A real-time learning soft-sensing modeling method for a butanizer based on a Gaussian mixture model

Abstract

The invention discloses a real-time learning debutanizer soft measurement modeling method on the basis of Gaussian mixture models (GMM). The real-time learning debutanizer soft measurement modeling method includes training process Gaussian mixture models to acquire various Gaussian component parameters and building corresponding sub-models; computing posterior probabilities of to-be-predicted samples and local Mahalanobis distances of various Gaussian components by a Bayesian process so as to obtain weighted sample similarity definition indexes; reasonably selecting similar samples by the aid of the new similarity indexes for local modeling. The posterior probabilities indicate whether the to-be-predicted samples belong to the various Gaussian components or not. The real-time learning debutanizer soft measurement modeling method has the advantages that problems of process non-Gaussianity and nonlinearity can be effectively solved, characteristics of the to-be-predicted samples can be sufficiently extracted, the similar samples can be reasonably selected for real-time learning modeling, and accordingly the real-time learning debutanizer soft measurement modeling method is favorable for improving the model prediction precision.

Description

technical field [0001] The invention belongs to the field of industrial process soft sensor modeling, in particular to a Gaussian mixture model-based real-time learning debutanizer soft sensor modeling method. Background technique [0002] With the continuous improvement of quality control and reliability requirements in modern industrial processes, real-time monitoring and control of quality-related process variables has become more important. However, in complex industrial production processes, there are many variables that are difficult to measure directly due to the limitation of technology and conditions. Although these variables can be measured with an online analyzer, the online analyzer cannot meet the needs of real-time control due to its high cost, difficult maintenance, and large measurement lag. In order to solve the above problems, soft sensor technology emerged as a new technology with broad development prospects. The core of the soft-sensing technology is to...

AI Technical Summary

Problems solved by technology

The traditional similarity criterion is a global similarity index, which only considers the distance information between samples, and does not fully consider the characteristics of new samples. At the same time, the traditional similarity criterion is suitable for Gaussian processes. In fact, complex and changeable Practical industrial processes often exhibit non-Gaussian behavior

These defects will affect the selection of similar samples, which will lead to a decrease in the prediction accuracy of the model

Images