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

Fermentation process soft measurement method based on online twin support vector regression machine

A technology of support vector regression and fermentation process, applied in program control, electrical testing/monitoring, testing/monitoring control systems, etc., and can solve problems such as the speed of training

Active Publication Date: 2020-03-24
JIANGNAN UNIV
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since the collection of new samples is often accumulated and new samples are often added, the traditional algorithm requires all the data to be retrained every time a new sample is added, which greatly affects the speed of training.

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 soft measurement method based on online twin support vector regression machine
  • Fermentation process soft measurement method based on online twin support vector regression machine
  • Fermentation process soft measurement method based on online twin support vector regression machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0100] A soft-sensing method for the fermentation process based on an online twin support vector regression machine proposed by the present invention is used to illustrate the effectiveness of the present invention in combination with a specific example of the fermentation process of penicillin. A total of 2000 groups of penicillin fermentation process data are taken from one production batch, each batch represents a complete fermentation process, forming a 2000×3-dimensional input sample matrix and a 2000×1-dimensional output sample matrix, of which 1900 groups The data is used as training data, and 100 sets of data are used as test data. The specific implementation method is as follows:

[0101] Initialize each parameter, set C 1 =C 2 = 2 10 , ε 1 =ε 2 =0.01, λ=10 -4 , through the online twin support vector regression algorithm, establish a penicillin concentration soft-sensing model, then store the determined parameters in the database, and directly substitute the test...

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 provides a fermentation process soft measurement method based on an online twin support vector regression machine, and belongs to the field of industrial fermentation production processsoft measurement modeling and application. The method comprises the following steps: firstly, normalizing auxiliary variables in a penicillin production process, and then carrying out soft measurementmodeling based on an online twin support vector regression machine on a nonlinear relationship between the auxiliary variables and the penicillin concentration of a product. Through performing on-line soft measurement on the penicillin concentration of a product difficult to measure through auxiliary variables easy to measure in the fermentation process, the method is very efficient for updatingthe model, and the method is provided for on-line real-time measurement of the penicillin concentration of the product in the penicillin fermentation production process. According to the soft measurement method, the real-time performance of online prediction can be improved, the model updating time is shortened, the prediction precision is high, and the method can be effectively used for guiding penicillin production.

Description

technical field [0001] The invention belongs to the field of soft-sensing modeling and application of industrial fermentation production process, and relates to a soft-sensing method for fermentation process based on an online twin support vector regression machine. Background technique [0002] Penicillin, as the first antibiotic purified by human beings for clinical use on a large scale, has been widely used in the field of medicine. The fermentation process is a typical biochemical reaction and a complex dynamic system with serious nonlinearity and time variation. In the actual production process, penicillin concentration is an important indicator in the fermentation process, but due to the limitation of detection means, the commonly used methods are offline measurement by wet chemical method, high pressure liquid chromatography and other methods. Compared with the online real-time measurement method, the off-line measurement of penicillin concentration generally takes m...

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
IPC IPC(8): G05B23/02
CPCG05B23/0224G05B2219/24065
Inventor 顾斌杰曹杰
Owner JIANGNAN UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com