Kernel learning monitoring method for penicillin production process under unequal-length batch conditions

A production process, penicillin technology, applied in the direction of electrical program control, comprehensive factory control, etc., can solve the problems of inconsistent data lengths, limit the scope of application of traditional methods, etc., to improve monitoring effects, reduce complexity, and strengthen modeling capabilities. Effect

Inactive Publication Date: 2014-07-02
ZHEJIANG UNIV
View PDF2 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since the penicillin production process often has very strong nonlinear characteristics, and the length of each batch of data is not exactly the same, this greatly limits the scope of application of the traditional method

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
  • Kernel learning monitoring method for penicillin production process under unequal-length batch conditions
  • Kernel learning monitoring method for penicillin production process under unequal-length batch conditions
  • Kernel learning monitoring method for penicillin production process under unequal-length batch conditions

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] The penicillin production process nuclear learning monitoring method under a kind of unequal length batch condition of the present invention comprises the following steps:

[0017] Step 1: Use the distributed control system to collect the data of the penicillin production process to form a training sample set for modeling: i=1,2,…,I, among them, R is a set of real numbers, which means X i Obey K i ×J two-dimensional data distribution, I is the batch information of the data, K i is the number of sampling data points of the i-th batch, J is the number of variables, and these data are stored in the historical database;

[0018] Step 2: Arrange each data matrix along the time point direction to obtain a new data matrix, and preprocess and normalize it, that is, make the mean value of each process variable zero and the variance 1, and obtain a new data matrix The data matrix set of is

[0019] Arrange the matrix composed of each batch of data along the direction of ti...

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 kernel learning monitoring method for the penicillin production process under unequal-length batch conditions. The kernel learning monitoring method is used for product quality on-line monitoring under the unequal-length batch conditions in the penicillin production process. A kernel learning method based on support vector data description is utilized for building an effective nonlinear monitoring model, the problem caused by unequal-length batches in the penicillin production process is solved, and on-line monitoring efficiency and performance of the penicillin production process are improved, so that the penicillin production process is more reliable, and penicillin quality is more stable.

Description

technical field [0001] The invention belongs to the field of penicillin production process monitoring, and in particular relates to a penicillin production process nuclear learning monitoring method under the condition of unequal length batches. Background technique [0002] The penicillin production process has extremely high requirements on product quality. How to effectively prevent the process from producing inferior or unqualified products is an urgent problem to be solved. On the other hand, if the process is not well monitored, accidents may occur, which may affect the quality of the product in the light, or cause loss of life and property in the severe case. In addition, the results obtained from monitoring the penicillin production process can in turn guide the improvement of the production process and production process. As a typical batch production process, the traditional penicillin process monitoring method usually adopts multi-dimensional multivariate statist...

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): G05B19/418
Inventor 葛志强
Owner ZHEJIANG UNIV
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap