A method for predicting butane concentration in debutanizer bottoms using a model based on a double-optimized semi-supervised regression algorithm

Abstract

The invention discloses a method for predicting the concentration of butane at the bottom of a debutanizer tower based on a model of a double-optimized semi-supervised regression algorithm, which belongs to the field of semi-supervised regression. Through a double-optimization strategy, the center of the dense area of ​​labeled samples is obtained, and the unlabeled samples are screened according to the similarity between the unlabeled samples and the center of the dense area, and the labeled samples are screened according to the similarity between the labeled samples; then use Gaussian The process regression method establishes an auxiliary learner for the selected labeled samples to predict the label for the selected unlabeled samples; finally, these pseudo-labeled samples are used to improve the prediction effect of the main learner, which solves the problem of inability to learn when there are few labeled samples. Guaranteed the quality of unlabeled samples so that accurate predictions cannot be achieved, and achieved the effect of using very few labeled samples to achieve accurate predictions.

Description

technical field [0001] The invention relates to a method for predicting the concentration of butane at the bottom of a debutanizer tower based on a model of a double-optimized semi-supervised regression algorithm, belonging to the field of semi-supervised regression. Background technique [0002] Some important quality variables in industrial processes such as chemical industry, metallurgy, and fermentation cannot be measured by online instruments, and there is a serious lag in offline analysis in the laboratory. Therefore, it is necessary to use some sample data that can be directly measured. important quality variables to predict. [0003] With the development of science and technology, especially the development of industrial big data technology, unlabeled samples are becoming more and more easy to obtain in large quantities, while the cost of obtaining labeled samples is still high, resulting in few labeled samples in some industrial processes. In this case, it is diffi...

AI Technical Summary

Problems solved by technology

However, when there are few labeled samples, these methods cannot guarantee the quality of unlabeled samples and cannot achieve accurate predictions.

Images