Unlock instant, AI-driven research and patent intelligence for your innovation.

Fermentation process quality variable prediction based on maximum quadratic mutual information criterion regression

A quality variable, fermentation process technology, applied in forecasting, instrumentation, data processing applications, etc., can solve problems such as difficulty in establishing mathematical models, and achieve the effect of improving forecasting accuracy

Active Publication Date: 2020-03-06
BEIJING UNIV OF TECH
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The kinetic model of the fermentation process is highly nonlinear, so it is difficult to establish an accurate mathematical model

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Fermentation process quality variable prediction based on maximum quadratic mutual information criterion regression
  • Fermentation process quality variable prediction based on maximum quadratic mutual information criterion regression
  • Fermentation process quality variable prediction based on maximum quadratic mutual information criterion regression

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] In the field of modern biopharmaceuticals, the target gene is usually introduced into the bacteria to form a genetically engineered bacteria, which is expressed through cultivation and fermentation to produce the desired pharmaceutical protein. Escherichia coli is one of the commonly used genetically engineered bacteria. In the actual drug preparation process, Escherichia coli is often genetically modified and fermented to produce recombinant human interleukin-2 (IL-2). IL-2 is an important pharmaceutical protein, widely used in the treatment of malignant tumors. The fermentation process of Escherichia coli is a typical batch production process, including a series of complex biochemical reactions, and the data are highly nonlinear and Gaussian. The verification of actual production data highlights the research significance and effect of the present invention, so the present invention takes the production data of actually preparing IL-2 as the verification object. In a...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a fermentation process quality variable prediction method based on maximum quadratic mutual information criterion regression. In actual production, key quality variables reflecting the quality of a final product are generally difficult to measure on line. At present, an off-line measurement method which is commonly adopted can cause the problems of lag, insufficient precision and the like, and the consistency of yield and quality is influenced. Aiming at the characteristics of strong nonlinearity and non-Gaussian property of fermentation production data, the invention provides a regression method based on a maximum quadratic mutual information criterion to realize prediction of key quality variables in a fermentation process. Compared with MPLS and other regressionmethods based on second-order statistics, regression between the process variable and the key quality variable is carried out by using the high-order statistics, the nonlinear dependence relationshipbetween the process variable and the key quality variable is mined, and it is unnecessary to assume that data obeys Gaussian distribution. Related experiments show that compared with an MPLS method, the prediction effect of the method is better.

Description

technical field [0001] The invention relates to the field of data-driven regression prediction methods, in particular to a regression method based on the maximum quadratic mutual information criterion for fermentation production data. Background technique [0002] Batch process is an important mode of production in modern industrial production. Batch processes widely exist in the fields of biopharmaceuticals, food processing, chemical industry, semiconductor production, etc., and the biggest features are small batches, high value-added, multiple specifications and high quality. The fermentation process is a typical batch production process. The industrial scale of my country's bio-fermentation industry continues to expand, and it has become an important part of my country's strategic emerging industries. In recent years, enhancing the independent innovation capability of the bio-fermentation industry and promoting high-tech transformation of traditional manufacturing techn...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/04G06Q10/06
CPCG06Q10/04G06Q10/06395Y02P90/30
Inventor 王普李征高学金高慧慧
Owner BEIJING UNIV OF TECH