wave number range is inputted into a preset model, so that the viscosity mixing index of the to-be-detected base oil is obtained, wherein the preset model represents a corresponding relationship between the near-infrared spectrum of the base oil and the viscosity mixing index; and the viscosity of the base oil is calculated according to the viscosity mixingindex and a preset function. A linear correlation between the viscosity mixing index obtained after the conversion of the preset function and the near infrared spectrum is higher that a linear correlation between viscosity and the near infrared spectrum, and therefore, by means of the conversion between the viscosity and the viscosity mixing index by the preset function, the problems of the instability and inaccurate prediction of a model which is established on the basis of a multiple regression analysis method and is used for representing a corresponding relationship between a near infraredspectrum and viscosity due to excessive nonlinear information between the near infrared spectrum and the viscosity property of base oil can be solved.

Description

technical field [0001] The present disclosure relates to the field of oil analysis, in particular, to a method and device for predicting the viscosity of base oil. Background technique [0002] In recent years, with the rapid development of the automobile manufacturing industry and the machinery industry, as well as the increasingly stringent requirements for environmental protection and energy saving, the quality requirements for lubricating oil products have become more stringent, which has directly led to an increase in the demand for high-quality lubricating oil base oils. At present, the production process of high-quality base oil is mainly the full hydrogenation process. The processing process involves a variety of processes and various types of materials and products. A change in one link may affect the production of the entire base oil. Online real-time tracking and monitoring of material and product indicators can quickly obtain relevant information, provide timely ...

AI Technical Summary

Problems solved by technology

[0005] The purpose of this disclosure is to provide a method and device for predicting the viscosity of base oil to solve the problem of excessive nonlinear information between the near-infrared spectrum and the viscosity properties of the base oil, which leads to the relationship between the characteristic near-infrared spectrum and the viscosity established based on the multiple regression analysis method. The model of the corresponding relationship between them is unstable and the prediction is inaccurate.

Images