Fermentation process stage division method based on scoring matrices

A scoring matrix and fermentation process technology, applied in the direction of program control, electrical program control, comprehensive factory control, etc., can solve the problems of "increasing false positives and false negatives, misclassification" and cannot reflect the characteristics of the transition stage well, to achieve The effect of improving accuracy

Active Publication Date: 2019-02-05
BEIJING UNIV OF TECH
View PDF6 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the traditional PLS-based quality prediction method is to establish a fixed model based on historical data. Considering the multi-stage characteristics of the batch process, it is obviously incomplete to establish a single model for the entire production process. Therefore, many scholars have conducted research on stage division.
Lu et al. proposed a K-means-based sub-period division method for the intermittent process, but this method is a hard division method, which cannot reflect the characteristics of the transition stage well, and may lead to the phenomenon of "misclassification", increasing false positives and missing Probability of reporting; Ge et al. proposed a multi-stage process quality variable sof

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 stage division method based on scoring matrices
  • Fermentation process stage division method based on scoring matrices
  • Fermentation process stage division method based on scoring matrices

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] Penicillin (Penicillin, or transliteration Penicillin) is a relatively common clinical antibacterial drug in life, and its production and preparation process is a typical batch process. The Pensim simulation platform developed by Professor Cinar of Illinois State Institute of Technology in the United States can analyze the microbial concentration and CO in the production process of penicillin under different operating conditions. 2 Concentration, pH value, penicillin concentration, oxygen concentration and heat generated etc. are simulated. The duration of each batch of penicillin fermentation was 400h, and the sampling interval was 1 hour. Select 10 main process variables as shown in Table 1, and select a quality variable (product concentration). In this paper, 60 batches of penicillin fermentation process are selected for training and modeling, and 20 batches are used for prediction.

[0026] Table 1 Penicillin Fermentation Process Variables

[0027] Table 1Process...

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 stage division method based on scoring matrices, and relates to the technical field of data-driven multivariate statistical process monitoring (MSPM). The invention discloses a method of stage division based on an extended scoring matrix method. For the multi-stage characteristics of batch processes, currently existing stage division methods rarely consider influences of quality variables on stage division. Firstly, an extended scoring matrix of each time slice is constructed, the extended scoring matrix is utilized for capturing influences of quality variable information on stage division, then similarity of two adjacent extended scoring matrices is calculated, an operation process is divided into different operation stages according to the similarity, and an MPLS quality prediction model is respectively established for each stage; and finally experiment verification of the algorithm is carried out on a penicillin fermentation simulationplatform and Escherichia coli production data, and an experiment result proves feasibility and effectiveness of the method.

Description

technical field [0001] The present invention relates to the technical field of data-driven multivariate statistical process monitoring (Multivariate Statistical Process Monitoring, MSPM), in particular to a batch process stage division method based on an extended score matrix proposed for the multi-stage characteristics of the batch process. The present invention uses the extended score matrix to capture the influence of quality variable information on the division stage, then calculates the similarity between two adjacent extended score matrices, and divides the operation process into different operation stages according to the similarity. Background technique [0002] With the development of industrial technology and the rapid change of market demand, the batch process has become an important production method and is widely used in chemistry, biomedicine and other aspects. However, in certain production processes such as fermentation, its quality variables are difficult to...

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): G05B19/418
CPCG05B19/41875G05B2219/31457Y02P90/02
Inventor 王普曹彩霞高学金
Owner BEIJING UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products