Soft measurement modeling method based on semi-supervised ensemble learning

Abstract

The invention discloses a soft measurement modeling method based on semi-supervised ensemble learning, belongs to the field of modeling and soft measurement in a complex industrial process, and is used for a chemical process with a small quantity of label samples. The method is an online prediction strategy based on semi-supervision. A Bagging algorithm is adopted to divide a no-label sample set into three sub sample sets, and the label sample is adopted to train three regression models; then, on the basis of a confidence coefficient index, the corresponding index value of the no-label sampleis calculated, the no-label sample which meets a confidence coefficient requirement is selected for carrying out labeling, and the labeled sample is added into the corresponding label sub sample set;and finally, a Gaussian process regression model is independently established for three enlarged label datasets, and a weighting method is adopted for carrying out result fusion. By use of the method,the no-label sample information in the chemical process can be effectively utilized to accurately predict a key variable so as to improve product quality and lower production cost.

Description

Technical field [0001] The invention relates to a soft measurement modeling method based on semi-supervised integrated learning, which belongs to the field of complex industrial process modeling and soft measurement. Background technique [0002] Some important quality variables in industrial processes such as chemical industry, metallurgy and fermentation are often unable to be measured by online instruments, and there is a serious lag in the way of offline analysis in the laboratory. The data-based soft-sensing modeling method does not require in-depth knowledge of the process mechanism, and has the advantages of low maintenance cost and low measurement delay. In recent years, it has been widely used in industrial process modeling. The traditional soft-sensing modeling method only considers the information of labeled samples in the industrial process and discards a large number of unlabeled samples. However, in the actual process, the number of labeled samples is far less than ...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem that the acquisition frequency of dominant variables is far lower than that of auxiliary variables in the actual industrial process, the soft sensor modeling method based on semi-supervised learning has low model prediction performance and inaccurate prediction of key variables. The invention provides a soft sensor modeling method based on semi-supervised integrated learning. The technical solution is as follows:

Images