Hydrocracking product yield prediction method, model building method and storage equipment

Abstract

The invention discloses a hydrocracking product yield prediction method, a model building method and a storage device, wherein the model building method includes the steps of: obtaining working condition information and property information data respectively; Make corrections; expand product property information data; build primary modeling data by establishing the corresponding relationship between working condition information and property information data; perform data screening on primary modeling data to obtain modeling data; classify modeling data Training, obtaining the key parameter items of the product yield; generating a product yield prediction model according to the key parameter items of the product yield. Through the present invention, there is better correspondence between the working condition information and the property information data, and the selection of key parameter items is more efficient, therefore, the prediction of the product yield prediction model thus established can be made accurate The rate is more accurate.

Description

technical field [0001] The invention relates to the field of petrochemical industry, in particular to a hydrocracking product yield prediction method, model building method and storage equipment. Background technique [0002] Petroleum is an important energy and high-quality chemical raw material, and an important strategic material related to the national economy and people's livelihood. The petroleum industry is an important basic industry of our national economy. Since the reform and opening up, my country's economy has developed rapidly, and the demand for energy is increasing. [0003] With the development of information technology, the degree of informatization of petroleum refining and chemical production equipment is getting higher and higher, and a large amount of production data has been accumulated accordingly; behind these data are hidden a large number of important production information, and big data technology is exactly the mining and utilization the most ef...

AI Technical Summary

Problems solved by technology

[0006] Since the validity of the values ​​used for the parameter value input of the working conditions has been unstable, it is difficult to build an accurate prediction model to predict the yield of the product

Images