Soft measuring method of industrial process under condition of small sample

Abstract

A soft measurement method of industrial course under small sample condition includes using support vector computer to structure I / O mapping relation, measurable variables, object control input and object measurable output variable and utilizing them as input variables of soft measurement model, using optimum estimation of estimated variable as output, using genetic algorithm to confirm optimum parameter of support vector computer and applying Bayes rule to speed up convergence velocity of genetic algorithm.

Description

technical field [0001] The invention relates to the technical field of soft sensing in the field of industrial process control, in particular to a soft sensing method under the condition of a small sample in an industrial production process. Background technique [0002] In the modern process industry, a large number of key parameters such as process status and product quality lack online direct measurement methods. This has become a bottleneck restricting the further improvement of production safety, product quality, output and production efficiency. Soft sensing technology is an effective way to solve such problems. [0003] Soft sensor technology is an important tool in the current control field, and its core technology is to establish a soft sensor model. At present, soft sensor modeling methods mainly include mechanism modeling, multivariate statistical methods, Kalman filter methods, artificial neural networks and so on. These methods have achieved certain results i...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to aim at the above deficiency of existing soft sensor method, provide a kind of soft sensor method under the small sample condition of industrial production process, provide the selection method of support vector machine optimal model, make it overcome support vector machine The problem of difficult model determination in the application has established a reliable foundation and basis for support vector machine modeling

Images