Quality variable prediction method and device under auxiliary training framework, terminal and medium

Abstract

The invention relates to a quality variable prediction method and device under a training-assisted framework, a terminal and a storage medium, and relates to the field of complex industrial process modeling and fault diagnosis. The method comprises the following steps: acquiring a to-be-tested data set, a labeled sample data set and an unlabeled sample data set; establishing an initial main learning model and an initial auxiliary learning model corresponding to the initial main learning model; training the initial main learning model and the initial auxiliary learning model; establishing a quality variable prediction model; and inputting the to-be-tested data set into the quality variable prediction model. In the prediction process, the quality of the quality variable prediction model is improved on the basis of selecting the label-free sample data set with high global information content through the pre-performed combined training of the label-free sample data set and the label sample data set, so that the quality of the quality variable prediction model is improved in a scene with a large number of label-free samples. The prediction of the quality variable has a stable and specific way, and the accuracy and efficiency of predicting the quality variable are improved.

Description

technical field [0001] The present application relates to the field of complex industrial process modeling and fault diagnosis, and in particular to a quality variable prediction method, device, terminal and storage medium under the training aid framework. Background technique [0002] Complex industrial processes widely exist in the fields of oil refining, chemical industry, etc., and have the characteristics of multivariable, strong coupling, strong nonlinearity, randomness, large time delay, output cannot be measured online, and working conditions vary greatly, so it is difficult to describe them with accurate mathematical models. [0003] In order to analyze the complex industrial process, it is necessary to determine the quality variables in the industrial process during the corresponding analysis of the complex industrial process. Usually, changes in quality variables can reflect whether the working conditions of complex industrial processes are normal or not. When me...

AI Technical Summary

Problems solved by technology

[0004] However, in related technologies, in the scenario of automatically measuring the quality variables of complex industrial processes, most sample sets cannot be accompanied by corresponding quality variable measurement results, that is, they are all unlabeled sample data sets

In this case, it is difficult to determine the specific prediction method for quality variables based on complex sample sets, resulting in low efficiency and accuracy of quality variable measurement

Images