An adaptive near-infrared rapid prediction method for crude oil properties

Abstract

The invention discloses an adaptive near-infrared rapid prediction method for crude oil properties. The method for constructing the model used for crude oil property prediction comprises: (1) measure the property data of crude oil sample; (2) measure the near-infrared spectrogram of described crude oil sample; (3) to the near-infrared spectrogram that step (2) obtains Carry out pretreatment, establish the initial training set; (4) adopt principal component analysis (PCA) in conjunction with the method of Hotelling T2 statistics to eliminate the abnormal sample points in the initial training set, obtain the final training set; (5) the sample obtained in step (4) Carry out principal component analysis, and save the load vector whose eigenvalue contribution rate is greater than 95% and record it as P pca ; (6) use P pca After reducing the dimensionality of the near-infrared spectrum of the test sample, select the local training set by the similarity index (SI); (7) determine one or more wavenumber segments according to the local training set, and use the partial least square method (PLS) to establish the crude oil properties local model of .

Description

technical field [0001] The invention relates to an adaptive near-infrared rapid prediction method of crude oil properties. Background technique [0002] With the rapid development of modern industry, petroleum, as a national material, plays a vital role in the national economy. Crude oil is the most important raw material for refining and chemical enterprises. The demand for crude oil has increased sharply, the import volume has expanded, and the price has remained high and fluctuated frequently. According to the "BP World Energy Statistical Yearbook 2016" report, in 2015, China's net oil imports increased by 770,000 barrels per day, and China once again became the world's largest oil importer. There are many types of imported crude oil, many of which are so-called "Opportunity oil", they either have a large specific gravity, or have a high acid content, or have a lot of impurities. These have brought tremendous pressure to refining and chemical enterprises. Timely access...

AI Technical Summary

Problems solved by technology

For the process industry, the continuity of production often requires the model to be able to track the on-site working conditions in real time; and when the model deviates greatly from the current working conditions and the prediction accuracy cannot meet the needs of online detection, the model can be updated in a timely and effective manner

Images