Method for quantitatively analyzing crude oil by Raman spectroscopy based on partial least square method

Abstract

The invention discloses a method for quantitatively analyzing crude oil by Raman spectroscopy based on a partial least square method. The method comprises the following steps: S1, obtaining a Raman spectrogram of a to-be-detected substance, and preprocessing the obtained Raman spectrogram data by adopting a Raman spectroscopy analysis technology; S2, performing feature extraction on the preprocessed data; S3, selecting data after feature extraction based on a partial least squares algorithm to establish a mathematical model; S4, completing qualitative analysis judgment on whether the to-be-detected substance contains crude oil or not; and S5, completing quantitative calculation of the crude oil content in the to-be-detected substance through the established mathematical model. According tothe method, the steps of preprocessing Raman spectrum data of a to-be-detected substance and extracting features are introduced, meanwhile, a corresponding mathematical algorithm is adopted to improve the processing precision of the data, then a mathematical model is established based on a partial least square analysis method, qualitative analysis and quantitative calculation of the crude oil inthe drilling fluid mixture are completed according to the mathematical model, and the final result shows relatively ideal calculation precision.

Description

technical field [0001] The invention relates to the technical field of quantitative analysis methods for material components and content, in particular to a method for quantitative analysis of crude oil by Raman spectroscopy based on partial least squares method. Background technique [0002] In recent years, oil exploration has become more and more difficult. In order to reduce the waste of resources and the consumption of input costs, the detection technology of formation oil and gas has been continuously updated and developed. The detection-while-drilling technology is widely used in exploration work due to its advantages of obtaining detection results in real time and quickly. This detection technology not only shortens the detection time, but also reduces the input cost. However, this underground detection method is more difficult than the traditional ground detection. How to ensure the accuracy of the detection-while-drilling technology has become one of the current t...

AI Technical Summary

Problems solved by technology

[0003] In view of the fact that the current crude oil drilling fluid mixture has a darker color and can not obtain more accurate analysis results when directly analyzing the Raman spectrum, the present invention proposes a method for quantitative analysis of crude oil based on the partial least squares Raman spectrum. In order to improve the above problems, through Raman spectral analysis technology, before the qualitative analysis and quantitative calculation, the Raman spectral data used are preprocessed and feature extracted, so as to obtain a relatively more true reflection of the substance. The spectrogram data of the information provides a guarantee for the implementation of the next algorithm

Images