Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Multi-kernel support vector machine based dynamic fermentation process predicating method

A technology of support vector machine and fermentation process, which is applied in the field of support vector machine to establish a fermentation process model to predict biochemical parameters, and can solve the problem that the model cannot adapt to the new environment.

Active Publication Date: 2014-03-05
BEIJING UNIV OF TECH
View PDF2 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The dynamics of the fermentation process model is realized by establishing a dynamic sample set of the fermentation process, which overcomes the problem that the original model cannot adapt to the new environment once the production conditions are changed due to the huge differences between batches of the fermentation process; at the same time, through Construct a multi-core function to adapt to the multi-stage characteristics of the fermentation process, saving the trouble of modeling the fermentation process in stages

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
  • Multi-kernel support vector machine based dynamic fermentation process predicating method
  • Multi-kernel support vector machine based dynamic fermentation process predicating method
  • Multi-kernel support vector machine based dynamic fermentation process predicating method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] Provide following embodiment in conjunction with content of the present invention:

[0049] The fermentation process of gene recombinant Escherichia coli to produce interleukin-2 is a typical multi-stage process, which mainly includes the stage of culture without feed, the stage of rapid growth of strain with feed, and the stage of inducing product synthesis. The whole fermentation cycle lasts about 19-20 hours, the sampling interval of the fermentation process is 0.5h, and the initial inoculation volume is 700ml.

[0050] The experimental data used in this experiment was obtained from a biopharmaceutical company in Yizhuang Economic Development Zone, Beijing. Using fed-batch fermentation, the actual fermentation process data of 5 batches of recombinant Escherichia coli exogenous protein expression to prepare interleukin-2 were obtained.

[0051] The specific implementation steps of the dynamic prediction method of the fermentation process product interleukin-2 realize...

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 belongs to the field of biological fermentation as well as the field of information science, relates to a multi-kernel support vector machine based dynamic fermentation process predicating method, in particular to a method for applying an improved support vector machine for establishing a fermentation process model to predict biological state parameters in the fermentation process. The method specifically includes: searching data most similar to data in a current time window from a historical batch database, combining the data to form a similar training sample set, and utilizing the established similar training sample set and applying a support vector machine algorithm to establish a local training model at current time in a current batch. Meanwhile, a multi-kernel function is constructed to process samples in different stages so as to establish local models. By the method, the biological state parameters of the fermentation process are measured timely and accurately, the trouble of staging the fermentation process prior to modeling is omitted, and the method has the advantages of small sample demand quantity, accuracy in prediction and short time, and is of important significance to control of the fermentation process and optimal control.

Description

technical field [0001] The invention not only belongs to the field of biological fermentation, but also belongs to the field of information science, and specifically relates to a method for establishing a fermentation process model and predicting biochemical parameters by using an improved support vector machine in the fermentation process. Background technique [0002] Fermentation engineering refers to a new technology that uses modern engineering technology to use some specific functions of microorganisms to produce useful products for human beings, or directly applies microorganisms to industrial production processes. It is an important part of biotechnology. An important link in the industrialization of biotechnology. Modern fermentation technologies are increasingly becoming an important part of the global economy. The National Development and Reform Commission and the Ministry of Industry and Information Technology issued the "Food Industry "Twelfth Five-Year" Develo...

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): G06F17/50
Inventor 高学金耿凌霄王普李亚芬
Owner BEIJING UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products