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

Sparseness data process modeling approach

A technology of sparse data and modeling methods, applied in neural learning methods, simulators, biological neural network models, etc.

Inactive Publication Date: 2008-02-06
NORTHEASTERN UNIV
View PDF0 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a modeling method based on process neural network to solve the modeling problem of sparse data process and provide an effective way for the modeling of sparse data process in view of the deficiencies in the prior art

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
  • Sparseness data process modeling approach
  • Sparseness data process modeling approach
  • Sparseness data process modeling approach

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] In order to better understand the technical solution of the present invention, the following uses the monosodium glutamate fermentation process as an example to model the cell concentration prediction model.

[0044] The fermentation process of monosodium glutamate is a complex biochemical reaction process. Due to the influence of on-site conditions, technological processes, testing equipment and other factors, the sample data of bacterial cell concentration is usually obtained every 3 hours, which is a sparse data process. In this fermentation process, according to actual data and the experience of on-site engineers, it is determined that the air intake volume has a certain relationship with the concentration of bacteria. Therefore, the current intake air volume and the current bacterial cell concentration are used as the two input nodes of the network, and the predicted bacterial cell concentration is the output node. The specific steps for establishing the prediction mod...

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 present invention relates to a method applying a procedure neural network to establish a procedure predicting model for sparse data. On the basis of the pretreatment of the sparse sample data, a learning algorithm based upon the discrete Walsh transform is applied to increase the learning efficiency and the modeling precision of the procedure neural network. To ensure that the established procedure predicting model can amend the prediction deviations timely, a method of data sampling periodic network rolling learning is adopted based upon the characteristics of the sparse data procedure to conduct an on-line amendment to the network predicting model timely through up-to-date sampled data, thereby improving the accuracy of the predicting model further. The present invention provides an effective approach for solving the modeling problem related to a kind of sparse data procedure.

Description

(1) Technical field [0001] The invention relates to a process modeling method using intelligent information processing technology, in particular to a sparse data process modeling method. (2) Background technology [0002] In many industrial processes, due to factors such as site conditions, technological processes and testing equipment, the time interval for collecting sample data is long, and the amount of data is limited, resulting in sparse sample data. Therefore, how to establish a process prediction model based on the characteristics of the sparse data process, and generate more continuous dense prediction data through the prediction model, which is beneficial to process control is an important research topic. [0003] At present, in system modeling, the identification modeling method represented by neural network is developing rapidly. However, most of the neural networks currently used for system modeling are feed-forward networks, which are characterized by the fact that ...

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): G06N3/02G06N3/08G05B17/02
Inventor 关守平尤富强
Owner NORTHEASTERN 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