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

Industrial process soft measurement method based on layer-by-layer data expansion deep learning

A deep learning and industrial process technology, applied in the field of soft measurement, can solve problems such as too few training samples and the inability of deep learning model technology to achieve satisfactory prediction accuracy.

Active Publication Date: 2019-08-06
CENT SOUTH UNIV
View PDF5 Cites 13 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 an industrial process soft-sensing method based on layer-by-layer data expansion deep learning to solve the problem that the existing deep learning model technology cannot achieve satisfactory prediction accuracy due to too few training samples in production practice

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
  • Industrial process soft measurement method based on layer-by-layer data expansion deep learning
  • Industrial process soft measurement method based on layer-by-layer data expansion deep learning
  • Industrial process soft measurement method based on layer-by-layer data expansion deep learning

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment 1

[0139] This embodiment shows the application of the technical solution of the present invention to the industrial process soft sensor of layer-by-layer data expansion and deep learning in the prediction of product quality in the hydrocracking process, including:

[0140] Based on the requirements of the production process, the 10% distillation point of jet fuel in the hydrocracking production process is selected as the output variable y, and 43 process variables that have a greater impact on the output variable are selected from the process through mechanism analysis as layer-by-layer data expansion deep learning The input variables of the model, as shown in Table 1, are recorded as x (1) ,x (2) ,...,x (43) . 600 data samples of the hydrocracking process were extracted as training data, and all variables were normalized.

[0141] Table 1 Selected 43 process variables that have a greater impact on the 10% distillation point of jet fuel

[0142]

[0143]

[0144]Constr...

specific Embodiment 2

[0173] This embodiment also shows that a method for predicting the quality of industrial process products of the present invention is applied to the prediction of product quality in the steel sintering process, including:

[0174] Based on the requirements of the production process, the content of ferrous oxide (FeO) is selected as the output variable y, and 19 process variables that have a great influence on the content of FeO are selected from the process through mechanism analysis as the input variables of the deep learning model for layer-by-layer data expansion, such as As shown in Table 3, denoted as x (1) ,x (2) ,...,x (19) . 1000 data samples of the steel sintering process were extracted as training data, and all variables were normalized.

[0175] Table 3 selects 19 process variables that have a greater impact on the content of ferrous oxide

[0176] Numbering Process variable description Numbering Process variable description 1 No. 1 bellows b...

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 an industrial process soft measurement method based on layer-by-layer data expansion deep learning, and belongs to the soft measurement technology field. According to the technical scheme disclosed by the invention, the sample size of the process variable is expanded by adopting the data expansion auto-encoder; a plurality of data expansion auto-encoders are stacked to forma deep network model; a large number of samples from a low level to a high level are obtained layer by layer from industrial process data, enough sample size is provided for a deep learning model, accurate prediction of product quality is achieved, the method can be widely applied to product quality prediction of complex industrial processes such as a hydrocracking process and a steel sintering process, and the method has the advantages of being high in prediction precision, good in generalization and the like.

Description

technical field [0001] The invention relates to the technical field of soft sensing, in particular to an industrial process soft sensing method based on layer-by-layer data expansion deep learning. Background technique [0002] In modern industrial production, in order to obtain the best process control strategy and realize the optimization of operating performance, it is necessary to measure and effectively detect the quality of key products in the industrial production process in real time. Traditional instruments or assays are used for detection, which have measurement lag and measuring instruments. Expensive and other shortcomings, it is difficult to meet production needs. Therefore, at present, the measurement method of soft sensor technology is generally adopted. For the process variables that are difficult to measure or cannot be measured temporarily in industrial production, by selecting and measuring other process variables that are easy to detect and closely relate...

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): G06F17/50G06N3/04G06N3/08
CPCG06N3/084G06F30/20G06N3/048G06N3/045
Inventor 袁小锋欧晨王雅琳阳春华桂卫华
Owner CENT SOUTH 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